{
  "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": 0.02264283667318523
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.006244247197173536
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.00514151350944303
      }
    ],
    "full": {
      "mean": 0.004185360565315932,
      "std": 0.00262482957347662,
      "per_seed": [
        0.0021960907615721226,
        0.008501192554831505,
        0.0017922910628840327,
        0.008076479658484459,
        0.0030377130024135113,
        0.0011907307198271155,
        0.0035283213946968317,
        0.005160065367817879
      ],
      "n": 8
    },
    "union_grid": [
      {
        "lr": 0.001
      },
      {
        "lr": 0.003
      },
      {
        "lr": 0.01
      }
    ]
  },
  "idea": {
    "mean": 0.002211095365055371,
    "std": 0.001581263928471004,
    "per_seed": [
      0.0014746395172551274,
      0.002074356423690915,
      0.000778969086240977,
      0.0025305193848907948,
      0.002626171102747321,
      0.0014305157819762826,
      0.006008145399391651,
      0.0007654462242498994
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.001974265200260561,
    "idea_wins": 6,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0007214512443169951,
      -0.00642683613114059,
      -0.0010133219766430557,
      -0.005545960273593664,
      -0.00041154189966619015,
      0.00023978506214916706,
      0.0024798240046948195,
      -0.004394619143567979
    ],
    "p_value": 0.14225,
    "mde": 0.0026083344497749737,
    "mde_rel_pct": 62.32042398904009,
    "verdict": "no significant win",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "result": {
        "mean": 0.06869563926011324,
        "std": 0.06865088808304035,
        "per_seed": [
          0.0694878026843071,
          0.22950862348079681,
          0.026874704286456108,
          0.011694572865962982,
          0.01833035983145237,
          0.047722410410642624,
          0.11673897504806519,
          0.029207665473222733
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "result": {
        "mean": 0.013020415848586708,
        "std": 0.007406346915347002,
        "per_seed": [
          0.017435848712921143,
          0.02717023342847824,
          0.010481353849172592,
          0.005967922043055296,
          0.004026471171528101,
          0.011689518578350544,
          0.019995147362351418,
          0.007396831642836332
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01
      },
      "result": {
        "mean": 0.002211095365055371,
        "std": 0.001581263928471004,
        "per_seed": [
          0.0014746395172551274,
          0.002074356423690915,
          0.000778969086240977,
          0.0025305193848907948,
          0.002626171102747321,
          0.0014305157819762826,
          0.006008145399391651,
          0.0007654462242498994
        ],
        "n": 8
      }
    }
  ],
  "structural_match": "Dynamics track directly tests recurrent trajectory sensitivity and long-horizon stability.",
  "mechanism_signature": {
    "predicted_ratio_bound": 0.9591663046625439,
    "observed_mean_ratio": NaN,
    "predicted_lmi_bound": 0.0,
    "observed_max_lmi": NaN,
    "confirmed": false
  },
  "selected_idea_cfg": {
    "lr": 0.01
  }
}