{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small_fractional",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.0004224302538204938
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 3.919086066161981e-05
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 1.4552034826920135e-05
      }
    ],
    "full": {
      "mean": 1.477801822602487e-05,
      "std": 5.904456722576056e-06,
      "per_seed": [
        2.641624269017484e-05,
        8.83757365954807e-06,
        8.367352165805642e-06,
        1.4586970792151988e-05,
        1.0999674486811273e-05,
        2.1751329768449068e-05,
        1.276554939977359e-05,
        1.4499452845484484e-05
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.00025887351512210444,
    "std": 5.818967880653584e-05,
    "per_seed": [
      0.0002734987938310951,
      0.00015879524289630353,
      0.00034040064201690257,
      0.00028941663913428783,
      0.000296872021863237,
      0.00026502739638090134,
      0.0002749341365415603,
      0.0001720432483125478
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.00024409549689607957,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.00024708255114092026,
      0.00014995766923675546,
      0.0003320332898510969,
      0.00027482966834213585,
      0.00028587234737642575,
      0.00024327606661245227,
      0.0002621685871417867,
      0.00015754379546706332
    ],
    "p_value": 0.0081,
    "mde": 5.2037973707415915e-05,
    "mde_rel_pct": 352.13093468631877,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "math_sanity": [
      {
        "dt": 0.1,
        "predicted_rho": 0.9992190550963239,
        "observed_rho": 0.9992190550963239,
        "stable": true
      },
      {
        "dt": 1.0,
        "predicted_rho": 0.9922179382602435,
        "observed_rho": 0.9922179382602435,
        "stable": true
      },
      {
        "dt": 4.0,
        "predicted_rho": 0.9692332344763441,
        "observed_rho": 0.9692332344763441,
        "stable": true
      },
      {
        "predicted_log_slope": -0.5,
        "observed_log_slope": -0.8731882906575884,
        "abs_error": 0.3731882906575884,
        "positive_weights": true
      }
    ],
    "trained_model_behavior": {
      "prediction": "trained exponential-bank memory impulse log-slope p-1",
      "p": 0.5,
      "predicted": -0.5,
      "observed": -0.8731883349875018,
      "abs_error": 0.3731883349875018,
      "trained_positive_weights": true,
      "measurement": "trained model lam/w state response",
      "confirmed": false
    },
    "track_choice": "dynamics: actuated pendulum stability/control is structurally matched",
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "p": 0.5
        },
        "mean": 0.00031832019703870174
      },
      {
        "cfg": {
          "lr": 0.003,
          "p": 0.5
        },
        "mean": 0.00025887351512210444
      },
      {
        "cfg": {
          "lr": 0.01,
          "p": 0.5
        },
        "mean": 0.0007522592495661229
      }
    ]
  },
  "stage2_protocol": {
    "epochs": 12,
    "batch": 128,
    "baseline_grid": [
      {
        "lr": 0.001
      },
      {
        "lr": 0.003
      },
      {
        "lr": 0.01
      }
    ],
    "idea_grid": [
      {
        "lr": 0.001,
        "p": 0.5
      },
      {
        "lr": 0.003,
        "p": 0.5
      },
      {
        "lr": 0.01,
        "p": 0.5
      }
    ],
    "paired_seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ]
  }
}