{
  "benchmark_version": 1,
  "notes": {
    "numeric_match": "Model and runner values are matched at max(1e-6, 0.5% relative error). Each model number can match only one runner number.",
    "scope": "Values only; task prompts, inputs, model reasoning, and response prose are intentionally excluded."
  },
  "provider": "openrouter",
  "rows": [
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        46
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.443,
        1.334
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147851,
        -5645568,
        2951927
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1930
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.289,
        1080
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        14,
        2,
        0.11,
        6.28,
        1.6,
        0.006,
        -0.05,
        0.006
      ],
      "numeric_coverage": 0.05357142857142857,
      "numeric_expected_count": 56,
      "numeric_matched_count": 3,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620667,
        -3005892,
        4290790
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.52086,
        0,
        0,
        16800707.8,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        311.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.38,
        1.29
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        8000
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5750,
        0.678,
        48810,
        317.2,
        250.78,
        12650,
        0.28,
        17440,
        294.9,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4663
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.8553,
        0.6843
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": null,
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        8000
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": null,
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        3750,
        0.841,
        63680,
        325.3,
        263.78,
        8250,
        0.511,
        34380,
        306.9,
        234.53
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5750,
        0.679,
        48864,
        317.46,
        250.78,
        12650,
        0.281,
        17457,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        8864
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.63,
        11.1,
        5.63
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        197300
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.598
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.503
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.18
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5750,
        0.678,
        48839,
        250.78,
        12650,
        0.281,
        17447,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.368
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3115,
        1.049
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        3195,
        799200
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        2555
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.25,
        295,
        0.75,
        200,
        2,
        495
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        197180
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.1
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        233.5,
        0.22,
        0.45,
        50,
        576,
        3.125,
        25,
        58.7,
        1800,
        14400
      ],
      "numeric_coverage": 0.13043478260869565,
      "numeric_expected_count": 23,
      "numeric_matched_count": 3,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        169.2,
        202.2,
        236.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        30
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.8
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        233.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.323
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.502
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        16560
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        3750,
        0.841,
        63683,
        325.6,
        263.78,
        8250,
        0.511,
        34377,
        307,
        234.53
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0066,
        123,
        0.323,
        6020
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.0027
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        82
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.353
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        42.6,
        222
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2597
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.513
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        16560
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        14400
      ],
      "numeric_coverage": 0.043478260869565216,
      "numeric_expected_count": 23,
      "numeric_matched_count": 1,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        18315852.75
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": null,
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2250
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620552,
        -2992680,
        4290731
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        8.34,
        10.49
      ],
      "numeric_coverage": 0.2222222222222222,
      "numeric_expected_count": 9,
      "numeric_matched_count": 2,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.7
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        576
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        920000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        2438.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2623.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.71
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.76,
        8,
        10.49
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2701172.5,
        -4326242.8,
        3818255.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.18
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        14400
      ],
      "numeric_coverage": 0.043478260869565216,
      "numeric_expected_count": 23,
      "numeric_matched_count": 1,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.13
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588,
        -4325046,
        3817401
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        493
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        30
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        9.51,
        13.12
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        149.2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5541
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        234,
        576,
        3.67,
        2.45,
        3.13,
        58.7,
        14400
      ],
      "numeric_coverage": 0.043478260869565216,
      "numeric_expected_count": 23,
      "numeric_matched_count": 1,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        2900,
        340,
        70,
        2500
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        194.6,
        233.5,
        272.5,
        1500,
        1800,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3419,
        1.2507
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.984,
        0.787,
        0.5,
        66.67,
        83.33
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        545300
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.141592653589793,
        0.5781,
        0,
        0,
        3326720,
        3.141592653589793
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        545
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": null,
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620801,
        -3006034,
        4290826
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147835,
        -5645800,
        2951200
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0095,
        0.098,
        5.64,
        1.22,
        0.0065,
        -0.014,
        0.218,
        -0.031
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        850000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        357
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4663
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.511
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5550
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000,
        100,
        10000,
        7,
        10,
        100
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        32.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.984,
        0.787
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9470
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.2
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        13,
        37.3618,
        -121.9287
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.07
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        61.5,
        222
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        483000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [
        115
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        8.34,
        10.49
      ],
      "numeric_coverage": 0.2222222222222222,
      "numeric_expected_count": 9,
      "numeric_matched_count": 2,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963403.2,
        45.1703,
        -122.0156
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        2438.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702504,
        -4322601.5,
        3817390.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3115,
        1.0492,
        7.6,
        9.5
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.18,
        255.3
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.93
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1904,
        2603,
        3281
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        8580
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2699340,
        -4324520,
        3816630
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.3636,
        -121.8917,
        13
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.225,
        101325,
        288.15,
        0.36391,
        22632.1,
        216.65,
        0.83135,
        54049.7,
        255.65
      ],
      "numeric_coverage": 0.5333333333333333,
      "numeric_expected_count": 15,
      "numeric_matched_count": 8,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        180
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": null,
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": null,
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3115,
        9.01,
        4000,
        47.92,
        1.0492,
        9.01,
        5000,
        59.89
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.1,
        1.65,
        -0.05,
        13,
        0.007
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 18,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.594
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [
        6.12,
        8.51,
        10.7
      ],
      "numeric_coverage": 0.2222222222222222,
      "numeric_expected_count": 9,
      "numeric_matched_count": 2,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147849,
        -5646184,
        2951921
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [
        914
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2698953,
        -4322176,
        3816065
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        6.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708333333333334
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.003
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        570
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        4494.74
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.4
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.89,
        222
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        337
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.7356,
        53985,
        320.5,
        255.65,
        11000,
        0.364,
        22635,
        295,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3616001.1,
        -3005775,
        4290651.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.513
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.6,
        0.0065,
        1150000,
        12,
        -2
      ],
      "numeric_coverage": 0.05357142857142857,
      "numeric_expected_count": 56,
      "numeric_matched_count": 3,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.2887
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.4
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892.1
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        2224
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1350
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1384
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544700
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.414213562373095
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.314
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        420
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        9.6,
        627.3,
        130.7,
        8,
        584.4,
        146.1,
        6.86,
        539.6,
        157.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 18,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.984,
        0.787
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702274.5,
        -4324977.5,
        3816558.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7988
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        4259.6,
        799200
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.855,
        73.5,
        0.684,
        91.8
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.81
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.409
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1520,
        194.6,
        1500,
        2180,
        233.6,
        1800,
        2950,
        272.5,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4663
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.61
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171,
        960
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        8280
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.57814,
        0,
        3326730,
        3.141592653589793
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        528
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3623458.234,
        -3001239.712,
        4291887.341
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        1920000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.2887,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        339.55,
        288.15,
        5000,
        0.7366,
        54049.3,
        320.53,
        255.65,
        11000,
        0.3639,
        22632.1,
        294.83,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        293
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        12575
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        233.55
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9470
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147846,
        -5646438,
        2951989
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.5708
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        420,
        790,
        1280
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        7000000
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [
        12,
        4,
        0.2,
        0.098,
        1.6,
        0.006,
        -2
      ],
      "numeric_coverage": 0.05357142857142857,
      "numeric_expected_count": 56,
      "numeric_matched_count": 3,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        4,
        1.5,
        0.007
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0.08333333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 2,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1930
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        14400
      ],
      "numeric_coverage": 0.043478260869565216,
      "numeric_expected_count": 23,
      "numeric_matched_count": 1,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3415,
        1.2505
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        8580
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.00004467
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        3750,
        0.841,
        63685,
        325.57,
        263.775,
        8250,
        0.5105,
        34370,
        307,
        234.525
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [
        28084307.55
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 18,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        2435
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        1400
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        1356
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.76,
        8,
        10.49
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        807000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [
        4496
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3439,
        1.2525
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        6,
        9.4
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": null,
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.736,
        54049.7,
        320.5,
        255.65,
        11000,
        0.3639,
        22632.1,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3817,
        1.2878
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.351
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.1
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        9.51,
        13.12
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        491
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        30
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3893
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        70.9
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.7364,
        54048,
        320.6,
        255.65,
        11000,
        0.3639,
        22632,
        295.1,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [
        1040
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        268
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        490
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        27.2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        12,
        150,
        1.5,
        0.0065,
        -0.02,
        4,
        1.2,
        1000000
      ],
      "numeric_coverage": 0.05357142857142857,
      "numeric_expected_count": 56,
      "numeric_matched_count": 3,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5565
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9836,
        4000,
        63.879,
        0.7869,
        5000,
        79.849
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.409
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.9
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.414213562373095
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3997,
        1.3023
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        5000,
        11000,
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.7364,
        54044,
        320.5,
        255.65,
        11000,
        0.3639,
        22632,
        295.1,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.346
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        194.6,
        480,
        3.125,
        1500,
        233.6,
        576,
        3.125,
        1800,
        272.5,
        672,
        3.125,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3817,
        1.2879
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.218,
        0.0065,
        1.22,
        -0.065,
        6.28,
        1000000
      ],
      "numeric_coverage": 0.03571428571428571,
      "numeric_expected_count": 56,
      "numeric_matched_count": 2,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.984,
        63.9,
        0.787,
        79.8
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2699894.752,
        -4322637.089,
        3819558.66
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        60
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        530000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        9.5,
        6,
        13.1
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702828,
        -4325427,
        3817740
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3100
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.5708
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.443,
        1.334
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        7800,
        910
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": null,
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        576
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": null,
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544700
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": null,
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.1
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        194.6,
        233.5,
        272.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147849.5,
        -5645970.2,
        2953591.4
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892.4
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        16560
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        311.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.38,
        1.29
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.984
      ],
      "numeric_coverage": 0.0625,
      "numeric_expected_count": 16,
      "numeric_matched_count": 1,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1769
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.1
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        1920570
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.511
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2594
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.003
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        4260
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.003
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        337
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        88.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        231,
        2.1,
        7500,
        518,
        380,
        898
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        0.038,
        0.22,
        0.45,
        50,
        576,
        233.6,
        25,
        2.45,
        14400
      ],
      "numeric_coverage": 0.08695652173913043,
      "numeric_expected_count": 23,
      "numeric_matched_count": 2,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        233.55
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        100,
        42,
        10001.70636883,
        9840.2002082,
        9996.29651756,
        10145.28153813,
        95.15778751
      ],
      "numeric_coverage": 0.7142857142857143,
      "numeric_expected_count": 7,
      "numeric_matched_count": 5,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        15.021,
        0.01,
        28.5,
        36.12,
        39.987,
        7000000,
        25
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [
        14,
        0.0065,
        1.35,
        -0.025,
        1150000
      ],
      "numeric_coverage": 0.03571428571428571,
      "numeric_expected_count": 56,
      "numeric_matched_count": 2,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [
        6.2,
        9.8,
        13.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2700259.8,
        -4324839.2,
        3817410.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.984,
        0.63,
        14.2,
        2.4,
        0.787,
        0.71,
        22.5,
        3.9
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.152
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.344,
        1.252
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        545
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        3750,
        90,
        600
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147835.5,
        -5645985,
        2953592
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        300
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        18
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2699141,
        -4324877,
        3817150
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        3675,
        1120,
        1804,
        550,
        28.6,
        34.3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.77,
        0.46,
        213,
        376,
        8.24,
        12.88
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.032,
        798,
        1531,
        0.51,
        12580
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [
        3628.1
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        0
      ],
      "numeric_coverage": 0.041666666666666664,
      "numeric_expected_count": 24,
      "numeric_matched_count": 1,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2608
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.2887,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        46.99997265,
        11.00000019,
        0.028012655019,
        0.007218225673,
        0.002628109974,
        0.001453842364,
        0.000346060145,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.000002043706,
        0.000002043706,
        0.000002043706,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        6.8755e-8,
        6.8755e-8,
        6.8755e-8,
        6.8755e-8,
        6.8755e-8,
        5.443e-8,
        5.443e-8,
        1.9553e-8,
        1.75e-8,
        1.75e-8,
        1.75e-8,
        6.43e-10,
        6.43e-10,
        6.43e-10,
        6.43e-10,
        6.43e-10,
        1.74e-10,
        1.74e-10,
        1.74e-10,
        1.74e-10,
        3.3e-11,
        3.3e-11,
        3.3e-11,
        3.3e-11,
        3.3e-11,
        2.3e-11,
        2.3e-11,
        2.3e-11,
        2.3e-11,
        2.3e-11,
        1.3e-11,
        1.3e-11,
        1.2e-11,
        1.2e-11,
        7e-12,
        7e-12,
        6e-12,
        5e-12,
        5e-12,
        5e-12,
        3e-12,
        3e-12,
        3e-12,
        1e-12,
        0,
        0,
        0,
        0,
        0,
        0,
        0,
        0,
        0,
        42
      ],
      "numeric_coverage": 0.4583333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 11,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        32.7,
        0,
        0,
        35.1,
        0,
        60,
        37.3,
        0,
        120,
        39.5,
        0,
        180
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        415,
        1120,
        1500
      ],
      "numeric_coverage": 0.1,
      "numeric_expected_count": 10,
      "numeric_matched_count": 1,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        270,
        4.752389,
        75,
        270,
        6.734252,
        500,
        270,
        8.367126
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 9,
      "numeric_matched_count": 6,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5550
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        13,
        37.3618,
        -121.9287
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -11436,
        36.869,
        -122.015
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        2466
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.86,
        76.4,
        0,
        19.25,
        80.1,
        60,
        20.59,
        83.85,
        120,
        21.87,
        87.65,
        180
      ],
      "numeric_coverage": 0.625,
      "numeric_expected_count": 16,
      "numeric_matched_count": 10,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        6930000,
        0,
        0,
        0,
        7621.894927,
        0
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9745
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        576
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.41421356237309503
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.36
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        417.4,
        500.9,
        584.4,
        78.5,
        169.2,
        203.1,
        236.9,
        3.59375,
        90.7,
        124.6,
        158.4,
        8,
        0.22,
        0.45,
        57.5,
        28.75,
        1500,
        1800,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        9804.2,
        10195.8,
        10297.9,
        9702.1,
        10000,
        100,
        10000,
        100,
        7,
        100
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        198184
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.61
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        66,
        222
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2.1,
        0.105,
        1.35,
        0.006,
        0.015,
        0.006,
        1.35,
        -0.2,
        1150000,
        13
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.312,
        0.698,
        0,
        0.322,
        1.125,
        60,
        0.301,
        1.552,
        120,
        0.278,
        1.979,
        180
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.428
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1552000,
        6417500,
        2137500.5,
        -7036.8,
        811.1,
        2806.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        20.36,
        80,
        0,
        21.64,
        82.73,
        60,
        22.95,
        85.56,
        120,
        24.14,
        88.41,
        180
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 16,
      "numeric_matched_count": 8,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        30
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        13,
        37.3623,
        -121.929
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        495000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47.03,
        11.01
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -654.2,
        36.952345,
        -122.004567
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        11670
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        247,
        200000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.4
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0254,
        630,
        0.338,
        8390,
        13.3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.65,
        0.62,
        174,
        276,
        5.5,
        8.55
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": null,
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1120,
        1650,
        2280,
        78.2,
        91.8,
        106.5,
        1500,
        1800,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171,
        960
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        11.5,
        0.0078,
        0.18,
        1.12,
        -0.048,
        1000000
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3988,
        1.3016
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2701154,
        -4325150,
        3817457
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 15,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": null,
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        14,
        37.3615,
        -121.9275
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        1000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [
        11.5,
        270,
        5.120295,
        115,
        270,
        7.102158,
        575,
        270,
        8.487421
      ],
      "numeric_coverage": 0.7777777777777778,
      "numeric_expected_count": 9,
      "numeric_matched_count": 7,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        11400
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        22
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 8,
      "numeric_matched_count": 8,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        152.3,
        175.8,
        199.4,
        78.2,
        102.5,
        127.1,
        194.6,
        233.6,
        272.5,
        1500,
        1800,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.5781,
        0,
        0,
        3326.73,
        180
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        210,
        152,
        138,
        315
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.225,
        101325,
        340.3,
        288.15,
        0.841,
        63660,
        325.6,
        263.8,
        0.51,
        34380,
        307,
        234.5
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        1920030
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.6,
        8.58,
        0.0266,
        759,
        0.401,
        1143,
        50,
        18.63,
        12.65
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3623311.2,
        -3006500.7,
        4295443.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        4495,
        12335
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 5,
      "numeric_matched_count": 2,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4663
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 8,
      "numeric_matched_count": 8,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": null,
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        780,
        29,
        1300
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.47,
        138,
        0.334,
        8285,
        511.4
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.8314,
        54049.9,
        320.5,
        255.65,
        11000,
        0.3639,
        22632.1,
        295.07,
        216.65
      ],
      "numeric_coverage": 0.9333333333333333,
      "numeric_expected_count": 15,
      "numeric_matched_count": 14,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -964000,
        45.17,
        -122
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2593
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 8,
      "numeric_matched_count": 8,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 8,
      "numeric_matched_count": 8,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        15
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        542000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        1350
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        46.99997265,
        11.00000019,
        0,
        42
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 24,
      "numeric_matched_count": 3,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": null,
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        330,
        45,
        230,
        32,
        560,
        77
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        0.038,
        0.22,
        0.45,
        50,
        576,
        50,
        233.6,
        75,
        25,
        2.45,
        1800,
        14400
      ],
      "numeric_coverage": 0.13043478260869565,
      "numeric_expected_count": 23,
      "numeric_matched_count": 3,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        45,
        135,
        35,
        230,
        75,
        235,
        55,
        255,
        120,
        370
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.7364,
        54049,
        295.1,
        255.65,
        11000,
        0.3639,
        22632,
        295.08,
        216.65
      ],
      "numeric_coverage": 0.9333333333333333,
      "numeric_expected_count": 15,
      "numeric_matched_count": 14,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        0
      ],
      "numeric_coverage": 0.08333333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 2,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2700247.2,
        -4325208.3,
        3817595.4
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.417,
        0.334,
        20,
        0.498,
        4000,
        5000,
        47.9,
        59.9
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        545000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3817,
        1.2879
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.361
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        4,
        16,
        3,
        22885500,
        3540000,
        22607200,
        3510000,
        23054100,
        3580000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.225,
        101325,
        288.15,
        0.364,
        22632.1,
        216.65,
        0.736,
        54049,
        255.65
      ],
      "numeric_coverage": 0.6,
      "numeric_expected_count": 15,
      "numeric_matched_count": 9,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        828,
        500,
        38,
        750,
        18000,
        2400
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        520
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 56,
      "numeric_matched_count": 56,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        311.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3817,
        1.2878
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        55,
        624,
        337,
        450
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        5.75,
        75,
        7.75,
        500,
        9.39
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 9,
      "numeric_matched_count": 3,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.36,
        293.931
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171,
        960
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        768,
        37.5,
        0.038,
        311.4,
        56.25,
        2.34375,
        78.32,
        3.263,
        14400
      ],
      "numeric_coverage": 0.043478260869565216,
      "numeric_expected_count": 23,
      "numeric_matched_count": 1,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.1
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.78,
        75,
        337,
        2800
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.3619,
        -121.9288,
        14
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.47,
        0.0054,
        134,
        0.338,
        8390
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        8000
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [
        115,
        11500,
        11500,
        115,
        7,
        115
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        270,
        5,
        100,
        270,
        6.981863,
        500,
        270,
        8.367126
      ],
      "numeric_coverage": 0.7777777777777778,
      "numeric_expected_count": 9,
      "numeric_matched_count": 7,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        8.3,
        10.4
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.343891,
        1.252489
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        58
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        311.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.5781,
        0,
        0,
        3326878.5,
        180
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [
        115,
        11500,
        7,
        11274.5,
        11725.5,
        11500,
        115,
        115
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.12,
        0,
        0.0000451,
        200000,
        200000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.67,
        233.6,
        576,
        2.45,
        58.74,
        14400
      ],
      "numeric_coverage": 0.043478260869565216,
      "numeric_expected_count": 23,
      "numeric_matched_count": 1,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1500,
        1800,
        2100,
        3480,
        3850,
        4220,
        1250,
        1420,
        1600,
        242.1,
        268.5,
        294.3
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        52.331,
        26.922
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        1850
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544820
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4663
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147784,
        -5644237,
        2952782
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        625,
        159.5,
        38.2,
        85,
        625
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.87
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0.520845,
        0,
        16799300,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        30
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 18,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        15.0214,
        0.01,
        28.5,
        39.9868,
        7000000,
        36.118
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        470
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.67,
        233.5,
        576,
        2.45,
        0.333,
        58.74
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": null,
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.289
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        546
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [
        11272.18,
        11727.82,
        115,
        11500,
        11500,
        115,
        7,
        115
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        55
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        204
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.3615,
        -121.9288,
        13
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.98,
        0.79,
        67.8,
        71.5,
        84.5,
        108.3,
        1.78,
        2.12
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        1667
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5550
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147820.5,
        -5645200.5,
        2953100.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": null,
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 18,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.414213562373095
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 7,
      "numeric_matched_count": 7,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        799200,
        53.2,
        3193,
        250
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.49999159,
        11.99998624,
        1e-12,
        42
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2699628.343,
        -4324879.227,
        3818515.809
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        233.55
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        139,
        650,
        1340
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7988
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": null,
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.08,
        5.06403,
        -0.506403,
        -0.8,
        0.12,
        0.2
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702492.5,
        -4325164.3,
        3817085.4
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4974188376711329,
        0.6981317007977318,
        0,
        0.5112,
        0.7123,
        60,
        0.525,
        0.7281,
        120,
        0.5388,
        0.7439,
        180
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.9672,
        0,
        0.02305,
        2.76,
        2000,
        0,
        0,
        0.0132,
        1.5738,
        0.2759,
        0.03013,
        7.05,
        2500,
        0.00528,
        0.097,
        0.0269,
        1.3115,
        0.9,
        0.03485,
        14.08,
        3000,
        0.02495,
        0.661,
        0.0448
      ],
      "numeric_coverage": 0.0625,
      "numeric_expected_count": 16,
      "numeric_matched_count": 1,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1041.8
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.414213562373095
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0.08333333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 2,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.8203,
        11
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.382,
        1.288
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        8.34,
        10.49
      ],
      "numeric_coverage": 0.2222222222222222,
      "numeric_expected_count": 9,
      "numeric_matched_count": 2,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 7,
      "numeric_matched_count": 7,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.6,
        0.00594,
        110.4,
        0.323,
        6014.5,
        1.47
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.44,
        1.33
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        6,
        8.5,
        10.4
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": null,
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.5708
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        46.99997265,
        11.00000019,
        0.028012655019,
        0.007218225673,
        0.002628109974,
        0.001453842364,
        0.000346060145,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.000031839124,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.00000944756,
        0.000002043706,
        0.000002043706,
        0.000002043706,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        4.48408e-7,
        6.8755e-8,
        6.8755e-8,
        6.8755e-8,
        6.8755e-8,
        6.8755e-8,
        5.443e-8,
        5.443e-8,
        1.9553e-8,
        1.75e-8,
        1.75e-8,
        1.75e-8,
        6.43e-10,
        6.43e-10,
        6.43e-10,
        6.43e-10,
        6.43e-10,
        1.74e-10,
        1.74e-10,
        1.74e-10,
        1.74e-10,
        3.3e-11,
        3.3e-11,
        3.3e-11,
        3.3e-11,
        3.3e-11,
        2.3e-11,
        2.3e-11,
        2.3e-11,
        2.3e-11,
        2.3e-11,
        1.3e-11,
        1.3e-11,
        1.2e-11,
        1.2e-11,
        7e-12,
        7e-12,
        6e-12,
        5e-12,
        5e-12,
        5e-12,
        3e-12,
        3e-12,
        3e-12,
        1e-12,
        0,
        0,
        0,
        0,
        0,
        0,
        0,
        0,
        0,
        42
      ],
      "numeric_coverage": 0.4583333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 11,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000,
        100,
        7,
        100,
        9702.822,
        10297.178,
        10000,
        100
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        940
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.87,
        0,
        0,
        18.64,
        0,
        60,
        19.39,
        0,
        120,
        20.13,
        0,
        180
      ],
      "numeric_coverage": 0.3125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 5,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907223,
        7220415,
        2771857,
        -6445.2,
        570.5,
        2948.7
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.93
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": null,
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.11,
        6.283,
        1.58,
        0.007,
        -0.05,
        12,
        -2
      ],
      "numeric_coverage": 0.05357142857142857,
      "numeric_expected_count": 56,
      "numeric_matched_count": 3,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4663
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.11
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2,
        16,
        0.007,
        1.22,
        0.11,
        -0.04,
        1000000,
        14
      ],
      "numeric_coverage": 0.05357142857142857,
      "numeric_expected_count": 56,
      "numeric_matched_count": 3,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.31,
        0.31,
        5.7,
        0.18,
        1.05,
        0.37,
        8.9,
        0.32
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        417.4,
        500.9,
        584.4,
        78.5,
        78.5,
        78.5,
        169.2,
        203.1,
        236.9,
        90.8,
        124.6,
        158.5,
        1500,
        1800,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        131.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        3360000,
        3420000,
        4,
        0.775,
        0.791,
        21200000,
        22000000,
        2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.52085,
        0,
        16800735.5,
        0
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3439,
        1.2525
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.89,
        53.2,
        3195,
        919.1,
        255.3
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        700
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.815,
        10800,
        0.82,
        11000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 8,
      "numeric_matched_count": 8,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [
        4496.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        5000,
        11000,
        0,
        1.225,
        101325,
        340.3,
        288.15,
        5000,
        0.7364,
        54049,
        320.5,
        255.66,
        11000,
        0.3639,
        22632,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        540
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        88.2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.31,
        0.25,
        1.8,
        0.45,
        1.05,
        0.23,
        3.2,
        0.75
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 2,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.381,
        1.287
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        6930000,
        0,
        0,
        0,
        7621.894927,
        0
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.012,
        0.104,
        1.6,
        0.006,
        -0.038,
        -0.035,
        13,
        -2
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        124,
        1520,
        768
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9692
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4,
        0.04,
        0.12,
        0.4,
        0.04,
        0.4,
        0.3,
        0.09,
        0.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.8,
        12,
        0.0075,
        0.095,
        1.12,
        -0.045
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        46
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000.2,
        99.7,
        10000,
        100,
        100,
        10000,
        7,
        100
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.1
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        75,
        626,
        338,
        5000,
        55,
        500,
        270,
        4000,
        130,
        1126,
        608,
        9000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.41421356237
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3891.2
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        2160,
        3150
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        233,
        2700,
        1250
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.38,
        1.29
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        28.5,
        40,
        0,
        28.5,
        52.3,
        60,
        28.5,
        71.1,
        180
      ],
      "numeric_coverage": 0.1875,
      "numeric_expected_count": 16,
      "numeric_matched_count": 3,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        46.99997265,
        11.00000019,
        0,
        42
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 24,
      "numeric_matched_count": 3,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        3000,
        3500,
        544000,
        2700,
        3100,
        435000,
        5700,
        6600,
        979000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        8000
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        280
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.225,
        101325,
        340.3,
        288.15,
        0.841,
        63710,
        325.5,
        263.78,
        0.51,
        34360,
        307,
        234.53
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        6010
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        337
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 18,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        255.3,
        46.4,
        330
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 7,
      "numeric_matched_count": 7,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        460,
        75,
        2500,
        620
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [
        1500
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.08,
        5.06403,
        -0.506403,
        -0.8,
        0.12
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620758,
        -3003823,
        4320084
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        13.5,
        -2.3,
        1.12,
        -0.021,
        750000
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        550000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        46.1,
        799200
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5550
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.171
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.1
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.41421356237
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        7500,
        75,
        100,
        7500,
        7,
        75
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        49.2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147806,
        -5644771,
        2952708
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.0027,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        9835.5,
        10164.5,
        10000,
        100,
        7,
        100,
        10000,
        100
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.006,
        149,
        0.346,
        8583
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        2435
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1120
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        3380,
        1.9,
        640,
        259.5,
        1500,
        4860,
        2.7,
        768,
        311.4,
        1800,
        6590,
        3.7,
        896,
        363.3,
        2100,
        8,
        0.22,
        0.45,
        37.5,
        9.81,
        18.75,
        1.225,
        1500,
        1800,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        60
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 9,
      "numeric_matched_count": 9,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.38,
        1.29
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 12,
      "numeric_matched_count": 0,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0.08333333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 2,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 56,
      "numeric_matched_count": 42,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4142135623730951
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 4,
      "numeric_matched_count": 4,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        100,
        7,
        7499.17729109,
        7378.76865298,
        7497.68096111,
        7625.99315268,
        75.29451859
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.52
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": null,
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.289,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        -0.53
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        55
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0,
        0,
        0,
        7000000,
        0
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        35.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        3200,
        3900,
        4,
        5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2160
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 23,
      "numeric_matched_count": 0,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.520835,
        0,
        0,
        16800700.5,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.00541,
        134,
        0.338,
        8388
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.58
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.003,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [
        310
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.4,
        0.02,
        0.12,
        0,
        0.12,
        0.25,
        0.035,
        0.1
      ],
      "numeric_coverage": 0.375,
      "numeric_expected_count": 8,
      "numeric_matched_count": 3,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        7702,
        7298,
        100,
        7500,
        7385,
        7420,
        7615,
        7580,
        7500.12,
        74.9,
        7,
        75
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        0
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 24,
      "numeric_matched_count": 3,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        13,
        4,
        37.3668,
        -121.93
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        543,
        293,
        367,
        198,
        910,
        491
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": null,
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        145
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3892.3,
        18990
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 5,
      "numeric_matched_count": 2,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        46
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        230,
        500000,
        2174,
        1500
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.7266,
        18988,
        3892.1,
        24421137
      ],
      "numeric_coverage": 0.6,
      "numeric_expected_count": 5,
      "numeric_matched_count": 3,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 56,
      "numeric_matched_count": 56,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": true,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0.041666666666666664,
      "numeric_expected_count": 24,
      "numeric_matched_count": 1,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 8,
      "numeric_matched_count": 8,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2698250,
        -4321200,
        3816660
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": null,
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -958250,
        45.232,
        -122.005
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": null,
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        398600441800000,
        5250000,
        5250000,
        7425000,
        766,
        1800,
        90
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        181,
        232.9,
        284.8,
        640,
        768,
        896,
        1500,
        1800,
        2100,
        12000,
        14400,
        16800
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        687.5,
        116.1,
        480,
        1500,
        1225.6,
        155.1,
        576,
        1800,
        1918.1,
        194,
        672,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": null,
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.19
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "nemotron-skills",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708333333,
        1.1,
        770,
        700,
        1.3,
        130,
        100,
        1.4,
        224,
        160,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        268,
        205,
        473
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.2621737752,
        0.01,
        180,
        0.49741883681838395,
        0.6221510626,
        0.6979017467,
        7000000,
        0.6339251501
      ],
      "numeric_coverage": 0.03571428571428571,
      "numeric_expected_count": 28,
      "numeric_matched_count": 1,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        442.9,
        196200,
        196.2,
        2,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.602,
        1531.25,
        4.63,
        0.00594,
        110.5,
        0.323,
        6013
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        9,
        181,
        212,
        243,
        166,
        197,
        228,
        150,
        181,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 18,
      "numeric_matched_count": 9,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.2,
        37.0000124,
        0.6457710418,
        -121.9999591,
        -2.1293001238
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.6,
        1531.25,
        5.1,
        0.0062,
        177,
        0.409,
        11674
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.095321,
        0,
        0,
        0.0949,
        1.39972,
        1.302318
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        75,
        268,
        70,
        205,
        145,
        473
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        1099
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        3750,
        0.8396,
        63549.6,
        325.522,
        263.775,
        8250,
        0.51,
        34331,
        307.001,
        234.525
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        1.578,
        94.7,
        140.7
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.1097,
        6.283,
        -2.08,
        -0.053,
        750000
      ],
      "numeric_coverage": 0.017857142857142856,
      "numeric_expected_count": 56,
      "numeric_matched_count": 1,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.4691,
        1531.25,
        4.708,
        0.00576,
        143,
        0.329,
        8155
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.0606601717798214,
        0.4142135623730951,
        0.5522847498307935
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        1565.5,
        -6872.5,
        -1413,
        0,
        7546.1,
        1565.5,
        1413,
        6872.5,
        0,
        6164750,
        1800,
        3131.1,
        90
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.311475,
        7.6,
        66.666667,
        4000,
        47.909288,
        2.631579,
        1.04918,
        9.5,
        83.333333,
        5000,
        59.88661,
        2.105263
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907236,
        7220460,
        2771882,
        -6436.94,
        601.462,
        2960.583
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3324554.8,
        -2760098.6,
        4675748.8
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        1004.4,
        7036.7,
        1004.4,
        2008.7,
        -6599.2,
        -904,
        0,
        904,
        6599.2,
        0,
        7291800,
        2070,
        90
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8,
        -4325046.2,
        3817399.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        1.18,
        71,
        187.7,
        39.24
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        0
      ],
      "numeric_coverage": 0.08333333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 2,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        8,
        37.5,
        2.34375,
        0,
        56.25,
        18.75,
        14400,
        1800,
        0,
        1800,
        8,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        0
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.5,
        768,
        311.397,
        56.25,
        1.5,
        1800,
        0,
        8,
        2.34375,
        78.314,
        14400,
        48,
        32
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        60
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [
        3615,
        1102
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.2,
        37.000012,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3531.66,
        1177.71,
        31.445,
        836.53,
        161.68,
        8,
        43.337,
        233.964,
        229.914,
        768,
        37.5,
        2339.75,
        58.282,
        311.397,
        56.25,
        2.34375
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.09,
        2952020.14
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.645,
        -5646761.173,
        2952028.023
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.866,
        76.406,
        0,
        19.274,
        79.844,
        60,
        20.61,
        83.31,
        120,
        21.866,
        86.906,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        5214262,
        1920357,
        7134618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        2160,
        15,
        16560,
        14400,
        270
      ],
      "numeric_coverage": 0.08695652173913043,
      "numeric_expected_count": 23,
      "numeric_matched_count": 2,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        240,
        160,
        40,
        30,
        200
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907235,
        7220448,
        2771878,
        -6436.938,
        601.462,
        2960.583
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        255.3,
        10.6,
        1449
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.834710744,
        0.834710744,
        0.469414602,
        0.469414602,
        0.09388292,
        0,
        0,
        0.09388292,
        1.381714537,
        1.287831616
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 12,
      "numeric_matched_count": 4,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7979,
        2432
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        799200,
        222,
        1.18,
        71,
        4258,
        187.7
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1003.11
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        268,
        55,
        2200,
        80
      ],
      "numeric_coverage": 0.18181818181818182,
      "numeric_expected_count": 11,
      "numeric_matched_count": 2,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        100,
        500,
        6,
        8.34,
        11.12
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        45
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        6936434.5,
        7134618.34,
        198183.84,
        0,
        0,
        106.507,
        -0.446,
        -106.506,
        0
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        15.02145,
        0.01,
        28.5,
        39.986825,
        7000000,
        36.3212,
        180,
        0.02145,
        -0.013175
      ],
      "numeric_coverage": 0.03571428571428571,
      "numeric_expected_count": 28,
      "numeric_matched_count": 1,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.36
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.0027070064,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.1
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.834,
        -4325046.225,
        3817399.181
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544360
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        268,
        205,
        473
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.9,
        52.3,
        26.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        268,
        49.7,
        187.6
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.33354,
        0.31161,
        558298,
        0,
        1.3983,
        0.33815,
        560505,
        60,
        1.46006,
        0.36163,
        562854,
        120,
        1.52302,
        0.38345,
        565457,
        180
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 16,
      "numeric_matched_count": 8,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        15,
        288.15,
        3750,
        0.84096,
        63675.2,
        -9.375,
        263.775,
        8250,
        0.50996,
        34331,
        -38.625,
        234.525
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        1544.78,
        600.38,
        23.58,
        354.04,
        93.86,
        8,
        32.5,
        152.82,
        1177.3,
        41.33
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [
        4390
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.08,
        2952020.13
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.095321017,
        0,
        0,
        0.094899536,
        1.399720042,
        1.302318393
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.602,
        1531.25,
        0.0785,
        4.499,
        0.00622,
        116,
        0.314,
        5845
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.68623101,
        0.466287835,
        0.405467683
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.469,
        1531.25,
        4.707,
        0.00575,
        143,
        0.329,
        8152
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3531.66,
        1178.04,
        31.445,
        37.5,
        836.539,
        161.663,
        8,
        43.338,
        233.961,
        229.914,
        768,
        2340.8,
        58.282,
        311.397
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.45,
        6417151.06,
        2127485.9,
        -7037.62,
        810.29,
        2793.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.275
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9380
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708333333,
        1.1,
        770,
        700,
        1.3,
        130,
        100,
        1.4,
        224,
        160,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        2000
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702594.131,
        -4325054.706,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        600,
        220,
        2.8,
        0.68,
        0.12,
        0.8,
        442.87,
        2,
        1.321,
        10000
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        442.9,
        196200,
        196.2,
        2,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9836,
        0.1144,
        -10.72,
        0.188,
        22.66,
        11.94,
        10.1333,
        66.6667,
        4000,
        63.8794,
        0.7869,
        0.1144,
        -6.52,
        0.235,
        18.46,
        11.94,
        12.6667,
        83.3333,
        5000,
        79.8496,
        20
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.3,
        6417151.6,
        2127484.9,
        -7037.6,
        810.3,
        2793.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        576,
        50,
        3.671,
        75,
        2.447,
        3.125,
        58.735,
        8,
        0,
        1800,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0938829,
        0,
        0,
        0.0938829,
        1.3817145,
        1.2878316
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.405,
        0,
        -17.748,
        255.871,
        60,
        18.193,
        76.749,
        120,
        -18.077,
        256.2,
        180
      ],
      "numeric_coverage": 0.375,
      "numeric_expected_count": 16,
      "numeric_matched_count": 6,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135623730951,
        0.41421356237309515,
        0.41421356237309515
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1530,
        499,
        21.7,
        547,
        109,
        78.2,
        155,
        8,
        950,
        -82.4,
        158,
        40.2
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1739.7,
        627.7,
        23.6,
        548.9,
        121.2,
        156.2,
        8,
        1240,
        187.6,
        42.4
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8,
        -4325046.1,
        3817399.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": true,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2592.54
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        50,
        576,
        58.73,
        75,
        3.125,
        8,
        1800,
        14400
      ],
      "numeric_coverage": 0.13043478260869565,
      "numeric_expected_count": 23,
      "numeric_matched_count": 3,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.4691,
        1531.25,
        8148,
        0.08212,
        4.705,
        1.003,
        0.00575,
        0.3285
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        -6872.4,
        -1413.3,
        0,
        1413.3,
        6872.4,
        0,
        1800,
        90,
        0.2412,
        6165000
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [
        15.058707,
        0.0075,
        28.5,
        41.782536,
        39.963941,
        5250000,
        42.359229,
        180,
        3,
        60
      ],
      "numeric_coverage": 0.07142857142857142,
      "numeric_expected_count": 28,
      "numeric_matched_count": 2,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.0027070064,
        433.125,
        130,
        224,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.59,
        1531.25,
        4.93,
        0.99,
        0.00683,
        195,
        0.396,
        11290
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.4691,
        1531.25,
        4.843,
        0.00541,
        134,
        0.338,
        8384
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.08,
        2952020.14
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.09,
        2952020.14
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        5000,
        0.73612,
        54019.9,
        320.529,
        255.65,
        11000,
        0.363918,
        22632.1,
        295.069,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7424621.202458749,
        5250000,
        5250000,
        1800,
        90,
        1.5707963267948966
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.785,
        -0.359
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        20,
        0.983607,
        36.48,
        10.133333,
        -0.973684,
        66.666667,
        4000,
        63.879051,
        0.786885,
        45.6,
        12.666667,
        -0.578947,
        83.333333,
        5000,
        79.848814,
        0.152
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        268,
        45,
        75,
        1,
        205,
        40,
        70,
        2,
        473,
        85,
        145
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1400,
        475,
        21,
        530,
        125,
        146,
        8,
        39,
        860,
        146
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.4691,
        1531.25,
        4.707,
        0.00575,
        142.7,
        0.3286,
        8151
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        6936434.5,
        198183.8,
        0,
        0,
        106.5,
        44.6,
        -96.7,
        0,
        7134618.4
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [
        1367.821,
        2262.007,
        3629.828,
        6.5054,
        23419.443
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 5,
      "numeric_matched_count": 4,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        76.406,
        17.861,
        0,
        81.836,
        19.997,
        60,
        87.41,
        21.946,
        120,
        93.133,
        23.683,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.183,
        71,
        215.8,
        255.3
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        120,
        150,
        180,
        195,
        30,
        45
      ],
      "numeric_coverage": 0.5714285714285714,
      "numeric_expected_count": 7,
      "numeric_matched_count": 4,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.093883,
        0,
        0,
        0.093883,
        1.381714,
        1.287832
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.311475,
        7.6,
        66.666667,
        4000,
        2.631579,
        1.04918,
        9.5,
        83.333333,
        5000,
        2.105263
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.83,
        -4325046.22,
        3817399.17
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.45,
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.000014123,
        0,
        180,
        6999901.15,
        180
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        -25,
        -38.32,
        25,
        47,
        412.22,
        116.17,
        480,
        1100.36,
        3.125,
        1500,
        557.42,
        155.1,
        576,
        1783.84,
        3.125,
        1800,
        702.63,
        194.02,
        672,
        2621.93,
        3.125,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.686231,
        0.466288,
        0.405468
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        100,
        500,
        6,
        8.34,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        5,
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.0075,
        28.5,
        40,
        5250000,
        0,
        25,
        15.618828,
        0.0075,
        28.5,
        39.619906,
        5250000,
        60,
        204.98651,
        16.237656,
        0.0075,
        28.5,
        39.239812,
        5250000,
        120,
        26.444912,
        16.856484,
        0.0075,
        28.5,
        38.859719,
        5250000,
        180,
        206.392907
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7980,
        2432
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5750,
        0.6782,
        48820.9,
        250.775,
        12650,
        0.2805,
        17447.2,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.5895,
        1531.25,
        4.992,
        0.00661,
        189,
        0.4008,
        11436
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        177.6,
        799200,
        222,
        268.1,
        0.662,
        39.7,
        187.7,
        71,
        39.23
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 6,
      "numeric_matched_count": 2,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.00001412,
        0,
        0,
        6999901.14,
        6999901.14,
        180
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9380
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3531.65,
        31.445,
        836.53,
        161.67,
        233.963,
        8,
        43.338,
        229.914,
        1177.72,
        768,
        37.5,
        266.731,
        58.282,
        43.338,
        -263.187,
        2340.81,
        56.25,
        2.34375
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40,
        60,
        240,
        260
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.29,
        288.15,
        5750,
        0.6782,
        48821,
        317.46,
        250.775,
        12650,
        0.2805,
        17447.2,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.83,
        -4325046.23,
        3817405.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5000,
        0.7361,
        54019.5,
        255.65,
        11000,
        0.3639,
        22632.1,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.83471074,
        0,
        0,
        0.83471074,
        0.4694146,
        0,
        0,
        0.4694146,
        0.09388292,
        0,
        0,
        0.09388292,
        1.38171452,
        1.2878316
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 12,
      "numeric_matched_count": 4,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        5214262,
        1920356,
        7134618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        576,
        58.73,
        3.125,
        8,
        0,
        1800,
        14400,
        50,
        75
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        433.125,
        525,
        1.0027070063694268,
        130,
        100,
        224,
        160,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        25551.4,
        0.520854,
        0,
        8050,
        12242.9,
        16800.7,
        0
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.9,
        52.3,
        26.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.1097,
        -4,
        -0.211,
        -2,
        0.009,
        0,
        0.228,
        2,
        0.447,
        4,
        0.667,
        6,
        0.886,
        8,
        1.105,
        -2.08,
        1000000
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 56,
      "numeric_matched_count": 8,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        20.363,
        75.204,
        0,
        21.695,
        63.124,
        60,
        22.972,
        51.096,
        120,
        24.191,
        39.122,
        180
      ],
      "numeric_coverage": 0.5625,
      "numeric_expected_count": 16,
      "numeric_matched_count": 9,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0914027149,
        0,
        0,
        0.0914027149,
        1.3438914027,
        1.2524886878
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        15,
        288.15,
        5000,
        0.7361,
        54019.9,
        320.529,
        -17.5,
        255.65,
        11000,
        0.3639,
        22632.1,
        295.069,
        -56.5,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.602,
        1531.25,
        5846,
        0.0785,
        4.498,
        0.00623,
        0.314
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0938829204,
        0,
        0,
        0.0938829204,
        1.3817145352,
        1.2878316159,
        2
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7980
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7017,
        -6873,
        -1413,
        0,
        7017,
        1413,
        6873,
        0,
        1800,
        90,
        6160000
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        75,
        500,
        5.76,
        8,
        10.49
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 9,
      "numeric_matched_count": 3,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        220,
        2157.46,
        2.71,
        3.54,
        0.83,
        0.71,
        442.87,
        2,
        1.306,
        575.73,
        10000
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963438.2,
        45.16975,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.01,
        28.5,
        40,
        7000000,
        0,
        25,
        15.00715,
        0.01,
        28.5,
        39.995608,
        7000000,
        60,
        28.778461,
        15.014301,
        0.01,
        28.5,
        39.991216,
        7000000,
        120,
        32.552309,
        15.021451,
        0.01,
        28.5,
        39.986825,
        7000000,
        180,
        36.323507
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        48,
        271,
        75,
        1,
        38,
        207,
        65,
        2,
        86,
        478,
        140
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        2160,
        15,
        16560,
        14400
      ],
      "numeric_coverage": 0.08695652173913043,
      "numeric_expected_count": 23,
      "numeric_matched_count": 2,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.46,
        6417151.05,
        2127485.89,
        -7037.62,
        810.29,
        2793.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        3180,
        4500,
        545000,
        2100,
        496000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.179
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135623730951,
        0.41421356237309515,
        0.41421356237309515
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2592.5
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7975
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        100,
        500,
        6,
        8.34,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.31174,
        1.33353,
        0,
        0.33655,
        1.39391,
        60,
        0.35989,
        1.45506,
        120,
        0.38179,
        1.51723,
        180
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290775.3
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.5,
        56.25,
        2.34375,
        18.75,
        0.038013,
        1643,
        624,
        164,
        1018,
        1500,
        21.7,
        2200,
        793,
        205,
        1407,
        1800,
        23.9,
        2735,
        968,
        243,
        1767,
        2100,
        25.5
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.089,
        2952020.138
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        100,
        500,
        6,
        8.335,
        10.55
      ],
      "numeric_coverage": 0.4444444444444444,
      "numeric_expected_count": 9,
      "numeric_matched_count": 4,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        181,
        212,
        243,
        165.5,
        196.5,
        227.5,
        150,
        181,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 18,
      "numeric_matched_count": 9,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [
        3680
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        770,
        700,
        1.1708333333,
        130,
        100,
        224,
        160,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805,
        6417152,
        2127486,
        -7037.62,
        810.29,
        2793.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        7353.0027,
        7646.9973,
        7500,
        7500,
        75,
        100,
        7,
        7.5
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.000014124,
        0,
        0,
        6999901.133,
        6999901.134,
        52822000000,
        180
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9836,
        10.1333,
        -0.9737,
        66.6667,
        4000,
        63.8791,
        0.7869,
        12.6667,
        -0.5789,
        83.3333,
        5000,
        79.8487
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        496000,
        380000,
        876000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        120,
        30,
        45,
        180,
        195
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        20,
        7894.737,
        0.984,
        10.133,
        -0.974,
        66.667,
        4000,
        0.787,
        12.667,
        -0.579,
        83.333,
        5000,
        0.152
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.686231,
        0.466288,
        0.405467
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        20.363,
        75.204,
        0,
        21.695,
        63.124,
        60,
        22.973,
        51.097,
        120,
        24.191,
        39.123,
        180
      ],
      "numeric_coverage": 0.5625,
      "numeric_expected_count": 16,
      "numeric_matched_count": 9,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9836,
        36.48,
        10.1333,
        66.6667,
        4000,
        1.9737,
        0.7869,
        45.6,
        12.6667,
        83.3333,
        5000,
        1.5789
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2160,
        13.0434782609,
        8,
        0,
        2070,
        16560,
        115,
        8,
        1800,
        0,
        14400
      ],
      "numeric_coverage": 0.21739130434782608,
      "numeric_expected_count": 23,
      "numeric_matched_count": 5,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        255.3,
        1.183,
        71,
        215.8
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        268,
        0.828,
        49.7,
        188
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.4691,
        1531.25,
        4.707,
        0.00575,
        143,
        0.3286,
        8153,
        1.4727
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.0606601717798214,
        0.41421356237309515,
        0.5522847498307935
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40,
        240,
        60,
        260
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1435,
        540,
        146,
        1800,
        21.1,
        -475,
        -33.1,
        1500,
        495,
        34.5,
        2100,
        960,
        402,
        111,
        1500,
        18.5,
        1435,
        540,
        146,
        1800,
        21.1,
        1930,
        676,
        179,
        2100,
        23.3
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1420,
        465,
        20.8,
        0,
        550,
        115,
        77.5,
        50,
        146,
        8,
        576,
        3.125,
        0.038
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8,
        -4325046.2,
        3817423.3
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [
        16.85649,
        0.0075,
        28.5,
        206.77685,
        38.85972,
        5250000,
        206.39287,
        180,
        3
      ],
      "numeric_coverage": 0.03571428571428571,
      "numeric_expected_count": 28,
      "numeric_matched_count": 1,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        1466.8,
        2425.7,
        3892.6,
        18990.2,
        5.2751
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 5,
      "numeric_matched_count": 4,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5000,
        0.7361,
        54019.9,
        255.65,
        11000,
        0.3639,
        22632.1,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.93
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.125,
        58.7,
        50,
        75,
        1800,
        8,
        0,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2592.5
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.2887,
        1.265,
        1018.325,
        805,
        1.3,
        149.5,
        115,
        1.4,
        224,
        160,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963438.2,
        45.169752,
        -122.00004
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.6
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        383.54,
        1.5,
        110324.81,
        110.32,
        7500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        56,
        268,
        80,
        50,
        205,
        70,
        106,
        473,
        150
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5630
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.83,
        -4325046.22,
        3817399.17
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        383.535,
        110324.813,
        1.5,
        7500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        6936434.554,
        198183.844,
        7134618.398
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        50,
        -145.21,
        412.22,
        116.17,
        480,
        1500,
        -38.92,
        0,
        557.42,
        155.1,
        576,
        1800,
        0,
        145.21,
        702.63,
        194.02,
        672,
        2100,
        38.92,
        75,
        3.125
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        442.9,
        196133,
        650,
        0.509,
        2.509,
        3.391,
        1.3516,
        0.882,
        2,
        10000
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135623730951,
        0.4142135623730951,
        0.4142135623730951
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.5,
        0,
        56.25,
        2.34375,
        14400,
        8,
        0,
        0,
        1800,
        14400,
        48,
        32
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.5,
        8,
        181.05,
        259.5,
        655,
        1500,
        232.95,
        311.4,
        848.8,
        1800,
        284.85,
        363.3,
        1042.5,
        2100,
        56.25,
        2.34375
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        474.9,
        2.3,
        259386,
        112776,
        11500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        20.36,
        75.204,
        0,
        21.69,
        77.915,
        60,
        22.97,
        80.679,
        120,
        24.19,
        83.494,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        1693.657,
        2800.852,
        4494.509,
        18315852.75,
        3.426251,
        12334.504
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135623730951,
        0.41421356237309515,
        0.41421356237309515
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8,
        -4325046.3,
        3817399.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.3,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        2325.39,
        -35.66,
        654.224,
        181.044,
        1500,
        3614.47,
        0,
        847.832,
        232.944,
        1800,
        5178.22,
        43.26,
        1041.439,
        284.844,
        2100
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 10,
      "numeric_matched_count": 5,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.288727,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9635,
        7980,
        2432
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 5,
      "numeric_matched_count": 2,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.1,
        37.0000107,
        -121.9999599
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2425.7,
        1466.8,
        3892.6,
        24421137,
        5.275,
        18990.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0914027149,
        0,
        0,
        0.0914027149,
        1.3438914027,
        1.2524886878
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.29,
        288.15,
        5000,
        0.73612,
        54019.9,
        320.53,
        255.65,
        11000,
        0.36392,
        22632.1,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        0.22,
        0.45,
        50,
        25,
        13420.845,
        3147.516,
        448.881,
        10273.329,
        1500,
        19507.779,
        3839.782,
        554.347,
        15667.997,
        1800,
        26728.969,
        4532.047,
        659.814,
        22196.922,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.404,
        0,
        19.997,
        81.836,
        60,
        21.946,
        87.413,
        120,
        23.684,
        93.134,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708333333,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963438,
        45.16975,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.29,
        288.15,
        5000,
        0.7361,
        54019.9,
        320.53,
        255.65,
        11000,
        0.3639,
        22632.1,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.406,
        0,
        19.275,
        79.851,
        60,
        20.612,
        83.347,
        120,
        21.867,
        86.906,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.261799388,
        0.01,
        0.497418837,
        0.698131701,
        7000000,
        0,
        0.436332313,
        0.261924183,
        0.01,
        0.497418837,
        0.69805505,
        7000000,
        60,
        0.502238835,
        0.262048978,
        0.01,
        0.497418837,
        0.697978399,
        7000000,
        120,
        0.568104929,
        0.262173773,
        0.01,
        0.497418837,
        0.697901748,
        7000000,
        180,
        0.633924819,
        0.000002079917,
        0.001078965,
        -0.000001277514
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        5750,
        0.678203,
        48820.9,
        317.459,
        250.775,
        12650,
        0.278701,
        17464.4,
        296.191,
        218.3
      ],
      "numeric_coverage": 0.8666666666666667,
      "numeric_expected_count": 15,
      "numeric_matched_count": 13,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135623730951,
        0.41421356237309515,
        0.41421356237309515
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.22,
        37.0000124,
        0.64577204,
        -121.9999599,
        -2.12930099
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        799200,
        222,
        71,
        4258,
        187.7
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.4,
        6417151,
        2127485.9,
        -7037.6,
        810.3,
        2793.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        412.22,
        116.17,
        1500,
        557.42,
        155.1,
        1800,
        702.63,
        194.02,
        2100,
        8,
        50,
        75,
        3.125,
        1800
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5635
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        55,
        75,
        268,
        45,
        65,
        205,
        100,
        140,
        473
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.142857,
        10,
        6,
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 9,
      "numeric_matched_count": 6,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708333333,
        1.1,
        770,
        700,
        1.3,
        130,
        100,
        1.4,
        224,
        160,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        57.5,
        317.516,
        90.784,
        1500,
        443.782,
        124.632,
        1800,
        570.047,
        158.479,
        2100,
        86.25,
        3.59375
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.36
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.2,
        37.0000124,
        -122.0000401
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        770,
        700,
        1.1708333333,
        130,
        100,
        224,
        160,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        4500,
        497000,
        3900,
        380000,
        8400,
        877000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5640
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        76.407,
        17.862,
        6936434,
        0,
        79.845,
        19.275,
        6938482,
        60,
        83.344,
        20.612,
        6940790,
        120,
        86.885,
        21.866,
        6943349,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.000014123918,
        -0.000014123918,
        0,
        0,
        0,
        3.14159265359,
        3.14159265359,
        6999901.134,
        6999901.134,
        52822000000,
        3.14159265359
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805,
        6417152,
        2127486,
        -7037.621,
        810.293,
        2793.188
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        50,
        58.73,
        75,
        3.125,
        8,
        0,
        1800,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955571,
        36.97588,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.3115,
        -1.6316,
        7.6,
        66.6667,
        4000,
        47.9093,
        1.0492,
        -1.1053,
        9.5,
        83.3333,
        5000,
        59.8869
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.654,
        -0.349
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.3
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7651000,
        1565,
        -6873,
        -1413,
        0,
        1565,
        1413,
        6873,
        0,
        0.241,
        4679000,
        6165000,
        1800,
        3130,
        90
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        50,
        75,
        268,
        290
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        2280,
        4200,
        496000,
        1,
        1800,
        3900,
        380000,
        2,
        4080,
        8100,
        876000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        3600,
        4800,
        540000,
        2500,
        496000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        3900,
        5100,
        530000,
        2500,
        496000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544359
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        268,
        55,
        2500,
        75,
        32000
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1100.29,
        412.22,
        116.17,
        1500,
        1783.85,
        557.42,
        155.09,
        1800,
        2621.91,
        702.63,
        194.02,
        2100,
        1800,
        -38.3,
        -26,
        -25.1,
        47,
        26,
        25.1
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955556,
        36.975893,
        -122.00004
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.57,
        36.99996898,
        -122.0000401
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        75,
        267,
        1,
        65,
        205,
        2,
        140,
        472
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.83471074,
        0,
        0,
        0.83471074,
        0.4694146,
        0,
        0,
        0.4694146,
        0.09388292,
        0,
        0,
        0.09388292,
        1.38171454,
        1.28783161
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 12,
      "numeric_matched_count": 4,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        268
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544360
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        55,
        75,
        269
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135623730951,
        0.4142135623730951,
        0.4142135623730951
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9380
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1018.325,
        805,
        1.288727,
        149.5,
        115,
        224,
        160,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        5,
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        383.535,
        110324.8125,
        1.5,
        7500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        1.577,
        94.6,
        140.8,
        29.43
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        3750,
        0.84096,
        63675.1,
        325.583,
        263.775,
        8250,
        0.50996,
        34330.9,
        307.001,
        234.525
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        20,
        0.152,
        0.98361,
        10.1333,
        -0.97368,
        66.6667,
        4000,
        63.8794,
        0.78689,
        12.6667,
        -0.57895,
        83.3333,
        5000,
        79.8492,
        0.49836,
        7894.74
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0001191712,
        -0.0000731967,
        36.3212,
        15.0214508,
        0.01,
        28.5,
        35.646631,
        39.9868246,
        7000000,
        180,
        60
      ],
      "numeric_coverage": 0.07142857142857142,
      "numeric_expected_count": 28,
      "numeric_matched_count": 2,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.0606601717798214,
        0.4142135623730951,
        0.5522847498307935
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        1566,
        1566,
        0.2412,
        -6872,
        -1413,
        0,
        1413,
        6872,
        0,
        6164700,
        1800,
        3132,
        90
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0914027149321267,
        0,
        0,
        0.0914027149321267,
        1.343891402714932,
        1.2524886877828054
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        308,
        268
      ],
      "numeric_coverage": 0.18181818181818182,
      "numeric_expected_count": 11,
      "numeric_matched_count": 2,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        9,
        3,
        181,
        212,
        243,
        165.5,
        196.5,
        227.5,
        150,
        181,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 18,
      "numeric_matched_count": 9,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7975
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570.2,
        36.975869,
        -121.994578
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.1,
        250,
        2.27,
        0.27,
        2.72,
        0.45,
        442.87,
        2,
        1.198,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        15.021451,
        0.01,
        28.5,
        35.6466,
        39.986825,
        7000000,
        36.321263,
        180,
        0.000002079928,
        0.001078965,
        -0.000001277522
      ],
      "numeric_coverage": 0.03571428571428571,
      "numeric_expected_count": 28,
      "numeric_matched_count": 1,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        50,
        58.7,
        0,
        75,
        1800,
        0,
        8,
        3.125,
        14400,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.406,
        0,
        19.275,
        79.245,
        60,
        20.612,
        83.346,
        120,
        21.867,
        86.907,
        180
      ],
      "numeric_coverage": 0.6875,
      "numeric_expected_count": 16,
      "numeric_matched_count": 11,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 10,
      "numeric_matched_count": 0,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.095321017,
        0,
        0,
        0.094899536,
        1.399720041,
        1.302318393
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        268,
        80,
        207,
        75,
        475,
        155
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1395.2,
        461.2,
        20.8,
        533.1,
        117.6,
        146.4,
        8,
        30.4,
        143.2
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.58
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.0115,
        32.775,
        40,
        8050000,
        0,
        25,
        15.003884,
        0.0115,
        32.775,
        39.997424,
        8050000,
        60,
        28.069538,
        15.007767,
        0.0115,
        32.775,
        39.994847,
        8050000,
        120,
        31.137315,
        15.011651,
        0.0115,
        32.775,
        39.992271,
        8050000,
        180,
        34.198828,
        15.011651,
        0.0115,
        32.775,
        39.992271,
        8050000,
        180,
        34.198828
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        7965910,
        906500,
        4.275,
        831292,
        4.275,
        2.747,
        850000,
        7134618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "terra-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.57,
        94.5,
        141,
        222
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0873,
        5,
        -0.00873,
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        288.8,
        36.9,
        187.7,
        222,
        46.1
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        90.37,
        48.79,
        25.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -4,
        0.0095,
        -0.22,
        -0.05,
        -2,
        0.009,
        0,
        -0.05,
        0,
        0.0095,
        0.22,
        -0.05,
        2,
        0.0109,
        0.44,
        -0.05,
        4,
        0.0134,
        0.66,
        -0.05,
        6,
        0.0167,
        0.88,
        -0.05,
        8,
        0.0211,
        1.1,
        -0.05,
        10,
        0.0264,
        1.32,
        -0.05,
        1000000
      ],
      "numeric_coverage": 0.44642857142857145,
      "numeric_expected_count": 56,
      "numeric_matched_count": 25,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.98,
        -0.498
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.78,
        -0.359
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.09388292,
        0,
        0,
        0.09388292,
        1.381714536,
        1.287831616,
        0.834710744,
        0,
        0,
        0.834710744,
        1,
        1,
        0.166942149,
        0,
        0,
        0.166942149,
        0.834710744,
        0.834710744,
        0.469414602,
        0,
        0,
        0.469414602,
        2,
        1.8,
        0.09388292,
        0,
        0,
        0.09388292,
        1.381714536,
        1.287831616
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 8,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -4,
        0.009,
        -0.22,
        -0.05,
        -2,
        0.008,
        0,
        -0.05,
        0,
        0.0084,
        0.22,
        -0.05,
        2,
        0.0097,
        0.44,
        -0.05,
        4,
        0.0119,
        0.66,
        -0.05,
        6,
        0.015,
        0.88,
        -0.05,
        8,
        0.0189,
        1.1,
        -0.05,
        10,
        0.023,
        1.28,
        -0.05,
        12,
        0.031,
        1.4,
        -0.05,
        14,
        0.045,
        1.45,
        -0.04,
        16,
        0.07,
        1.25,
        -0.02,
        1000000,
        1.45,
        0.11,
        0.008,
        14,
        -2
      ],
      "numeric_coverage": 0.48214285714285715,
      "numeric_expected_count": 56,
      "numeric_matched_count": 27,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544362
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        268
      ],
      "numeric_coverage": 0.18181818181818182,
      "numeric_expected_count": 11,
      "numeric_matched_count": 2,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.2
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0015,
        4.275,
        850000,
        7965910,
        906484,
        2.7475,
        831292,
        7134618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.833,
        -4325046.227,
        3817399.179
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5000,
        0.736116,
        54019.9,
        255.65,
        11000,
        0.363918,
        22632.1,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        1430,
        475,
        21.1,
        535,
        118,
        30.7,
        57.5,
        147.7,
        8,
        144.5,
        86.25,
        2.447,
        82,
        0.03801
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        200,
        1.824,
        1.216,
        0.324,
        383.54,
        1.5,
        7500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.204,
        37.0000124,
        -121.9999598
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [
        11.5,
        115,
        575,
        6.12,
        8.5,
        10.71
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.406,
        0,
        19.997,
        81.836,
        60,
        21.946,
        87.411,
        120,
        23.683,
        93.133,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        9804.004,
        10195.996,
        10000,
        100,
        10000,
        100,
        7,
        10
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [
        0
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_system_status/boundary",
      "trial_id": "flight-planning/get_system_status/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1390,
        533,
        117,
        30.6,
        50,
        145.7,
        8,
        142.4,
        880,
        145,
        2.45,
        13000,
        0.038,
        20.8,
        38.5
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.34375,
        2192.22,
        37.5,
        4.89417,
        768,
        78.3142,
        311.397,
        0,
        14400,
        3288.33,
        56.25,
        3.26278,
        0.0380133,
        8,
        1800,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        5,
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        8,
        50,
        3.671,
        576,
        58.716,
        26.19,
        14.193,
        0,
        75,
        2.447,
        3.125,
        0.038013,
        14400,
        1800,
        0,
        1800,
        8,
        0,
        8.000001,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.000014124,
        0,
        180,
        6999901.1,
        52822000000,
        180
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.089,
        2952020.138
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3074.661,
        42164137,
        2425.732,
        7725.76,
        6678137,
        1466.824,
        3892.557,
        1607.837,
        0.72654275,
        10151.492,
        24421137,
        18990.212
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        5000,
        0.736116,
        54019.9,
        320.529,
        255.65,
        11000,
        0.363918,
        22632,
        295.069,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [
        3060
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570,
        36.97587,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        20,
        2,
        0.305,
        0.07306,
        0.152,
        0.4984,
        0.9836,
        10.133,
        0.1969,
        66.937,
        -0.9737,
        66.667,
        63.879,
        4000,
        0.7869,
        12.667,
        0.2421,
        82.315,
        -0.5789,
        83.333,
        79.849,
        5000,
        7894.7
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        500,
        1,
        2200,
        1.25,
        2000,
        1800,
        2600
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.261799388,
        0.01,
        0.497418837,
        0.4279374,
        0.698131701,
        7000000,
        0,
        0.436332313,
        0.261924185,
        0.01,
        0.497418837,
        0.492675287,
        0.698055049,
        7000000,
        60,
        0.5022401,
        0.262048982,
        0.01,
        0.497418837,
        0.557413175,
        0.697978398,
        7000000,
        120,
        0.5681062,
        0.262173779,
        0.01,
        0.497418837,
        0.622151062,
        0.697901746,
        7000000,
        180,
        0.633926,
        0.00000207995,
        0.00107896479,
        -0.00000127752
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        19
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7016.3,
        -6872.5,
        -1413.1,
        0,
        7016.3,
        1413.1,
        6872.5,
        0,
        90
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.01,
        28.5,
        24.519,
        40,
        7000000,
        0,
        25,
        15.0071,
        0.01,
        28.5,
        28.2282,
        39.9956,
        7000000,
        60,
        28.7762,
        15.0143,
        0.01,
        28.5,
        31.9374,
        39.9912,
        7000000,
        120,
        32.5502,
        15.0214,
        0.01,
        28.5,
        35.6466,
        39.9868,
        7000000,
        180,
        36.3213,
        0.0000020797,
        0.0010789647,
        -0.0000012776
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        9,
        243,
        150,
        181,
        212,
        243,
        165.5,
        196.5,
        227.5,
        150,
        181,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 18,
      "numeric_matched_count": 9,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.686231,
        0.46628783,
        0.40546768
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.3,
        -5646746.2,
        2952020.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.592,
        -0.3444
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.125,
        8,
        50,
        3.671,
        26.193,
        576,
        233.548,
        75,
        2.447,
        14.193,
        58.74,
        1800,
        14400,
        155.095
      ],
      "numeric_coverage": 0.13043478260869565,
      "numeric_expected_count": 23,
      "numeric_matched_count": 3,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        -38.32,
        0,
        46.98,
        1100.29,
        412.22,
        116.17,
        688.08,
        480,
        2.039,
        1500,
        19.846,
        1783.89,
        557.42,
        155.095,
        1226.47,
        576,
        2.447,
        1800,
        23.815,
        2621.91,
        702.63,
        194.019,
        1919.28,
        672,
        2.855,
        2100,
        27.784,
        50,
        75,
        3.125,
        0.038013
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135624,
        0.4142135624,
        0.4142135624
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.17,
        -0.115,
        -0.595
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.92
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        20.363,
        75.204,
        0,
        21.695,
        77.914,
        60,
        22.972,
        80.677,
        120,
        24.191,
        83.494,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708,
        960,
        1124
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.46,
        6417151.07,
        2127485.9,
        -7037.62,
        810.292,
        2793.189
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        268,
        1.4,
        289,
        205,
        1.2,
        221,
        473,
        2.6,
        510
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        -6872.5,
        -1413.2,
        0,
        9899494.94,
        1413.2,
        6872.5,
        0,
        5806120,
        -32330000,
        1.570796327
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        40,
        240
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        398600441800000,
        0.00007292115,
        76.405,
        17.861,
        0,
        25,
        79.845,
        19.275,
        60,
        28.773,
        83.345,
        20.612,
        120,
        32.544,
        86.906,
        21.866,
        180,
        36.311
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.5,
        6417151.1,
        2127485.9,
        -7037.62,
        810.29,
        2793.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        5,
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/safety",
      "trial_id": "aerodynamics/calculate_stability_derivatives/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8,
        -4325046.2,
        3817399.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        25551415.5,
        0,
        0.520853519,
        0,
        8050000,
        0,
        12242870.8,
        16800707.8,
        69857095000,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        60,
        260
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1018.325,
        149.5,
        1.28873,
        224,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        398600441800000,
        6050000,
        6661,
        -6599,
        -904,
        0,
        6661,
        904,
        6599,
        0,
        0,
        2520000,
        6879,
        5096,
        4621,
        0,
        6879,
        -4621,
        -5096,
        0,
        0,
        2070,
        90
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        47.03752565,
        10.97583384,
        0.004560086105,
        0.002456404809,
        0.002220171811,
        0.00212665086,
        0.00044154997,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000043067397,
        0.000031234487,
        0.000031234487,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000011206835,
        0.000002758259,
        0.000002758259,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/variation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        20,
        20,
        7,
        0,
        0
      ],
      "numeric_coverage": 0.041666666666666664,
      "numeric_expected_count": 24,
      "numeric_matched_count": 1,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        33.943,
        -118.408,
        37.364,
        -121.929,
        3300,
        4500,
        3600,
        4200,
        5700,
        4800,
        505000,
        570000,
        530000,
        6000,
        9160,
        7270,
        1900,
        2900,
        2300,
        496000
      ],
      "numeric_coverage": 0.36363636363636365,
      "numeric_expected_count": 11,
      "numeric_matched_count": 4,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.469,
        1531.25,
        4.707,
        142.7,
        0.00575,
        57.1,
        8152,
        0.329
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.00000112973,
        0.0008746276,
        -7.49462e-7,
        6378137,
        398600441800000,
        0.00108262668,
        15,
        0.0115,
        32.775,
        24.447407,
        40,
        8050000,
        0,
        25,
        15.003884,
        0.0115,
        32.775,
        27.454155,
        39.997424,
        8050000,
        60,
        28.069643,
        15.007767,
        0.0115,
        32.775,
        30.460903,
        39.994847,
        8050000,
        120,
        31.137325,
        15.011651,
        0.0115,
        32.775,
        33.467651,
        39.992271,
        8050000,
        180,
        34.203167
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.469,
        1531.25,
        142.6,
        8149,
        4.706,
        1.002,
        0.00575,
        0.329
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/lqr_controller_design/validation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        50,
        -38.32,
        412.22,
        116.17,
        1100.29,
        2.039,
        1500,
        19.846,
        0,
        557.42,
        155.09,
        1783.89,
        2.447,
        1800,
        23.815,
        46.98,
        702.63,
        194.02,
        2621.91,
        2.855,
        2100,
        27.784,
        75,
        3.125,
        0.03801
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1400,
        533,
        118,
        30.5,
        50,
        146.5,
        8,
        143.3,
        873,
        477,
        145,
        75,
        0.038,
        20.9,
        38.6
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/safety",
      "trial_id": "aerodynamics/get_airfoil_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.22875,
        0.3,
        1.31148,
        11.94,
        29.09,
        -17.15,
        -1.63158,
        7.6,
        0.1526,
        51.918,
        47.909,
        4000,
        0.24,
        1.04918,
        11.94,
        23.99,
        -12.05,
        -1.10526,
        9.5,
        0.1855,
        63.138,
        59.887,
        5000,
        0.49836,
        0.114,
        20
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.520853519,
        0,
        0,
        16800707.8,
        69857095000,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        682,
        313,
        87.9,
        1.773,
        1500,
        16.6,
        1078,
        435,
        119.2,
        2.128,
        1800,
        19.2,
        1510,
        555,
        149.7,
        2.482,
        2100,
        21.6,
        57.5,
        86.25,
        3.59375,
        0.03801,
        -396,
        -36.7,
        1500,
        0,
        0,
        1800,
        432,
        40.1,
        2100
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        500,
        0.95,
        0.75,
        1.25,
        1,
        2600,
        1900,
        5200,
        3800
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.0115,
        32.775,
        24.4474,
        40,
        8050000,
        0,
        25,
        15.003884,
        0.0115,
        32.775,
        27.454149,
        39.997424,
        8050000,
        60,
        28.069536,
        15.007769,
        0.0115,
        32.775,
        30.460897,
        39.994847,
        8050000,
        120,
        31.13732,
        15.011653,
        0.0115,
        32.775,
        33.467646,
        39.992271,
        8050000,
        180,
        34.20317,
        0.000064737,
        0.050112478,
        -0.000042941
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        9.80665,
        1.5,
        3.125,
        0.038013,
        8,
        0.22,
        0.45,
        50,
        75,
        25,
        1500,
        1800,
        2100,
        -38.32,
        412.22,
        116.17,
        480,
        48.947,
        2.039,
        1500,
        19.846,
        1100.29,
        0,
        557.42,
        155.095,
        576,
        58.736,
        2.447,
        1800,
        23.815,
        1783.85,
        46.98,
        702.63,
        194.019,
        672,
        68.524,
        2.855,
        2100,
        27.784,
        2621.91
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.204,
        0.6457720403,
        37.00001244,
        -2.1293009864,
        -121.99995983
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        202000,
        198000,
        6936434.553,
        7134618.398,
        0,
        -106.506,
        0,
        0,
        198183.844,
        -0.446,
        198183.844,
        106.507
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        37,
        -122
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.33,
        267,
        294,
        1,
        1.25,
        206,
        227,
        2,
        2.58,
        473,
        521
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.09532102,
        0,
        0,
        0.09489954,
        1.39972004,
        1.30231839,
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 12,
      "numeric_matched_count": 6,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        6378137,
        398600441800000,
        0.00108262668,
        0.000119171,
        0.06182013,
        -0.0000731967,
        15,
        0.01,
        28.5,
        24.519,
        40,
        7000000,
        0,
        25,
        15.0071503,
        0.01,
        28.5,
        28.2282077,
        39.9956082,
        7000000,
        60,
        28.7762,
        15.0143005,
        0.01,
        28.5,
        31.9374154,
        39.9912164,
        7000000,
        120,
        32.5501,
        15.0214508,
        0.01,
        28.5,
        35.6466231,
        39.9868246,
        7000000,
        180,
        36.3213
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.0000141239,
        0,
        0,
        6999901.134,
        180
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.5
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        302.3,
        16.1,
        19.52,
        10.039
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/boundary",
      "trial_id": "aircraft-performance/landing_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.00011918,
        0.001078965,
        -0.0000732,
        15,
        0.01,
        28.5,
        40,
        7000000,
        0,
        25,
        15.007151,
        0.01,
        28.5,
        39.995608,
        7000000,
        60,
        28.776182,
        15.014302,
        0.01,
        28.5,
        39.991216,
        7000000,
        120,
        32.550033,
        15.021453,
        0.01,
        28.5,
        39.986824,
        7000000,
        180,
        36.321237
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/safety",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9,
        1.2,
        267,
        285
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        255.3,
        1.183,
        71,
        215.8,
        45.13
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570.4,
        36.97587,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        5.76,
        75,
        8,
        500,
        10.49
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 9,
      "numeric_matched_count": 3,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        5,
        7,
        700,
        2157.46,
        11.6,
        9.68,
        2.68,
        5783,
        500,
        5.27,
        2,
        0.277,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        6936434.55,
        198183.84,
        7134618.4
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2200,
        795,
        112,
        37.5,
        207,
        8,
        466,
        840,
        159,
        23.9,
        47.3
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.602,
        1531.25,
        4.344,
        1.234,
        0.00653,
        121.5,
        0.303,
        5642
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        1450,
        21.3,
        535,
        118,
        30.7,
        57.5,
        8,
        145,
        486,
        39.4,
        904,
        153
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.58
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7087000,
        0.544,
        2091000,
        3229000,
        4589000,
        0,
        0,
        35878000000,
        -43430,
        -6834,
        -4276,
        0,
        398600441800000,
        4276,
        6834,
        0,
        5250000,
        0,
        0,
        0,
        5250000,
        0,
        1800,
        90
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.5
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.333533,
        0,
        0.311736,
        0.436332,
        1.393565,
        60,
        0.33641,
        0.502181,
        1.454656,
        120,
        0.359747,
        0.567989,
        1.516813,
        180,
        0.38164,
        0.633751
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0914027,
        0,
        0,
        0.0914027,
        0.7916667,
        0.7916667,
        1.3438914,
        1.2524887,
        1.3438914,
        1.2524887
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 12,
      "numeric_matched_count": 6,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.83,
        -4325046.23,
        3817399.18
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.002707,
        785,
        787.125
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963438,
        45.169752,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2070,
        7279127.671543,
        3888.888889,
        0,
        -3888.888889,
        -7279127.671543,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        8534250,
        -6599,
        -904.4,
        0,
        904.4,
        6599,
        0,
        0.17046,
        6048650,
        7079710,
        7291450,
        -27334,
        90,
        8534250,
        8050000,
        6660.7
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/variation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        56.06,
        1.58,
        94.7,
        140.7,
        29.43
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        46
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        3750,
        0.842635,
        63802.1,
        263.775,
        8250,
        0.50997,
        34331.7,
        234.525
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/boundary",
      "trial_id": "flight-planning/search_airports/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        0
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        267,
        205,
        472
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.834710744,
        0.834710744,
        1.381714536,
        1.287831617,
        0.09388292,
        0,
        0,
        0.09388292,
        1.381714536,
        1.287831617
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 12,
      "numeric_matched_count": 6,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        5000,
        120,
        129.3,
        66.5
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 4,
      "numeric_matched_count": 2,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.3,
        -5646746.1,
        2952020.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.46,
        6417151.07,
        2127485.91,
        1551805.46,
        6417151.07,
        2127485.91,
        -7037.62,
        810.292,
        2793.189,
        -7037.62,
        810.292,
        2793.189
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        496000,
        380000,
        876000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/get_airfoil_database/boundary",
      "trial_id": "aerodynamics/get_airfoil_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/safety",
      "trial_id": "aircraft-performance/true_airspeed_converter/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        5250000,
        3.141592653589793,
        0,
        3.141592653589793,
        0.57813096,
        0,
        3.141592653589793,
        1403440.2,
        2214812.47,
        3326720.1,
        3.141592653589793
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        3.125,
        2922.9,
        50,
        3.671,
        576,
        58.74,
        233.55,
        0,
        4384.4,
        75,
        2.447,
        1.5,
        0.03801,
        14400,
        8,
        0,
        1800,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3074.66,
        42164137,
        2425.73,
        7725.76,
        6678137,
        1466.82,
        3892.56,
        1607.84,
        10151.49,
        24421137,
        18990.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.2502,
        -5646746.0891,
        2952020.138
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.09,
        2952020.14
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/boundary",
      "trial_id": "coordinate-frames/geodetic_to_ecef/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.28873,
        1018.325,
        149.5,
        224,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        19,
        37.3626,
        -121.929
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/nominal",
      "trial_id": "flight-planning/search_airports/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        1646,
        626.9,
        164.1,
        65.3,
        1500,
        21.7,
        2215,
        798.8,
        205.8,
        78.3,
        1800,
        23.9,
        2756,
        968.9,
        245.3,
        91.4,
        2100,
        25.6,
        2.34375,
        0.038
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        8,
        768,
        37.5,
        4.894,
        56.25,
        3.262,
        2.34375,
        0.03801,
        78.31,
        1800,
        14400
      ],
      "numeric_coverage": 0.13043478260869565,
      "numeric_expected_count": 23,
      "numeric_matched_count": 3,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        398600441800000,
        3074.6613,
        2425.7322,
        7725.7602,
        6678137,
        42164137,
        1466.8243,
        3892.5565,
        1607.837,
        0.726542748,
        10151.4924,
        24421137,
        18990.21,
        5.27506
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135624,
        -1.4142135624,
        0.4142135624,
        0.4142135624
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.3,
        -5646746.1,
        2952020.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135624,
        0.4142135624,
        0.4142135624
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.204,
        37.00001244,
        0.6457720404,
        -121.99995984,
        -2.1293009865
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9,
        1.25,
        2200,
        268,
        295
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.3,
        0.85531,
        11.6533,
        -0.71625,
        76.1347,
        66.6667,
        73.4609,
        4000,
        0.68425,
        14.5667,
        -0.373,
        93.9789,
        83.3333,
        91.8261,
        5000,
        0.35075,
        0.49836,
        0.1748,
        20
      ],
      "numeric_coverage": 0.3125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 5,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        58,
        6950,
        535,
        1900,
        2700,
        80,
        2200,
        496
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/safety",
      "trial_id": "flight-planning/plan_flight/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5638
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        1466.82,
        2425.73,
        42164137,
        6678137,
        3892.56,
        24421137,
        18990.2,
        5.27506
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        33.943,
        -118.408,
        37.364,
        -121.929,
        4200,
        5100,
        535000,
        2400,
        496000
      ],
      "numeric_coverage": 0.36363636363636365,
      "numeric_expected_count": 11,
      "numeric_matched_count": 4,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.447,
        90,
        1.5708
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.28873,
        1391.825,
        1080
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/variation",
      "trial_id": "aircraft-performance/weight_and_balance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        1693.74,
        2800.99,
        4494.74,
        18315852.75,
        12334.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        182,
        700,
        12,
        0.6,
        3.72,
        1.12,
        443,
        5,
        2,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7651700,
        7016.2,
        -6872.5,
        -1413.2,
        0,
        7016.2,
        1413.2,
        6872.5,
        0,
        0.2412,
        1565.5,
        1565.5,
        3131,
        7651700,
        7000000,
        4677800,
        5806100,
        6164800,
        1800,
        1.570796327
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/validation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        84307,
        7979,
        2432,
        0.9635,
        1228
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 5,
      "numeric_matched_count": 2,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9380
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/optimize_thrust_profile/validation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0000141239181,
        0,
        6999901.134,
        3.141592653589793
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/optimize_launch_angle/validation",
      "trial_id": "rocket-analysis/optimize_launch_angle/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.9635,
        7978,
        2432,
        84306,
        1226
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 5,
      "numeric_matched_count": 2,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        0.4984,
        7894.7368,
        0.9836,
        0.1952,
        10.1333,
        -0.9737,
        66.9365,
        66.6667,
        63.8791,
        4000,
        1.9737,
        0.7869,
        0.24,
        12.6667,
        -0.5789,
        82.3152,
        83.3333,
        79.8484,
        5000,
        1.5789,
        0.152,
        0.4984,
        20
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.09388292,
        0,
        0,
        0.09388292,
        1.381714536,
        1.287831616
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.5,
        129.3
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.8347107438,
        0,
        0,
        0.8347107438,
        1,
        1,
        0.1669421488,
        0,
        0,
        0.1669421488,
        0.8347107438,
        0.8347107438,
        0.4694146021,
        0,
        0,
        0.4694146021,
        2,
        1.8,
        0.0938829204,
        0,
        0,
        0.0938829204,
        1.3817145363,
        1.2878316159,
        0.0938829204,
        0,
        0,
        0.0938829204,
        1.3817145363,
        1.2878316159
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 8,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.5,
        6417151.1,
        2127486.9,
        -7037.62,
        810.29,
        2793.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2592.6
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.89,
        1.24,
        268,
        289,
        0.74,
        1.09,
        205,
        221,
        1.63,
        2.33,
        473,
        510
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        20995200,
        12960000,
        181,
        201.666667,
        222.333333,
        243,
        170.666667,
        191.333333,
        212,
        232.666667,
        160.333333,
        181,
        201.666667,
        222.333333,
        150,
        170.666667,
        191.333333,
        212,
        15638400,
        17424000,
        19209600,
        20995200,
        14745600,
        16531200,
        18316800,
        20102400,
        13852800,
        15638400,
        17424000,
        19209600,
        12960000,
        14745600,
        16531200,
        18316800
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 32,
      "numeric_matched_count": 16,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        2100,
        6640,
        496000,
        3720,
        4800,
        536000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/nominal",
      "trial_id": "flight-planning/plan_flight/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.09029,
        5.173,
        -0.01038,
        -0.5949,
        -0.115
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        267,
        1,
        205,
        2,
        472
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/safety",
      "trial_id": "flight-planning/plan_multi_leg_flight/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        200,
        1961.33,
        1.559,
        1.896,
        0.337,
        0.059,
        383.54,
        1.5,
        1.216,
        7500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        268,
        380,
        205,
        2,
        876,
        473
      ],
      "numeric_coverage": 0.2727272727272727,
      "numeric_expected_count": 11,
      "numeric_matched_count": 3,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        919080,
        255.3,
        1.183,
        71,
        215.8,
        45.13
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        3.1922,
        3.59375,
        57.5,
        16560,
        2160,
        15,
        86.25,
        2.1281,
        1800,
        6.9565,
        2070,
        8,
        0,
        1800,
        14400
      ],
      "numeric_coverage": 0.2608695652173913,
      "numeric_expected_count": 23,
      "numeric_matched_count": 6,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.0027,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/nominal",
      "trial_id": "flight-planning/convert_units/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/get_atmosphere_profile/validation",
      "trial_id": "atmosphere/get_atmosphere_profile/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1440,
        470,
        540,
        118,
        148,
        8,
        576,
        860,
        39.3,
        3.125,
        0.038,
        21.1
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        1693.743,
        2800.994,
        5008602.75,
        31623102.75,
        4494.737,
        0.726542748,
        18315852.75,
        12334.504
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        7353.003,
        7646.997,
        7500,
        7.5,
        7500,
        100,
        7,
        75
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/safety",
      "trial_id": "aircraft-performance/takeoff_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.170620639,
        0,
        0,
        0.170588235,
        1,
        1,
        0.853103195,
        0.852941176,
        0.095321017,
        0,
        0,
        0.094899536,
        2,
        1.8,
        1.399720042,
        1.302318393,
        0.095321017,
        0,
        0,
        0.094899536,
        1.399720042,
        1.302318393
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 8,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        313,
        87.9,
        -122,
        -31.3,
        -396,
        681,
        1500,
        435,
        119.2,
        0,
        0,
        0,
        1077,
        1800,
        555,
        149.7,
        120,
        30.5,
        433,
        1510,
        2100,
        0.404,
        0.103,
        1.382
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.29,
        288.15,
        5000,
        0.736116,
        54019.9,
        320.53,
        255.65,
        11000,
        0.363918,
        22632,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        375,
        202.5,
        1700,
        2300,
        0.75,
        2000,
        1,
        6320
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 4,
      "numeric_matched_count": 2,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.94,
        52.35,
        26.93
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0914027149,
        0,
        0,
        0.0914027149,
        1.3438914027,
        1.2524886878,
        0.1583333333,
        0,
        0,
        0.1583333333,
        0.0914027149,
        0,
        0,
        0.0914027149,
        0.7916666667,
        0.7916666667,
        1.3438914027,
        1.2524886878
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 12,
      "numeric_matched_count": 6,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        799200,
        639360,
        268,
        39.8,
        71,
        187.6
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        500,
        0.85,
        1.1,
        2300,
        1800,
        2800,
        230
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        48.14368299,
        11.01835951,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0045600861,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0021157266,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.0002761557,
        0.000276155749,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/variation",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        800,
        1961.33,
        0.2,
        3.3,
        1.11,
        1.3,
        2170,
        442.9,
        200,
        10.9,
        6.17,
        2,
        1.504,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [
        1166524.4,
        4823905.6,
        1599285.7,
        -8109.96,
        925.08,
        3215.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        5828.52,
        6936435,
        7614.89,
        198184,
        106.51,
        202000,
        0.000044604,
        198000,
        9.2,
        6080.09,
        7134618,
        7508.38
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/nominal",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        1.2,
        1.5,
        268,
        281,
        1,
        1.3,
        205,
        215,
        2.2,
        2.8,
        473,
        496
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/variation",
      "trial_id": "flight-planning/plan_multi_leg_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1879.541,
        -47.49,
        986.947,
        1500,
        -24.386,
        1421.203,
        1800,
        2.92,
        1934.415,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        317.516,
        90.784,
        1.773,
        1500,
        737.731,
        443.782,
        124.632,
        2.127,
        1800,
        1235.873,
        570.047,
        158.479,
        2.482,
        2100,
        1850.594,
        57.5,
        86.25,
        3.59375,
        126.266,
        33.848
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        44.99089353,
        11.29067946,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050971012,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0050641209,
        0.0034323873,
        0.0023233945,
        0.002323394525,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        20,
        20,
        7,
        0
      ],
      "numeric_coverage": 0.041666666666666664,
      "numeric_expected_count": 24,
      "numeric_matched_count": 1,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/boundary",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/calculate_stability_derivatives/validation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.7,
        6417151.1,
        2127485.9,
        -7037.62,
        810.292,
        2793.189
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/safety",
      "trial_id": "orbital-mechanics/elements_to_state_vector/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [
        2867.136,
        48488757.55,
        2262.007,
        7204.309,
        7679857.55,
        1367.821,
        3629.828,
        1499.316,
        9466.315,
        28084307.55,
        23419.44
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.067,
        50,
        3.671,
        576,
        14.193,
        75,
        2.447,
        3.125,
        0.03801,
        58.73,
        0,
        8,
        0,
        0,
        1800,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.8196104164,
        7220448.355437925,
        2771878.2328183074,
        0,
        -6436.93776978662,
        601.4617472224113,
        2960.582731896053,
        1518494.4731,
        7246271.5012,
        2945486.8586,
        60,
        -6517.997091,
        259.157306,
        2825.02025,
        1125446.3941,
        7251538.9348,
        3110722.629,
        120,
        -6580.499716,
        -83.561878,
        2681.558039,
        729208.651,
        7236255.7642,
        3267124.4742,
        180,
        -6624.299749,
        -425.696773,
        2530.630223
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.0115,
        32.775,
        24.4474,
        40,
        8050000,
        0,
        25,
        15.003884,
        0.0115,
        32.775,
        27.455693,
        39.997423,
        8050000,
        60,
        28.071116,
        15.007768,
        0.0115,
        32.775,
        30.463989,
        39.994846,
        8050000,
        120,
        31.140472,
        15.011653,
        0.0115,
        32.775,
        33.472285,
        39.992269,
        8050000,
        180,
        34.207894,
        0.00000112988,
        0.0008747869,
        -7.4959e-7
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/variation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.36
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [
        15,
        0.0075,
        28.5,
        40,
        5250000,
        25,
        0.00032615,
        0.09524398,
        -0.00020033,
        15,
        0.0075,
        28.5,
        24.63863,
        40,
        5250000,
        0,
        25,
        15.01957,
        0.0075,
        28.5,
        30.35327,
        39.98798,
        5250000,
        60,
        30.79115,
        15.03914,
        0.0075,
        28.5,
        36.06791,
        39.97596,
        5250000,
        120,
        36.57776,
        15.05871,
        0.0075,
        28.5,
        41.78255,
        39.96394,
        5250000,
        180,
        42.35922
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7086600,
        8061.4,
        8061.4,
        0.5443,
        2091300,
        5250000,
        0,
        0,
        0,
        5250000,
        0,
        4588940,
        1800,
        90,
        4276.1,
        6833.9,
        0,
        -6833.9,
        -4276.1,
        0
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.2,
        0.6457720403,
        37.0000124,
        -2.1293009864,
        -121.9999598
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/nominal",
      "trial_id": "coordinate-frames/ecef_to_geodetic/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        1425,
        535,
        118,
        57.5,
        147.8,
        39.2,
        890,
        149,
        86.25,
        21.2
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/variation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        20.3631,
        75.2036,
        25,
        60,
        21.6948,
        77.9141,
        28.0678,
        120,
        22.9723,
        80.6769,
        31.1339,
        180,
        24.1909,
        83.494,
        34.198
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1587773.37,
        20.363051,
        75.203634,
        0,
        1589934.85,
        21.694723,
        77.913943,
        60,
        1592311.03,
        22.972049,
        80.67665,
        120,
        1594895.36,
        24.190506,
        83.493588,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        20.363,
        75.204,
        0,
        21.695,
        77.915,
        60,
        22.973,
        80.678,
        120,
        24.192,
        83.495,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/variation",
      "trial_id": "orbital-mechanics/calculate_ground_track/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        20,
        20,
        0,
        7
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 24,
      "numeric_matched_count": 3,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        308,
        268
      ],
      "numeric_coverage": 0.18181818181818182,
      "numeric_expected_count": 11,
      "numeric_matched_count": 2,
      "operation": "plan_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5000,
        0.736116,
        54019.9,
        255.65,
        11000,
        0.363918,
        22632.1,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/nominal",
      "trial_id": "atmosphere/get_atmosphere_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.22875,
        1.31148,
        -1.63158,
        7.6,
        51.9185,
        66.6667,
        47.9093,
        4000,
        1.04918,
        -1.10526,
        9.5,
        63.1384,
        83.3333,
        59.8869,
        5000,
        0.114,
        0.49836,
        20
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        0.152,
        0.4984,
        0.9836,
        0.3,
        10.133,
        -0.9737,
        0.1969,
        66.936,
        66.667,
        63.879,
        4000,
        0.7869,
        0.24,
        12.667,
        -0.5789,
        0.2421,
        82.316,
        83.333,
        79.849,
        5000,
        20,
        7894.7
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1800,
        50,
        26.193,
        3.671,
        576,
        557.421,
        155.095,
        233.548,
        75,
        14.193,
        2.447,
        3.125,
        0.03801,
        58.74,
        0,
        1800,
        8,
        0,
        0,
        8,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/safety",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.0606601718,
        0.4142135624,
        0.5522847498
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        3000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.02,
        0.4,
        0.12,
        0.1097,
        -0.053,
        -2.08,
        -4,
        -0.211,
        -0.053,
        -2,
        0.009,
        -0.053,
        0,
        0.228,
        -0.053,
        2,
        0.447,
        -0.053,
        4,
        0.667,
        -0.053,
        6,
        0.886,
        -0.053,
        8,
        1.105,
        -0.053,
        750000
      ],
      "numeric_coverage": 0.16071428571428573,
      "numeric_expected_count": 56,
      "numeric_matched_count": 9,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        57.5,
        16560,
        2160,
        15,
        86.25,
        3.59375,
        3.192,
        2.12817,
        8,
        1800,
        14400,
        0.0380133,
        8,
        2070,
        500.86957,
        51.07346,
        1800,
        6.95652,
        14400
      ],
      "numeric_coverage": 0.21739130434782608,
      "numeric_expected_count": 23,
      "numeric_matched_count": 5,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/validation",
      "trial_id": "flight-planning/get_aircraft_performance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7980
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        69,
        299
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/validation",
      "trial_id": "flight-planning/get_system_status/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        5250000,
        0.57813096,
        0,
        180,
        1403440.2,
        3326720.1,
        29712375000,
        180
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        16560
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/variation",
      "trial_id": "rocket-analysis/optimize_launch_angle/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        3074.66,
        42164137,
        2425.73,
        7725.76,
        6678137,
        1466.82,
        3892.56,
        1607.84,
        0.72654275,
        10151.49,
        24421137,
        18990.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/nominal",
      "trial_id": "orbital-mechanics/hohmann_transfer/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        600,
        1863.26,
        2.2099,
        0.2099,
        3.0494,
        0.8395,
        1564.1,
        442.87,
        149.5,
        10.46,
        2,
        1.3799,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        120,
        30,
        180
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11,
        20,
        20,
        7
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 24,
      "numeric_matched_count": 3,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963438.2,
        45.169753,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.92,
        52.33,
        26.92
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.98,
        -0.498
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [
        1367.82,
        2262.01,
        3629.83,
        28084307.55,
        23419.4
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.00032615,
        0.09524398,
        -0.000200327,
        15,
        0.0075,
        28.5,
        24.638583,
        40,
        5250000,
        0,
        25,
        15.019569,
        0.0075,
        28.5,
        30.353222,
        39.9879804,
        5250000,
        60,
        30.791067,
        15.039138,
        0.0075,
        28.5,
        36.067861,
        39.9759608,
        5250000,
        120,
        36.57771,
        15.058707,
        0.0075,
        28.5,
        41.7825,
        39.9639411,
        5250000,
        180,
        42.359171,
        60
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        20,
        2,
        0.305,
        0.152,
        0.4984,
        0.3,
        0.9836,
        418.879,
        -10.72,
        22.66,
        0.1951,
        11.94,
        10.133,
        66.6667,
        4000,
        66.936,
        63.879,
        1.9737,
        0.24,
        0.7869,
        523.599,
        -6.52,
        18.46,
        0.24,
        11.94,
        12.667,
        83.3333,
        5000,
        82.315,
        79.849,
        1.5789
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        30,
        40,
        240,
        45,
        60,
        260
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1400,
        20.9,
        534,
        118,
        50,
        147,
        8,
        480,
        890,
        146,
        75,
        147,
        3.125,
        0.038,
        38.7
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/weight_and_balance/validation",
      "trial_id": "aircraft-performance/weight_and_balance/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/fuel_reserve_calculator/validation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        5750,
        0.678204,
        48820.97,
        317.459,
        250.775,
        12650,
        0.280515,
        17445.22,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -0.08,
        5.06403,
        -0.582363,
        -0.92,
        0.12,
        0.23
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.28,
        -0.607,
        -0.115
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/variation",
      "trial_id": "aerodynamics/calculate_stability_derivatives/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.9,
        52.3,
        26.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        4,
        181,
        201.6667,
        222.3333,
        243,
        170.6667,
        191.3333,
        212,
        232.6667,
        160.3333,
        181,
        201.6667,
        222.3333,
        150,
        170.6667,
        191.3333,
        212,
        16
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 32,
      "numeric_matched_count": 16,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/nominal",
      "trial_id": "flight-planning/get_aircraft_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        308,
        268
      ],
      "numeric_coverage": 0.18181818181818182,
      "numeric_expected_count": 11,
      "numeric_matched_count": 2,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/boundary",
      "trial_id": "flight-planning/plan_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        268.09,
        2384.1,
        39.74,
        187.66,
        799200,
        639360,
        39.24
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708,
        1124,
        960
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/safety",
      "trial_id": "aircraft-performance/weight_and_balance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        7000000,
        0.0000141239181,
        0,
        3.141592654,
        6999802.268,
        6999901.133,
        6999901.134,
        52822000000,
        3.141592654
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        -3379902.9654112225,
        -5408975.42035582,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/transform_frames/validation",
      "trial_id": "coordinate-frames/transform_frames/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        5.76,
        75,
        8,
        500,
        10.49
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 9,
      "numeric_matched_count": 3,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        268.1,
        187.7,
        71,
        222,
        39.7,
        177.6
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 6,
      "numeric_matched_count": 2,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.59,
        1531.25,
        4.87,
        1.04,
        0.00708,
        202,
        0.391,
        11150
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2592.5
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2800.994236,
        1693.742867,
        12334.504276,
        4494.737102,
        18315852.75
      ],
      "is_valid_case": true,
      "model_numbers": [
        1693.74,
        2800.99,
        3550.31,
        8920.94,
        4494.74,
        1856.57,
        11721.93,
        18315852.75,
        12334.5
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/boundary",
      "trial_id": "orbital-mechanics/hohmann_transfer/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        497
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        25.11
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/safety",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        14.7,
        7.5,
        75,
        7500,
        100,
        7,
        7353.003,
        7646.997,
        7500
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        212.98
      ],
      "is_valid_case": true,
      "model_numbers": [
        212.98
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/variation",
      "trial_id": "flight-planning/convert_units/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728029316,
        -3005984.3688082914,
        4290815.835922118
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.2,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/variation",
      "trial_id": "coordinate-frames/transform_frames/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        8142575,
        7957425,
        7965910,
        906300,
        4.275,
        685425,
        2.748,
        850000,
        7272000,
        7128000,
        7134618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        40,
        240,
        60,
        260
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/safety",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2240,
        790,
        207,
        8,
        1120,
        -85,
        162,
        24.4,
        47.8
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.2
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        955570.10669806,
        36.9758692,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        955570.1,
        36.975869,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/variation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        799.2,
        222,
        56.04,
        1.578,
        94.7,
        140.7,
        29.42
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [
        1166524.4,
        4823905.6,
        1599275.3,
        -8109.96,
        925.08,
        3215.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/nominal",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5640
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.0606601718,
        -1.0606601718,
        0.4142135624,
        0.5522847498
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/validation",
      "trial_id": "aerodynamics/get_airfoil_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        2.4,
        1.3,
        308,
        1.1,
        205,
        2,
        513
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2425.732164,
        1466.82435,
        18990.211638,
        3892.556514,
        24421137
      ],
      "is_valid_case": true,
      "model_numbers": [
        1466.82,
        2425.73,
        3892.56,
        24421137,
        18990.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/safety",
      "trial_id": "orbital-mechanics/hohmann_transfer/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2262.006906,
        1367.820759,
        23419.443193,
        3629.827665,
        28084307.549999997
      ],
      "is_valid_case": true,
      "model_numbers": [
        2867.136,
        2262.007,
        7204.309,
        7679857.55,
        48488757.55,
        1367.821,
        3629.827,
        1499.316,
        0.7265427,
        9466.315,
        28084307.55,
        23419.4
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 5,
      "numeric_matched_count": 5,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/hohmann_transfer/variation",
      "trial_id": "orbital-mechanics/hohmann_transfer/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        799200,
        222,
        639360,
        298,
        35.8,
        2145.5,
        187.7,
        44.7
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/nominal",
      "trial_id": "propeller-systems/uav_energy_estimate/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        959,
        -473,
        -33,
        403,
        110.8,
        1500,
        18.4,
        1432,
        0,
        0,
        541,
        145.5,
        1800,
        21.1,
        1924,
        492,
        34.4,
        677,
        179.2,
        2100,
        23.3,
        1.61,
        0.03801
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        50.64,
        50.64,
        210.42
      ],
      "is_valid_case": true,
      "model_numbers": [
        799200,
        222,
        56.06,
        0.884,
        53,
        1.578,
        94.7,
        140.7,
        29.43
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/boundary",
      "trial_id": "propeller-systems/uav_energy_estimate/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7980,
        2432
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/nominal",
      "trial_id": "aircraft-performance/density_altitude_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/validation",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.3,
        0.85531,
        11.6533,
        -0.71625,
        76.1348,
        73.4609,
        4000,
        0.24,
        0.684248,
        14.5667,
        -0.372998,
        93.9789,
        91.8261,
        5000,
        0.35075,
        0.1748,
        20
      ],
      "numeric_coverage": 0.3125,
      "numeric_expected_count": 16,
      "numeric_matched_count": 5,
      "operation": "propeller_bemt_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.5,
        623.3,
        164.3,
        65.3,
        1500,
        798,
        205.8,
        78.3,
        1800,
        968.3,
        245.2,
        91.4,
        2100,
        0.03801,
        56.25,
        0.575,
        0.1349,
        2.34375
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.5895,
        0.869,
        1531.25,
        3.731,
        5.096,
        177,
        0.00621,
        11670,
        0.4091
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        0.152,
        0.4984,
        0.3,
        0.9836,
        10.1333,
        -0.9737,
        0.1969,
        66.936,
        66.6667,
        63.879,
        4000,
        0.24,
        0.7869,
        12.6667,
        -0.5789,
        0.2421,
        82.315,
        83.3333,
        79.849,
        5000,
        20
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/safety",
      "trial_id": "propeller-systems/propeller_bemt_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.86167,
        120,
        0.19888,
        129.274
      ],
      "is_valid_case": true,
      "model_numbers": [
        66.46,
        129.18
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/nominal",
      "trial_id": "aircraft-performance/true_airspeed_converter/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        30
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.179
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/nominal",
      "trial_id": "coordinate-frames/transform_frames/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.9,
        52.3,
        26.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.29,
        288.15,
        5000,
        0.736116,
        54019.9,
        320.55,
        255.65,
        11000,
        0.363918,
        22632.1,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.686231,
        0.46628783,
        0.40546768
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "hohmann_transfer",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/hohmann_transfer/validation",
      "trial_id": "orbital-mechanics/hohmann_transfer/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        1,
        1961.3,
        3,
        4.29,
        1.29,
        2525,
        210,
        12,
        5,
        442.9,
        2,
        0.3,
        1.07,
        1.51,
        700,
        10000
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/nominal",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.407,
        0,
        19.997,
        81.835,
        60,
        21.946,
        87.411,
        120,
        23.683,
        93.135,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7980
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "uav_energy_estimate",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/uav_energy_estimate/validation",
      "trial_id": "propeller-systems/uav_energy_estimate/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2592.539,
        1399.859,
        291.137
      ],
      "is_valid_case": true,
      "model_numbers": [
        2592.5
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/boundary",
      "trial_id": "flight-planning/calculate_distance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.8531032,
        0.85294118,
        1.39972004,
        1.30231839,
        1.39972004,
        1.30231839,
        0.30874102,
        0.30805768,
        1,
        1,
        1.1468968,
        0.94705882
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.09532102,
        0,
        0,
        0.09489954,
        1.39972004,
        1.30231839
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 2,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/variation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135624,
        -1.4142135624,
        0.4142135624,
        0.4142135624
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.894786,
        90,
        0.14573,
        95.144
      ],
      "is_valid_case": true,
      "model_numbers": [
        95.1
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/boundary",
      "trial_id": "aircraft-performance/true_airspeed_converter/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        9,
        181,
        165.5,
        150,
        212,
        196.5,
        181,
        243,
        227.5,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 18,
      "numeric_matched_count": 9,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708,
        960,
        1124,
        9414.4
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        5289375,
        5210625,
        5214262,
        1920357,
        1917375,
        0,
        -3.83,
        1264.59,
        1264.58,
        7272000,
        7128000,
        7134618
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        33.9425,
        -118.40805,
        37.36299,
        -121.92862,
        495.739,
        267.677,
        77.7,
        450,
        495.739,
        2362.1,
        139.05
      ],
      "is_valid_case": true,
      "model_numbers": [
        65,
        85,
        2100,
        268,
        285
      ],
      "numeric_coverage": 0.09090909090909091,
      "numeric_expected_count": 11,
      "numeric_matched_count": 1,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_flight/variation",
      "trial_id": "flight-planning/plan_flight/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        222,
        0.72,
        177.6,
        38.67,
        38.67,
        275.56
      ],
      "is_valid_case": true,
      "model_numbers": [
        222,
        177.6,
        268.1,
        39.7,
        12.1,
        39.24,
        187.7,
        49.7
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 6,
      "numeric_matched_count": 2,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/safety",
      "trial_id": "propeller-systems/uav_energy_estimate/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.79166667,
        0.79166667,
        1.3438914,
        1.25248869,
        1.3438914,
        1.25248869,
        0.30232882,
        0.30232882,
        1,
        1,
        1.20833333,
        1.00833333
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.091402715,
        0,
        0,
        0.091402715,
        1.343891403,
        1.252488688,
        0.791666667,
        0.791666667,
        1.343891403,
        1.252488688
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 12,
      "numeric_matched_count": 6,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135624,
        0.4142135624,
        0.4142135624
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/nominal",
      "trial_id": "guidance-navigation-control/lqr_controller_design/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        3750,
        0.840958,
        63675.1,
        325.583,
        263.775,
        8250,
        0.509959,
        34331,
        307.001,
        234.525
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/get_propeller_database/boundary",
      "trial_id": "propeller-systems/get_propeller_database/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        100,
        7,
        10011.36785036,
        9829.10588804,
        10008.50961552,
        10184.32109819,
        106.74891129
      ],
      "is_valid_case": true,
      "model_numbers": [
        10000,
        100,
        10225.99,
        10001.21,
        9771.17,
        102.39,
        7,
        10.24,
        9804,
        10196
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9380
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        5750,
        0.678204,
        48821,
        317.459,
        250.775,
        12650,
        0.280515,
        17445.2,
        295.07,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/variation",
      "trial_id": "flight-planning/get_aircraft_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        4,
        4,
        243,
        150,
        181,
        201.666667,
        222.333333,
        243,
        170.666667,
        191.333333,
        212,
        232.666667,
        160.333333,
        181,
        201.666667,
        222.333333,
        150,
        170.666667,
        191.333333,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 32,
      "numeric_matched_count": 16,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "kalman_filter_state_estimation",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "invalid_request",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/validation",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        375,
        0.9,
        1700,
        2400,
        2000
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 4,
      "numeric_matched_count": 2,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.3115,
        0.9,
        0.03485,
        7.92,
        4000,
        0.02495,
        0.372,
        0.0189,
        1.0492,
        0.9,
        0.03957,
        17.57,
        5000,
        0.04463,
        1.039,
        0.0336
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.22875,
        0.114,
        0.49836,
        1.31148,
        7.6,
        -1.63158,
        51.9188,
        66.6667,
        47.9093,
        4000,
        1.04918,
        9.5,
        -1.10526,
        63.1385,
        83.3333,
        59.8866,
        5000,
        20
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/boundary",
      "trial_id": "propeller-systems/propeller_bemt_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1.17083,
        1124,
        960
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.1708,
        960,
        1124
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/nominal",
      "trial_id": "aircraft-performance/weight_and_balance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.83,
        -4325046.23,
        3817399.18
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/calculate_distance/validation",
      "trial_id": "flight-planning/calculate_distance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.4
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [
        11.5,
        115,
        575,
        6.12,
        8.5,
        10.71
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        2046.53,
        200.348,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        8,
        57.5,
        2160,
        15,
        16560,
        86.25,
        3.59375,
        1800,
        270,
        2070,
        500.8695652,
        51.07,
        1800,
        8,
        0,
        0.8695652174,
        14400
      ],
      "numeric_coverage": 0.21739130434782608,
      "numeric_expected_count": 23,
      "numeric_matched_count": 5,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/variation",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.7,
        -3005984.4,
        4290815.8
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "invalid_request",
      "task_id": "rocket-analysis/estimate_rocket_sizing/validation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5000,
        0.736116,
        54019.888188,
        320.529394,
        255.65,
        11000,
        0.363918,
        22632.040095,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        288.15,
        5000,
        0.73612,
        54019.9,
        255.65,
        11000,
        0.36392,
        22632.1,
        216.65
      ],
      "numeric_coverage": 0.8,
      "numeric_expected_count": 15,
      "numeric_matched_count": 12,
      "operation": "get_atmosphere_profile",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/safety",
      "trial_id": "atmosphere/get_atmosphere_profile/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.602,
        1531.3,
        1.052,
        110.5,
        0.00594,
        6014,
        0.3232,
        0.08081,
        4.63
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        3600,
        5100,
        536000,
        496000,
        3000,
        4500,
        411000,
        380000,
        6600,
        9600,
        947000,
        876000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.3521820833,
        4823905.576603966,
        1599275.2863258962,
        0,
        -8109.9599211131335,
        925.082722070581,
        3215.186142814247,
        674844.3415,
        4854902.8133,
        1783725.9645,
        60,
        -8265.518447,
        107.46636,
        2928.022743,
        176338.4611,
        4836802.2794,
        1950050.7357,
        120,
        -8337.332968,
        -710.110861,
        2611.521658,
        -323949.426,
        4769857.5605,
        2096588.0622,
        180,
        -8324.910507,
        -1519.290682,
        2269.018852
      ],
      "is_valid_case": true,
      "model_numbers": [
        6378137,
        398600441800000,
        0.00108262668,
        5289375,
        0.00000569245,
        0.00166232098,
        0.0016597013,
        5210625,
        -0.00000349636,
        5249704.6875,
        15,
        0.0075,
        28.5,
        24.6386,
        40,
        5250000,
        0,
        25,
        15.01957,
        0.0075,
        28.5,
        30.3534,
        39.98798,
        5250000,
        60,
        30.7911,
        15.03914,
        0.0075,
        28.5,
        36.068,
        39.97596,
        5250000,
        120,
        36.5777,
        15.05871,
        0.0075,
        28.5,
        41.7826,
        39.96394,
        5250000,
        180,
        42.3592
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/boundary",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/nominal",
      "trial_id": "aircraft-performance/landing_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1166524.352182,
        4823905.576604,
        1599275.286326,
        -8109.959921,
        925.082722,
        3215.186143
      ],
      "is_valid_case": true,
      "model_numbers": [
        1236724.3,
        4823905.4,
        1599275.3,
        -8109.96,
        925.08,
        3215.18
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/boundary",
      "trial_id": "orbital-mechanics/elements_to_state_vector/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        0.0000141239181,
        0,
        0,
        6999901.133,
        6999901.134,
        180
      ],
      "numeric_coverage": 0.8333333333333334,
      "numeric_expected_count": 6,
      "numeric_matched_count": 5,
      "operation": "state_vector_to_elements",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/safety",
      "trial_id": "orbital-mechanics/state_vector_to_elements/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        46.92221994,
        10.98457212,
        0.00509710118,
        0.001879362981,
        0.001879362981,
        0.001879362981,
        0.001704787163,
        0.001201504008,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000205509398,
        0.000073443378,
        0.000073443378,
        0.000032415261,
        0.000032415261,
        0.000032415261,
        0.000016605509,
        0.000015930573,
        0.000015209428,
        0.000005892026,
        0.000003917289,
        0.000003917289,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [
        47,
        11
      ],
      "numeric_coverage": 0.08333333333333333,
      "numeric_expected_count": 24,
      "numeric_matched_count": 2,
      "operation": "particle_swarm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/particle_swarm_optimization/boundary",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        220,
        3.249,
        0.807,
        0.142,
        1.3315,
        475,
        2.3,
        617.5,
        11500
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "estimate_rocket_sizing",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        50,
        959.4,
        -33,
        403.6,
        110.8,
        555.8,
        2.039,
        7518,
        17.62,
        1500,
        18.44,
        1432.3,
        0,
        541.3,
        145.5,
        891,
        2.447,
        12972,
        21.76,
        1800,
        21.07,
        1923.7,
        34.3,
        677,
        179.2,
        1246.7,
        2.855,
        19671,
        25.46,
        2100,
        23.26,
        0.03801,
        75,
        3.125,
        1800
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/safety",
      "trial_id": "flight-planning/get_aircraft_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        8.20379153,
        37.00001244,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.2,
        37.000012,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/safety",
      "trial_id": "coordinate-frames/ecef_to_geodetic/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/safety",
      "trial_id": "atmosphere/wind_model_simple/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.58
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        0.57813096,
        0,
        0,
        3326720.11256726,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        5250000,
        0.578130959,
        0,
        180,
        1403440.2,
        3326720.1,
        29712375000,
        -59908923.6,
        180
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 4,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/boundary",
      "trial_id": "orbital-mechanics/state_vector_to_elements/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        3341.406,
        -30.556,
        2320.421,
        1500,
        0,
        3341.406,
        1800,
        36.111,
        4548.025,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        -571,
        -25.8,
        1500,
        538,
        24.3,
        2100,
        1644,
        625,
        164.2,
        65.26,
        2.719,
        22.7,
        1500,
        21.7,
        2215,
        799,
        205.7,
        78.32,
        3.263,
        26.4,
        1800,
        23.9,
        2753,
        969,
        245,
        91.37,
        3.807,
        29.4,
        2100,
        25.5,
        1.848,
        1.5,
        0.573,
        0.1348,
        2.34375,
        0.03801
      ],
      "numeric_coverage": 0.3,
      "numeric_expected_count": 10,
      "numeric_matched_count": 3,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        -3620725.6728,
        -3005984.3688,
        4290815.8359
      ],
      "is_valid_case": true,
      "model_numbers": [
        -3620725.673,
        -3005984.369,
        4290815.836
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/variation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.47,
        1531,
        1,
        0.00575,
        143,
        0.329,
        4.71,
        8150
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "search_airports",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/search_airports/validation",
      "trial_id": "flight-planning/search_airports/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.982,
        8,
        4628.195,
        43731.332,
        267.204,
        2006.8,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        2160,
        610,
        23.7,
        788,
        152,
        37.5,
        206.5,
        8
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/boundary",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "geodetic_to_ecef",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/geodetic_to_ecef/validation",
      "trial_id": "coordinate-frames/geodetic_to_ecef/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -1163875.26,
        17.861176,
        76.405624,
        0,
        -1162087.29,
        19.996866,
        81.835758,
        60,
        -1160048.33,
        21.944591,
        87.410686,
        120,
        -1157776.3,
        23.679333,
        93.133278,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.406,
        0,
        19.997,
        81.836,
        60,
        21.946,
        87.41,
        120,
        23.682,
        93.133,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/boundary",
      "trial_id": "orbital-mechanics/calculate_ground_track/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907235,
        7220448,
        2771878,
        -6436.9,
        601.5,
        2960.6
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -0.08,
        4.905763,
        -0.490576,
        -0.8,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        5,
        -0.5
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/nominal",
      "trial_id": "aerodynamics/calculate_stability_derivatives/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        138.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        138.9
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/boundary",
      "trial_id": "flight-planning/convert_units/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/elements_to_state_vector/validation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -4,
        0.00958,
        -0.22,
        -0.05,
        -2,
        0.009,
        0,
        -0.05,
        0,
        0.00958,
        0.22,
        -0.05,
        2,
        0.01132,
        0.44,
        -0.05,
        4,
        0.01423,
        0.66,
        -0.05,
        6,
        0.01829,
        0.88,
        -0.05,
        8,
        0.02352,
        1.1,
        -0.05,
        10,
        0.02991,
        1.32,
        -0.05,
        12,
        0.03746,
        1.54,
        -0.05,
        750000
      ],
      "numeric_coverage": 0.5892857142857143,
      "numeric_expected_count": 56,
      "numeric_matched_count": 33,
      "operation": "airfoil_polar_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "landing_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/validation",
      "trial_id": "aircraft-performance/landing_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/safety",
      "trial_id": "rocket-analysis/optimize_launch_angle/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.9635,
        7988.7,
        0.786531,
        5.09,
        24.91
      ],
      "is_valid_case": true,
      "model_numbers": [
        7980
      ],
      "numeric_coverage": 0.2,
      "numeric_expected_count": 5,
      "numeric_matched_count": 1,
      "operation": "density_altitude_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/safety",
      "trial_id": "aircraft-performance/density_altitude_calculator/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        0.52085352,
        0,
        0,
        16800707.7668711,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        0.520853519,
        0,
        0,
        12242870.8,
        16800707.8,
        69857095000,
        0
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/variation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        17.861,
        76.406,
        0,
        19.275,
        79.845,
        60,
        20.612,
        83.345,
        120,
        21.867,
        86.907,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        175.08,
        1765.2,
        2.588,
        3.74,
        1.152,
        0.288,
        1.44,
        2034,
        183.4,
        11.09,
        5,
        474.92,
        2.3,
        1.445,
        650,
        11500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "state_vector_to_elements",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/state_vector_to_elements/validation",
      "trial_id": "orbital-mechanics/state_vector_to_elements/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7016.3,
        -6872.5,
        -1413.2,
        0,
        7016.3,
        1413.2,
        6872.5,
        0,
        398600441800000,
        -0.205636,
        1018.56,
        -0.205636,
        7000000,
        0,
        0,
        0,
        7000000,
        0,
        1800,
        1.5707963268,
        3.79749
      ],
      "numeric_coverage": 0.42857142857142855,
      "numeric_expected_count": 7,
      "numeric_matched_count": 3,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/nominal",
      "trial_id": "orbital-mechanics/lambert_problem_solver/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.842256,
        138,
        0.23195,
        150.369
      ],
      "is_valid_case": true,
      "model_numbers": [
        150.4
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "true_airspeed_converter",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/true_airspeed_converter/variation",
      "trial_id": "aircraft-performance/true_airspeed_converter/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        343.8296,
        -198.917153,
        -204.546848,
        3313.147393,
        403.464001,
        7625000
      ],
      "is_valid_case": true,
      "model_numbers": [
        7965910,
        4.275,
        906500,
        2.748,
        831292,
        7134618
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/variation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -6,
        0.011269,
        -0.438649,
        -38.925,
        -0.05,
        -4,
        0.009537,
        -0.219325,
        -22.997,
        -0.05,
        -2,
        0.00896,
        0,
        0,
        -0.05,
        0,
        0.009537,
        0.219325,
        22.997,
        -0.05,
        2,
        0.011269,
        0.438649,
        38.925,
        -0.05,
        4,
        0.014155,
        0.657974,
        46.483,
        -0.05,
        6,
        0.018196,
        0.877298,
        48.214,
        -0.05,
        8,
        0.023391,
        1.096623,
        46.882,
        -0.05,
        10,
        0.029741,
        1.315947,
        44.247,
        -0.05,
        12,
        0.037245,
        1.535272,
        41.221,
        -0.05,
        14,
        0.037569,
        1.544045,
        41.099,
        -0.05,
        750000
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.45,
        0.11,
        12,
        -2,
        -4,
        0.0124,
        -0.22,
        -0.05,
        -2,
        0.012,
        0,
        -0.05,
        0,
        0.0124,
        0.22,
        -0.05,
        2,
        0.0137,
        0.44,
        -0.05,
        4,
        0.0159,
        0.66,
        -0.05,
        6,
        0.019,
        0.88,
        -0.05,
        8,
        0.0229,
        1.1,
        -0.05,
        10,
        0.0277,
        1.32,
        -0.05,
        12,
        0.04,
        1.45,
        -0.05,
        14,
        0.065,
        1.35,
        750000
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 56,
      "numeric_matched_count": 28,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/boundary",
      "trial_id": "aerodynamics/airfoil_polar_analysis/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propeller_bemt_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/validation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.93
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/boundary",
      "trial_id": "aircraft-performance/stall_speed_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        6378137,
        398600441800000,
        0.00108262668,
        0.00000207992,
        0.0010789648,
        0.0010780076,
        -0.00000127755,
        6999300,
        0.261799388,
        0.01,
        0.497418837,
        0.4279371,
        0.698131701,
        7000000,
        0,
        0.436332313,
        0.261924183,
        0.01,
        0.497418837,
        0.49267499,
        0.698055048,
        7000000,
        60,
        0.50223996,
        0.262048978,
        0.01,
        0.497418837,
        0.55741288,
        0.697978395,
        7000000,
        120,
        0.56810608,
        0.262173773,
        0.01,
        0.497418837,
        0.62215077,
        0.697901742,
        7000000,
        180,
        0.63392617
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        11.5,
        270,
        6.144354,
        115,
        270,
        8.522589,
        575,
        270,
        10.184905
      ],
      "is_valid_case": true,
      "model_numbers": [
        11.5,
        6.12,
        115,
        8.51,
        575,
        10.71
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/variation",
      "trial_id": "atmosphere/wind_model_simple/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "calculate_ground_track",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/calculate_ground_track/validation",
      "trial_id": "orbital-mechanics/calculate_ground_track/validation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907234.8,
        7220448.4,
        2771878.2,
        -6436.94,
        601.46,
        2960.58
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/variation",
      "trial_id": "propeller-systems/get_propeller_database/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.4142136,
        0.5522848
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.0606601718,
        0.4142135624,
        0.5522847498
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/boundary",
      "trial_id": "guidance-navigation-control/lqr_controller_design/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        10,
        270,
        6,
        100,
        270,
        8.378236,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        10,
        6,
        100,
        8.34,
        500,
        10.49
      ],
      "numeric_coverage": 0.5555555555555556,
      "numeric_expected_count": 9,
      "numeric_matched_count": 5,
      "operation": "wind_model_simple",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/nominal",
      "trial_id": "atmosphere/wind_model_simple/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/safety",
      "trial_id": "flight-planning/get_system_status/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/stall_speed_calculator/validation",
      "trial_id": "aircraft-performance/stall_speed_calculator/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/nominal",
      "trial_id": "aerodynamics/airfoil_polar_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/validation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        16,
        181,
        201.6667,
        222.3333,
        243,
        170.6667,
        191.3333,
        212,
        232.6667,
        160.3333,
        181,
        201.6667,
        222.3333,
        150,
        170.6667,
        191.3333,
        212,
        243,
        150
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 32,
      "numeric_matched_count": 16,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/safety",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/propagate_orbit_j2/validation",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/variation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        26.9417,
        243,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212,
        27.4693,
        232.67,
        38.9146,
        160.33,
        34.0787,
        181,
        30.5829,
        201.67,
        28.2442,
        222.33,
        41.92,
        150,
        36.3142,
        170.67,
        32.1766,
        191.33,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 32,
      "numeric_matched_count": 0,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/nominal",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/nominal",
      "trial_id": "flight-planning/get_system_status/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        5214261.7,
        1920356.7,
        7134618.4
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "lambert_problem_solver",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/lambert_problem_solver/validation",
      "trial_id": "orbital-mechanics/lambert_problem_solver/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        255.3,
        0.72,
        204.24,
        38.95,
        38.95,
        314.64
      ],
      "is_valid_case": true,
      "model_numbers": [
        255.3,
        56.06,
        308.3,
        49.7,
        71,
        215.8,
        45.13
      ],
      "numeric_coverage": 0.16666666666666666,
      "numeric_expected_count": 6,
      "numeric_matched_count": 1,
      "operation": "uav_energy_estimate",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/uav_energy_estimate/variation",
      "trial_id": "propeller-systems/uav_energy_estimate/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.9836,
        0.9,
        0.04075,
        39.04,
        4000,
        0.04954,
        2.334,
        0.0932,
        0.7869,
        0.9,
        0.04429,
        82.87,
        5000,
        0.0643,
        4.733,
        0.1583
      ],
      "is_valid_case": true,
      "model_numbers": [
        2,
        0.305,
        0.152,
        0.4984,
        0.3,
        0.9836,
        9.8667,
        10.1333,
        66.9368,
        66.6667,
        63.8791,
        4000,
        0.24,
        0.7869,
        7.3333,
        12.6667,
        82.315,
        83.3333,
        79.8492,
        5000
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 16,
      "numeric_matched_count": 4,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "success",
      "task_id": "propeller-systems/propeller_bemt_analysis/nominal",
      "trial_id": "propeller-systems/propeller_bemt_analysis/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        115,
        7,
        11516.57315149,
        11314.11193456,
        11509.78605785,
        11711.96926292,
        122.83436588
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/validation",
      "trial_id": "propeller-systems/get_propeller_database/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/validation",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0.89862,
        217.8,
        30.7,
        12.522
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/nominal",
      "trial_id": "aircraft-performance/takeoff_performance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1879.541,
        -30.556,
        1305.237,
        1500,
        0,
        1879.541,
        1800,
        36.111,
        2558.264,
        2100
      ],
      "is_valid_case": true,
      "model_numbers": [
        404,
        110.7,
        960,
        18.4,
        1500,
        12000,
        541,
        145.5,
        1431,
        21.1,
        1800,
        14400,
        678,
        179.1,
        1924,
        23.2,
        2100,
        16800,
        -471,
        -32.9,
        1500,
        0,
        0,
        1800,
        493,
        34.5,
        2100,
        50,
        75,
        3.125,
        0.03801,
        1.61,
        0.457,
        0.114,
        1800
      ],
      "numeric_coverage": 0.4,
      "numeric_expected_count": 10,
      "numeric_matched_count": 4,
      "operation": "trajectory_sensitivity_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety",
      "trial_id": "trajectory-optimization/trajectory_sensitivity_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -963438.2338072,
        45.16975204,
        -121.99995983
      ],
      "is_valid_case": true,
      "model_numbers": [
        -963442,
        45.16971,
        -121.99996
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "ecef_to_geodetic",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/ecef_to_geodetic/boundary",
      "trial_id": "coordinate-frames/ecef_to_geodetic/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1929.583,
        1041.891,
        95.995
      ],
      "is_valid_case": true,
      "model_numbers": [
        1929.58
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/variation",
      "trial_id": "flight-planning/calculate_distance/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        69,
        450,
        375,
        1999.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        375
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/boundary",
      "trial_id": "flight-planning/get_aircraft_performance/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        3750,
        0.840958,
        63675.11042,
        325.583045,
        263.775,
        8250,
        0.509959,
        34330.965516,
        307.000821,
        234.525
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        3750,
        0.840958,
        63675.1,
        325.583,
        263.775,
        8250,
        0.509959,
        34331,
        307.001,
        234.525
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/boundary",
      "trial_id": "atmosphere/get_atmosphere_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -6,
        0.011029,
        -0.438649,
        -39.772,
        -0.05,
        -4,
        0.009297,
        -0.219325,
        -23.59,
        -0.05,
        -2,
        0.00872,
        0,
        0,
        -0.05,
        0,
        0.009297,
        0.219325,
        23.59,
        -0.05,
        2,
        0.011029,
        0.438649,
        39.772,
        -0.05,
        4,
        0.013915,
        0.657974,
        47.285,
        -0.05,
        6,
        0.017956,
        0.877298,
        48.859,
        -0.05,
        8,
        0.023151,
        1.096623,
        47.368,
        -0.05,
        10,
        0.029501,
        1.315947,
        44.607,
        -0.05,
        12,
        0.037005,
        1.535272,
        41.489,
        -0.05,
        14,
        0.037329,
        1.544045,
        41.363,
        -0.05,
        1000000
      ],
      "is_valid_case": true,
      "model_numbers": [
        -4,
        0.0079,
        -0.21,
        -0.05,
        -2,
        0.0075,
        0,
        -0.05,
        0,
        0.0079,
        0.21,
        -0.05,
        2,
        0.0091,
        0.42,
        -0.05,
        4,
        0.0111,
        0.63,
        -0.05,
        6,
        0.0139,
        0.84,
        -0.05,
        8,
        0.0174,
        1.05,
        -0.05,
        10,
        0.0218,
        1.26,
        -0.05,
        1000000
      ],
      "numeric_coverage": 0.3392857142857143,
      "numeric_expected_count": 56,
      "numeric_matched_count": 19,
      "operation": "airfoil_polar_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/airfoil_polar_analysis/safety",
      "trial_id": "aerodynamics/airfoil_polar_analysis/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/validation",
      "trial_id": "aircraft-performance/takeoff_performance/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        308,
        21.8,
        22.74,
        11.699
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/safety",
      "trial_id": "aircraft-performance/landing_performance/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.47,
        1531,
        8150,
        4.71,
        1,
        0.00575,
        0.329
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/safety",
      "trial_id": "aerodynamics/wing_vlm_analysis/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1.00271,
        787.125,
        785
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.002707,
        787.125,
        785
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "weight_and_balance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/weight_and_balance/boundary",
      "trial_id": "aircraft-performance/weight_and_balance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.469,
        1531.25,
        2.997,
        4.708,
        1.003,
        142.7,
        0.005754,
        57.11,
        8152,
        0.3286,
        0.08216
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/wing_vlm_analysis/validation",
      "trial_id": "aerodynamics/wing_vlm_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/convert_units/validation",
      "trial_id": "flight-planning/convert_units/validation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "true_airspeed_converter",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/true_airspeed_converter/validation",
      "trial_id": "aircraft-performance/true_airspeed_converter/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        7.5,
        270,
        5.702866,
        75,
        270,
        8.081102,
        500,
        270,
        10.040551
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.5,
        5.76,
        75,
        8,
        500,
        10.49
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 9,
      "numeric_matched_count": 3,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/wind_model_simple/boundary",
      "trial_id": "atmosphere/wind_model_simple/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544358,
        544.358
      ],
      "numeric_coverage": 0.3333333333333333,
      "numeric_expected_count": 3,
      "numeric_matched_count": 1,
      "operation": "calculate_distance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.75,
        2300,
        1,
        7300,
        99,
        2100,
        500
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/nominal",
      "trial_id": "flight-planning/get_aircraft_performance/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        1800,
        7839171.950386,
        2916.666667,
        0,
        -2916.666667,
        -7839171.950386,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        -6833.9,
        -4276.1,
        0,
        4276.1,
        6833.9,
        0,
        0.5443,
        3229350,
        4588930,
        90
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/boundary",
      "trial_id": "orbital-mechanics/lambert_problem_solver/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        76.406,
        0,
        17.861,
        79.852,
        60,
        19.28,
        83.344,
        120,
        20.612,
        86.906,
        180,
        21.867
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/density_altitude_calculator/validation",
      "trial_id": "aircraft-performance/density_altitude_calculator/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        90,
        35.314,
        8,
        4729.492,
        43944.906,
        267.856,
        0,
        78.314,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/boundary",
      "trial_id": "rocket-analysis/optimize_launch_angle/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        5.602,
        0.036902,
        686.55,
        0.014902,
        0.463738,
        8627.7,
        12.567
      ],
      "is_valid_case": true,
      "model_numbers": [
        5.6029,
        1531.25,
        0.07582,
        4.344,
        1.59,
        121.5,
        0.00653,
        5642,
        0.3033,
        46.4,
        1.4727
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/boundary",
      "trial_id": "aerodynamics/wing_vlm_analysis/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.99,
        -4325046.48,
        3817399.18
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/safety",
      "trial_id": "coordinate-frames/geodetic_to_ecef/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0,
        46,
        30,
        276,
        138,
        230
      ],
      "is_valid_case": true,
      "model_numbers": [
        18.4,
        211.6,
        69,
        299
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/variation",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0,
        40,
        30,
        240,
        120,
        200
      ],
      "is_valid_case": true,
      "model_numbers": [
        7200,
        2700,
        60,
        260,
        200
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "fuel_reserve_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/nominal",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.0938829,
        0,
        0,
        0.0938829,
        1.3817145,
        1.2878316,
        0.8347107,
        0.8347107,
        0.4694146,
        0.4694146,
        0.8347107,
        0.8347107,
        1.3817145,
        1.2878316
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 12,
      "numeric_matched_count": 6,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/safety",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        47.91719169,
        11.65170582,
        0.0095992045,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0042842112,
        0.0018927423,
        0.0018927423,
        0.001892742286,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "genetic_algorithm_optimization",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/genetic_algorithm_optimization/safety",
      "trial_id": "trajectory-optimization/genetic_algorithm_optimization/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.922364,
        9457,
        0.75295,
        3.61,
        30.89
      ],
      "is_valid_case": true,
      "model_numbers": [
        9381
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/variation",
      "trial_id": "aircraft-performance/density_altitude_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        311.9,
        25.7,
        24.68,
        12.694
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "landing_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/landing_performance/variation",
      "trial_id": "aircraft-performance/landing_performance/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/nominal",
      "trial_id": "propeller-systems/get_propeller_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_aircraft_database/validation",
      "trial_id": "flight-planning/get_aircraft_database/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        83.4,
        450,
        575,
        2599.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        575,
        60,
        4,
        70,
        2300,
        1900,
        2800
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/variation",
      "trial_id": "flight-planning/get_aircraft_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        496,
        268,
        380,
        205,
        2,
        876,
        473
      ],
      "numeric_coverage": 0.2727272727272727,
      "numeric_expected_count": 11,
      "numeric_matched_count": 3,
      "operation": "plan_multi_leg_flight",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/boundary",
      "trial_id": "flight-planning/plan_multi_leg_flight/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544360
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "calculate_distance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/nominal",
      "trial_id": "flight-planning/calculate_distance/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/nominal",
      "trial_id": "aerodynamics/get_airfoil_database/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        1.121,
        3000,
        0.915,
        825
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "takeoff_performance",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        46.97958263,
        11.0000819,
        0.009599204541,
        0.000492385529,
        0.000492385529,
        0.000492385529,
        0.000238755222,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000025632578,
        0.000002632958,
        0.000002632958,
        0.000002632958,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        1.15823e-7,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 24,
      "numeric_matched_count": 0,
      "operation": "particle_swarm_optimization",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/particle_swarm_optimization/nominal",
      "trial_id": "trajectory-optimization/particle_swarm_optimization/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "ecef_to_geodetic",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "invalid_request",
      "task_id": "coordinate-frames/ecef_to_geodetic/validation",
      "trial_id": "coordinate-frames/ecef_to_geodetic/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        2.55,
        0.28,
        2.31,
        1.5,
        1.58,
        710.24,
        220,
        5.63
      ],
      "is_valid_case": true,
      "model_numbers": [
        180,
        1,
        650,
        3.61,
        1.11,
        11.1,
        177,
        0.1,
        383.6,
        1.5,
        1.445,
        7500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/boundary",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        -2702588.8325,
        -4325046.2264,
        3817399.1785
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.832,
        -4325046.226,
        3817399.178
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "geodetic_to_ecef",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/geodetic_to_ecef/nominal",
      "trial_id": "coordinate-frames/geodetic_to_ecef/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0.46628786,
        0.40546771
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.68623102,
        0.46628784,
        0.40546769
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/variation",
      "trial_id": "guidance-navigation-control/lqr_controller_design/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        78,
        450,
        500,
        2374.9
      ],
      "is_valid_case": true,
      "model_numbers": [
        500,
        1.15,
        6000,
        1900,
        1600,
        2300
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 4,
      "numeric_matched_count": 1,
      "operation": "get_aircraft_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_performance/safety",
      "trial_id": "flight-planning/get_aircraft_performance/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0,
        0.00001412,
        0,
        0,
        6999901.13396958,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.000014123918,
        0,
        3.141592654,
        6999901.134,
        52822000000,
        -28471862.257,
        3.141592654
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 6,
      "numeric_matched_count": 3,
      "operation": "state_vector_to_elements",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/state_vector_to_elements/nominal",
      "trial_id": "orbital-mechanics/state_vector_to_elements/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7000000,
        7652000,
        0.241,
        6165000,
        -6872,
        -1414,
        0,
        1414,
        6872,
        0,
        7016,
        90
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "lambert_problem_solver",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 3,
      "numeric_matched_count": 0,
      "operation": "search_airports",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/variation",
      "trial_id": "flight-planning/search_airports/variation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        96.95,
        52.35,
        26.93
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/nominal",
      "trial_id": "aircraft-performance/stall_speed_calculator/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        2706.54,
        230.4,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.22,
        0.45,
        0.0380133,
        50,
        50,
        75,
        3.125,
        25,
        26.193,
        3.671,
        576,
        58.736,
        78.453,
        233.548,
        155.095,
        14.193,
        2.447,
        8,
        0,
        1800,
        14400
      ],
      "numeric_coverage": 0.17391304347826086,
      "numeric_expected_count": 23,
      "numeric_matched_count": 4,
      "operation": "optimize_thrust_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/nominal",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        22,
        450,
        20,
        2500,
        27,
        488,
        25,
        5800,
        23,
        453,
        20,
        2600,
        28,
        493,
        26,
        10200,
        27,
        490,
        25,
        6800,
        20,
        447,
        18,
        1900,
        12,
        122,
        10,
        32
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 28,
      "numeric_matched_count": 0,
      "operation": "get_aircraft_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/get_aircraft_database/boundary",
      "trial_id": "flight-planning/get_aircraft_database/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_multi_leg_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_multi_leg_flight/validation",
      "trial_id": "flight-planning/plan_multi_leg_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.87775,
        223.3,
        36.2,
        13.587
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "invalid_request",
      "task_id": "aircraft-performance/takeoff_performance/variation",
      "trial_id": "aircraft-performance/takeoff_performance/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        6936435,
        198184,
        7134618
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        4811.62,
        307.2,
        1.6,
        1,
        0,
        1530,
        3.2,
        2,
        1.6,
        1665,
        4.8,
        3,
        3.2,
        1800,
        6.4,
        4,
        4.8,
        1935,
        8,
        5,
        6.4,
        2070,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.5,
        4.894,
        14400,
        768,
        78.31,
        311.4,
        0,
        56.25,
        3.262,
        2.34375,
        1800,
        32,
        0,
        56.25,
        1800,
        34.9091,
        2,
        51.5625,
        1800,
        38.4,
        4,
        46.875,
        1800,
        42.6667,
        6,
        42.1875,
        1800,
        48,
        8,
        37.5,
        0.0380133,
        14400
      ],
      "numeric_coverage": 0.2608695652173913,
      "numeric_expected_count": 23,
      "numeric_matched_count": 6,
      "operation": "optimize_thrust_profile",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/optimize_thrust_profile/boundary",
      "trial_id": "trajectory-optimization/optimize_thrust_profile/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        8.59,
        0.036921,
        1053.26,
        0.014921,
        0.574607,
        16391.93,
        15.563
      ],
      "is_valid_case": true,
      "model_numbers": [
        8.59,
        1531.3,
        4.867,
        1.037,
        201.7,
        0.00707,
        55.25,
        11146,
        0.391
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/variation",
      "trial_id": "aerodynamics/wing_vlm_analysis/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "invalid_request",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/validation",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        1800,
        6787559.072208,
        3888.888889,
        0,
        -3888.888889,
        -6787559.072208,
        0
      ],
      "is_valid_case": true,
      "model_numbers": [
        7652000,
        1565.5,
        -6872.5,
        -1413.2,
        0,
        1565.5,
        1413.2,
        6872.5,
        0,
        0.2412,
        4678000,
        6165000,
        3131,
        90
      ],
      "numeric_coverage": 0.2857142857142857,
      "numeric_expected_count": 7,
      "numeric_matched_count": 2,
      "operation": "lambert_problem_solver",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/lambert_problem_solver/safety",
      "trial_id": "orbital-mechanics/lambert_problem_solver/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        0.254,
        0.119,
        2,
        0.305,
        0.152,
        2,
        0.457,
        0.165
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 9,
      "numeric_matched_count": 0,
      "operation": "get_propeller_database",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/get_propeller_database/safety",
      "trial_id": "propeller-systems/get_propeller_database/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        6936434.55,
        198183.84,
        7134618.4
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        185.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        185.2
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 1,
      "numeric_matched_count": 1,
      "operation": "convert_units",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/convert_units/safety",
      "trial_id": "flight-planning/convert_units/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        76.404,
        1.3335,
        17.861,
        0.311735,
        0,
        79.844,
        1.39355,
        19.275,
        0.336409,
        60,
        83.345,
        1.45464,
        20.612,
        0.359752,
        120,
        86.906,
        1.51679,
        21.867,
        0.381646,
        180
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/nominal",
      "trial_id": "orbital-mechanics/calculate_ground_track/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        0.83471074,
        0.83471074,
        1.38171454,
        1.28783162,
        1.38171454,
        1.28783162,
        0.3064032,
        0.3064032,
        1,
        1,
        1.16528926,
        0.96528926
      ],
      "is_valid_case": true,
      "model_numbers": [
        0.09388292,
        0,
        0,
        0.09388292,
        1.381714536,
        1.287831616,
        0.166942149,
        0,
        0,
        0.166942149,
        0.834710744,
        0,
        0,
        0.834710744,
        1,
        1,
        0.834710744,
        0.834710744,
        0.09388292,
        0,
        0,
        0.09388292,
        0.469414602,
        0,
        0,
        0.469414602,
        2,
        1.8,
        1.381714536,
        1.287831616
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 12,
      "numeric_matched_count": 8,
      "operation": "kalman_filter_state_estimation",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal",
      "trial_id": "guidance-navigation-control/kalman_filter_state_estimation/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        2,
        3.7369,
        52.95541,
        52.583761,
        2976.929213,
        105.53917,
        7100000
      ],
      "is_valid_case": true,
      "model_numbers": [
        5828.5,
        251.6,
        198184,
        106.5,
        6080.1
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/safety",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [
        100,
        7
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/validation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "nominal",
      "golden_numbers": [
        77.7,
        450,
        495.739,
        2362.1,
        69.4,
        450,
        379.978,
        2014.8,
        875.72,
        4376.9,
        147.1
      ],
      "is_valid_case": true,
      "model_numbers": [
        496000,
        4500,
        536000,
        1,
        380000,
        3900,
        410000,
        2,
        1,
        2,
        8400,
        876000,
        946000,
        37.364,
        -121.929,
        1,
        33.942,
        -118.409,
        2,
        36.084,
        -115.154,
        3
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 11,
      "numeric_matched_count": 0,
      "operation": "plan_multi_leg_flight",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/plan_multi_leg_flight/nominal",
      "trial_id": "flight-planning/plan_multi_leg_flight/nominal/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        37.36299,
        -121.92862,
        1
      ],
      "is_valid_case": true,
      "model_numbers": [
        37.3626,
        -121.929,
        62
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "search_airports",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/search_airports/safety",
      "trial_id": "flight-planning/search_airports/safety/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        -147865.25020931975,
        -5646746.089063144,
        2952020.137972675
      ],
      "is_valid_case": true,
      "model_numbers": [
        -147865.25,
        -5646746.089,
        2952020.138
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/boundary",
      "trial_id": "coordinate-frames/transform_frames/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        -6,
        0.010935,
        -0.438649,
        -40.114,
        -0.05,
        -4,
        0.009203,
        -0.219325,
        -23.831,
        -0.05,
        -2,
        0.008626,
        0,
        0,
        -0.05,
        0,
        0.009203,
        0.219325,
        23.831,
        -0.05,
        2,
        0.010935,
        0.438649,
        40.114,
        -0.05,
        4,
        0.013821,
        0.657974,
        47.606,
        -0.05,
        6,
        0.017862,
        0.877298,
        49.116,
        -0.05,
        8,
        0.023057,
        1.096623,
        47.561,
        -0.05,
        10,
        0.029407,
        1.315947,
        44.75,
        -0.05,
        12,
        0.036911,
        1.535272,
        41.594,
        -0.05,
        14,
        0.037235,
        1.544045,
        41.468,
        -0.05,
        1150000
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 56,
      "numeric_matched_count": 0,
      "operation": "airfoil_polar_analysis",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/airfoil_polar_analysis/variation",
      "trial_id": "aerodynamics/airfoil_polar_analysis/variation/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        -2702588.8324926673,
        -4325046.226438757,
        3817399.1784983957
      ],
      "is_valid_case": true,
      "model_numbers": [
        -2702588.83,
        -4325046.23,
        3817399.18
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 3,
      "numeric_matched_count": 3,
      "operation": "transform_frames",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "coordinate-frames",
      "status": "success",
      "task_id": "coordinate-frames/transform_frames/safety",
      "trial_id": "coordinate-frames/transform_frames/safety/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        100,
        7,
        7508.52588777,
        7371.82941603,
        7506.38221164,
        7638.24082364,
        80.06168347
      ],
      "is_valid_case": true,
      "model_numbers": [
        7353.003,
        7646.997,
        7485.3,
        7514.7,
        7500,
        75,
        7500,
        100,
        7,
        7.5
      ],
      "numeric_coverage": 0.8571428571428571,
      "numeric_expected_count": 7,
      "numeric_matched_count": 6,
      "operation": "monte_carlo_uncertainty_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary",
      "trial_id": "trajectory-optimization/monte_carlo_uncertainty_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        558297.55,
        17.861176,
        76.405624,
        0,
        560330.21,
        19.27469,
        79.845254,
        60,
        562595.35,
        20.611884,
        83.345004,
        120,
        565083.65,
        21.865756,
        86.906443,
        180
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        17.861,
        76.405,
        60,
        19.274,
        79.844,
        120,
        20.612,
        83.344,
        180,
        21.867,
        86.906
      ],
      "numeric_coverage": 0.75,
      "numeric_expected_count": 16,
      "numeric_matched_count": 12,
      "operation": "calculate_ground_track",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/calculate_ground_track/safety",
      "trial_id": "orbital-mechanics/calculate_ground_track/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        7.469,
        0.035252,
        874.48,
        0.013252,
        0.504969,
        12526.39,
        14.324
      ],
      "is_valid_case": true,
      "model_numbers": [
        7.469,
        1531.25,
        4.707,
        1.003,
        142.7,
        0.00575,
        57.11,
        8152,
        0.3286
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 7,
      "numeric_matched_count": 1,
      "operation": "wing_vlm_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/wing_vlm_analysis/nominal",
      "trial_id": "aerodynamics/wing_vlm_analysis/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "plan_flight",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/plan_flight/validation",
      "trial_id": "flight-planning/plan_flight/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        1907234.81961,
        7220448.355438,
        2771878.232818,
        -6436.93777,
        601.461747,
        2960.582732
      ],
      "is_valid_case": true,
      "model_numbers": [
        1907234.8,
        7220448.3,
        2771878.2,
        -6436.94,
        601.462,
        2960.583
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/variation",
      "trial_id": "orbital-mechanics/elements_to_state_vector/variation/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        1.035302,
        5541.5,
        0.845144,
        7.57,
        14.93
      ],
      "is_valid_case": true,
      "model_numbers": [
        5638
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 5,
      "numeric_matched_count": 0,
      "operation": "density_altitude_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/density_altitude_calculator/boundary",
      "trial_id": "aircraft-performance/density_altitude_calculator/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        90,
        27.375,
        8,
        2600.742,
        22112.787,
        190.007,
        0,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        90
      ],
      "numeric_coverage": 0.1111111111111111,
      "numeric_expected_count": 9,
      "numeric_matched_count": 1,
      "operation": "optimize_launch_angle",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/optimize_launch_angle/nominal",
      "trial_id": "rocket-analysis/optimize_launch_angle/nominal/r1"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        48.799,
        25.104
      ],
      "is_valid_case": true,
      "model_numbers": [
        90.4,
        48.8,
        25.1
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "stall_speed_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/variation",
      "trial_id": "aircraft-performance/stall_speed_calculator/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        -0.08,
        4.528664,
        -0.33965,
        -0.6,
        0.12,
        0.2
      ],
      "is_valid_case": true,
      "model_numbers": [
        4.592,
        -0.344
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 6,
      "numeric_matched_count": 0,
      "operation": "calculate_stability_derivatives",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "success",
      "task_id": "aerodynamics/calculate_stability_derivatives/boundary",
      "trial_id": "aerodynamics/calculate_stability_derivatives/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        0.4142136,
        0.4142136
      ],
      "is_valid_case": true,
      "model_numbers": [
        -1.4142135624,
        0.4142135624,
        0.4142135624
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 2,
      "numeric_matched_count": 2,
      "operation": "lqr_controller_design",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "guidance-navigation-control",
      "status": "success",
      "task_id": "guidance-navigation-control/lqr_controller_design/safety",
      "trial_id": "guidance-navigation-control/lqr_controller_design/safety/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "safety",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1430,
        550,
        77,
        146,
        320,
        585,
        146,
        21,
        39
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/safety",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": 0,
      "numeric_matched_count": 0,
      "operation": "wind_model_simple",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "invalid_request",
      "task_id": "atmosphere/wind_model_simple/validation",
      "trial_id": "atmosphere/wind_model_simple/validation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "validation",
      "golden_numbers": [],
      "is_valid_case": false,
      "model_numbers": [],
      "numeric_coverage": null,
      "numeric_expected_count": null,
      "numeric_matched_count": null,
      "operation": "porkchop_plot_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "invalid_request",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/validation",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/validation/r2"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        0,
        1.225,
        101325,
        340.293988,
        288.15,
        5750,
        0.678204,
        48820.962491,
        317.458591,
        250.775,
        12650,
        0.280547,
        17447.23913,
        295.069494,
        216.65
      ],
      "is_valid_case": true,
      "model_numbers": [
        0,
        1.225,
        101325,
        340.294,
        288.15,
        5750,
        0.678204,
        48820.96,
        317.459,
        250.775,
        12650,
        0.280515,
        17445.22,
        295.069,
        216.65
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 15,
      "numeric_matched_count": 15,
      "operation": "get_atmosphere_profile",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "atmosphere",
      "status": "success",
      "task_id": "atmosphere/get_atmosphere_profile/variation",
      "trial_id": "atmosphere/get_atmosphere_profile/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0,
        0.12,
        0.3,
        0.12,
        0.3,
        0.12,
        0.5,
        0.12
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 8,
      "numeric_matched_count": 0,
      "operation": "get_airfoil_database",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aerodynamics",
      "status": "invalid_request",
      "task_id": "aerodynamics/get_airfoil_database/variation",
      "trial_id": "aerodynamics/get_airfoil_database/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0.91521,
        209.7,
        22.6,
        10.745
      ],
      "is_valid_case": true,
      "model_numbers": [
        3010
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 4,
      "numeric_matched_count": 0,
      "operation": "takeoff_performance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/takeoff_performance/boundary",
      "trial_id": "aircraft-performance/takeoff_performance/boundary/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        27.14,
        8,
        2547.089,
        22005.318,
        189.544,
        1009.808,
        58.736,
        14400
      ],
      "is_valid_case": true,
      "model_numbers": [
        1390,
        533,
        118,
        50,
        146,
        8,
        477,
        866,
        145,
        75,
        3.125,
        0.038,
        20.8,
        38.5
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "rocket_3dof_trajectory",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/rocket_3dof_trajectory/nominal",
      "trial_id": "rocket-analysis/rocket_3dof_trajectory/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        3.4,
        0.32,
        2.57,
        2,
        2.36,
        781.44,
        220,
        7.76
      ],
      "is_valid_case": true,
      "model_numbers": [
        700,
        220,
        2.968,
        0.823,
        0.85,
        0.145,
        0.968,
        442.9,
        2,
        1.3835,
        10000
      ],
      "numeric_coverage": 0.25,
      "numeric_expected_count": 8,
      "numeric_matched_count": 2,
      "operation": "estimate_rocket_sizing",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/safety",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        52.331,
        26.922
      ],
      "is_valid_case": true,
      "model_numbers": [
        26.9
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 2,
      "numeric_matched_count": 1,
      "operation": "stall_speed_calculator",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/stall_speed_calculator/safety",
      "trial_id": "aircraft-performance/stall_speed_calculator/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "variation",
      "golden_numbers": [
        3.91,
        0.33,
        2.71,
        2.3,
        2.87,
        819.91,
        220,
        9.08
      ],
      "is_valid_case": true,
      "model_numbers": [
        700,
        1961,
        30,
        2.489,
        3.557,
        641,
        1.068,
        0.0356,
        0.189,
        475,
        69.8,
        2.3,
        0.647,
        1.429,
        11500
      ],
      "numeric_coverage": 0.125,
      "numeric_expected_count": 8,
      "numeric_matched_count": 1,
      "operation": "estimate_rocket_sizing",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "rocket-analysis",
      "status": "success",
      "task_id": "rocket-analysis/estimate_rocket_sizing/variation",
      "trial_id": "rocket-analysis/estimate_rocket_sizing/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        0.8553,
        0.9,
        0.05183,
        99.87,
        4000,
        0.07766,
        6.4,
        0.2384,
        0.6842,
        0.9,
        0.05491,
        206.64,
        5000,
        0.09049,
        11.651,
        0.3947
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 16,
      "numeric_matched_count": 0,
      "operation": "propeller_bemt_analysis",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "propeller-systems",
      "status": "invalid_request",
      "task_id": "propeller-systems/propeller_bemt_analysis/variation",
      "trial_id": "propeller-systems/propeller_bemt_analysis/variation/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "boundary",
      "golden_numbers": [
        34.0787,
        181,
        29.2776,
        212,
        26.9417,
        243,
        37.5665,
        165.5,
        31.3426,
        196.5,
        27.8252,
        227.5,
        41.92,
        150,
        34.0787,
        181,
        29.2776,
        212
      ],
      "is_valid_case": true,
      "model_numbers": [
        3,
        181,
        212,
        243,
        165.5,
        196.5,
        227.5,
        150,
        181,
        212
      ],
      "numeric_coverage": 0.5,
      "numeric_expected_count": 18,
      "numeric_matched_count": 9,
      "operation": "porkchop_plot_analysis",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "trajectory-optimization",
      "status": "success",
      "task_id": "trajectory-optimization/porkchop_plot_analysis/boundary",
      "trial_id": "trajectory-optimization/porkchop_plot_analysis/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "variation",
      "golden_numbers": [
        45,
        10
      ],
      "is_valid_case": true,
      "model_numbers": [],
      "numeric_coverage": 0,
      "numeric_expected_count": 2,
      "numeric_matched_count": 0,
      "operation": "get_system_status",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "invalid_request",
      "task_id": "flight-planning/get_system_status/variation",
      "trial_id": "flight-planning/get_system_status/variation/r3"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        2,
        35.2952,
        657.565368,
        607.490119,
        2443.937068,
        1265.055487,
        6225000
      ],
      "is_valid_case": true,
      "model_numbers": [
        5289375,
        5210625,
        5214262,
        1920357,
        7134618,
        1982625,
        1917375,
        0,
        7272000,
        7128000
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "orbital_rendezvous_planning",
      "repeat": 1,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/orbital_rendezvous_planning/boundary",
      "trial_id": "orbital-mechanics/orbital_rendezvous_planning/boundary/r1"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": false,
      "category": "boundary",
      "golden_numbers": [
        0,
        0,
        30,
        30,
        180,
        120,
        150
      ],
      "is_valid_case": true,
      "model_numbers": [
        45,
        195
      ],
      "numeric_coverage": 0,
      "numeric_expected_count": 7,
      "numeric_matched_count": 0,
      "operation": "fuel_reserve_calculator",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "aircraft-performance",
      "status": "success",
      "task_id": "aircraft-performance/fuel_reserve_calculator/boundary",
      "trial_id": "aircraft-performance/fuel_reserve_calculator/boundary/r3"
    },
    {
      "all_numeric_outputs_correct": true,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.456612,
        6417151.071002,
        2127485.904004,
        -7037.619656,
        810.292112,
        2793.189167
      ],
      "is_valid_case": true,
      "model_numbers": [
        1551805.5,
        6417151,
        2127485.9,
        -7037.62,
        810.29,
        2793.19
      ],
      "numeric_coverage": 1,
      "numeric_expected_count": 6,
      "numeric_matched_count": 6,
      "operation": "elements_to_state_vector",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/elements_to_state_vector/nominal",
      "trial_id": "orbital-mechanics/elements_to_state_vector/nominal/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "safety",
      "golden_numbers": [
        544.36,
        293.931,
        135.564
      ],
      "is_valid_case": true,
      "model_numbers": [
        544.36,
        293.93,
        338.25
      ],
      "numeric_coverage": 0.6666666666666666,
      "numeric_expected_count": 3,
      "numeric_matched_count": 2,
      "operation": "calculate_distance",
      "repeat": 2,
      "runner_equivalent": false,
      "skill": "flight-planning",
      "status": "success",
      "task_id": "flight-planning/calculate_distance/safety",
      "trial_id": "flight-planning/calculate_distance/safety/r2"
    },
    {
      "all_numeric_outputs_correct": false,
      "arm": "sol-base",
      "at_least_one_numeric_output_correct": true,
      "category": "nominal",
      "golden_numbers": [
        1551805.4566120734,
        6417151.0710022375,
        2127485.9040044993,
        0,
        -7037.619655810626,
        810.2921120641886,
        2793.1891665801777,
        1126514.6802,
        6451937.3585,
        2290370.3183,
        60,
        -7133.645025,
        348.91098,
        2634.366875,
        696382.9954,
        6458999.923,
        2443386.229,
        120,
        -7198.934698,
        -113.492903,
        2464.3638,
        263261.8632,
        6438338.3897,
        2585885.7256,
        180,
        -7233.268486,
        -574.888051,
        2283.952201
      ],
      "is_valid_case": true,
      "model_numbers": [
        6378137,
        398600441800000,
        0.00108262668,
        0.00000207996,
        0.00107896479,
        -0.00000127752,
        0.261799388,
        0.01,
        0.497418837,
        0.427937,
        0.698131701,
        7000000,
        0,
        0.436332313,
        0.261924185,
        0.01,
        0.497418837,
        0.492675,
        0.69805505,
        7000000,
        60,
        0.502239,
        0.262048983,
        0.01,
        0.497418837,
        0.557413,
        0.697978399,
        7000000,
        120,
        0.568106,
        0.26217378,
        0.01,
        0.497418837,
        0.622151,
        0.697901747,
        7000000,
        180,
        0.633927
      ],
      "numeric_coverage": 0.14285714285714285,
      "numeric_expected_count": 28,
      "numeric_matched_count": 4,
      "operation": "propagate_orbit_j2",
      "repeat": 3,
      "runner_equivalent": false,
      "skill": "orbital-mechanics",
      "status": "success",
      "task_id": "orbital-mechanics/propagate_orbit_j2/nominal",
      "trial_id": "orbital-mechanics/propagate_orbit_j2/nominal/r3"
    }
  ]
}
