{
  "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": 0.004247799690347165
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.0018907261837739497
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.0005508567701326683
      }
    ],
    "full": {
      "mean": 0.00043304020073264837,
      "std": 0.00018680572581609252,
      "per_seed": [
        0.000348469679011032,
        0.00044166683801449835,
        0.0005423855036497116,
        0.0008709050598554313,
        0.00039059933624230325,
        0.0003389842459000647,
        0.0002937567769549787,
        0.00023755416623316705
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 1.8605211664635135e-05,
    "std": 2.831933136541298e-05,
    "per_seed": [
      1.025223082251614e-05,
      5.093114396004239e-06,
      3.275605195085518e-06,
      2.0394263628986664e-05,
      5.965866421320243e-06,
      7.376182111329399e-06,
      9.230343130184337e-05,
      4.180999439995503e-06
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.00041443498906801324,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.00033821744818851585,
      -0.0004365737236184941,
      -0.0005391098984546261,
      -0.0008505107962264447,
      -0.000384633469820983,
      -0.0003316080637887353,
      -0.00020145334565313533,
      -0.00023337316679317155
    ],
    "p_value": 0.0081,
    "mde": 0.0001724928317781249,
    "mde_rel_pct": 39.832983516608664,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "predicted_slowest_memory_mode": 0.3352634608745575,
    "observed_max_state_norm": 2.583609104156494,
    "bounded_observed_state": true,
    "confirmed": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "mean": 5.264711217023432e-05
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "mean": 1.748438717186218e-05
    },
    {
      "cfg": {
        "lr": 0.01
      },
      "mean": 9.75380351064814e-06
    }
  ],
  "idea_best_cfg": {
    "lr": 0.01
  },
  "track_justification": "Dynamics is structurally matched: the task is actuated pendulum forecasting and the intervention is a stable recurrent memory state.",
  "search_space_parity": {
    "baseline_grid": [
      0.001,
      0.003,
      0.01
    ],
    "idea_grid": [
      0.001,
      0.003,
      0.01
    ],
    "selected_idea_lr": 0.01
  },
  "parameterization": {
    "baseline_params": 3585,
    "idea_params": 16077,
    "epochs": 12,
    "n_train": 1000,
    "n_test": 300
  }
}