{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "epochs": 8
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 8
        },
        "mean": 0.0228443113155663
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 8
        },
        "mean": 0.006279829074628651
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 8
        },
        "mean": 0.005194205295993015
      }
    ],
    "full": {
      "mean": 0.004214190877974033,
      "std": 0.0026682777355217157,
      "per_seed": [
        0.002182353986427188,
        0.008899358101189137,
        0.0017826670082286,
        0.007912442088127136,
        0.003060318995267153,
        0.0012072835816070437,
        0.0036685036029666662,
        0.005000599659979343
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.004029877163702622,
    "std": 0.0015034226018154422,
    "per_seed": [
      0.0031153184827417135,
      0.0026313886046409607,
      0.006552070379257202,
      0.0028610709123313427,
      0.005238592624664307,
      0.002022449392825365,
      0.004396332893520594,
      0.005421794019639492
    ],
    "n": 8,
    "selected_cfg": {
      "lr": 0.01,
      "epochs": 8
    }
  },
  "comparison": {
    "delta_mean": -0.0001843137142714113,
    "idea_wins": 2,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0009329644963145256,
      -0.006267969496548176,
      0.004769403371028602,
      -0.0050513711757957935,
      0.002178273629397154,
      0.0008151658112183213,
      0.0007278292905539274,
      0.0004211943596601486
    ],
    "p_value": 0.9399,
    "mde": 0.003068421703670571,
    "mde_rel_pct": 72.81164504693035,
    "verdict": "no significant win",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "recursive predicted variance should calibrate observed squared error near 1 and track heteroscedasticity",
    "predicted_vs_observed": {
      "mean_q_recursive": 0.8105446696281433,
      "mean_observed_squared_error": 0.005421794019639492,
      "calibration_ratio_mean": 0.005157590081528752,
      "calibration_ratio_per_seed": [
        0.003714949226948883,
        0.0034924976914672296,
        0.00926556392303059,
        0.003918822999611737,
        0.006340776802686519,
        0.002460186822311339,
        0.005378848268044676,
        0.00668907491812904
      ],
      "q_error_correlation_mean": -0.09872341295990021
    },
    "confirmed": false
  },
  "protocol_notes": {
    "structural_match": "multi-step stochastic actuated pendulum rollout; recursive uncertainty applies to transition branches",
    "baseline": "standard MSE training",
    "idea": "mean/variance RNN with detached recursive child q plus between-child variance",
    "n_train": 400,
    "n_test": 200,
    "branch_count": 4,
    "grid_union": [
      {
        "lr": 0.001,
        "epochs": 8
      },
      {
        "lr": 0.003,
        "epochs": 8
      },
      {
        "lr": 0.01,
        "epochs": 8
      }
    ]
  }
}