{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.001864717691205442
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.0010901302302954718
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.0006186682076076977
      }
    ],
    "full": {
      "mean": 0.00054517226817552,
      "std": 0.00020361842727135583,
      "per_seed": [
        0.0004930912400595844,
        0.0004765945195686072,
        0.0004673648509196937,
        0.0010376222198829055,
        0.000511663849465549,
        0.00027233464061282575,
        0.0005571767687797546,
        0.0005455300561152399
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.0005829526708112098,
    "std": 0.00020220543356011604,
    "per_seed": [
      0.000502792012412101,
      0.0004844724608119577,
      0.0005921015981584787,
      0.0010409810347482562,
      0.000540185603313148,
      0.00027245740056969225,
      0.000595726422034204,
      0.0006349048344418406
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 3.7780402635689825e-05,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      9.700772352516651e-06,
      7.877941243350506e-06,
      0.00012473674723878503,
      3.3588148653507233e-06,
      2.852175384759903e-05,
      1.2275995686650276e-07,
      3.854965325444937e-05,
      8.937477832660079e-05
    ],
    "p_value": 0.0081,
    "mde": 3.818063477530496e-05,
    "mde_rel_pct": 7.003407363892651,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "idea_grid": [
    {
      "lr": 0.01,
      "target": 0.1,
      "lam": 1.0
    },
    {
      "lr": 0.01,
      "target": 0.2,
      "lam": 1.0
    },
    {
      "lr": 0.01,
      "target": 0.3,
      "lam": 1.0
    }
  ],
  "baseline_lr_union": [
    0.001,
    0.003,
    0.01
  ],
  "epochs": 18,
  "n_train": 400,
  "structural_match": "dynamics stability/control; paired end-to-end systems",
  "parameter_count_baseline": 13313,
  "parameter_count_idea": 13313,
  "mechanism_signature": {
    "baseline": {
      "predicted_radius_target": 0.98,
      "observed_local_jacobian_gain_mean": 0.3045346140861511,
      "observed_full_input_jacobian_gain_mean": 0.45282769203186035,
      "observed_local_gain_median": 0.30631518363952637,
      "n_samples": 32,
      "confirmed": true
    },
    "idea": {
      "predicted_radius_target": 0.98,
      "observed_local_jacobian_gain_mean": 0.2943377196788788,
      "observed_full_input_jacobian_gain_mean": 0.44500285387039185,
      "observed_local_gain_median": 0.29613810777664185,
      "n_samples": 32,
      "confirmed": true
    },
    "prediction": "idea should reduce trained-model local Jacobian gain toward target 0.98",
    "confirmed": true
  }
}