{
  "bench_version": 1,
  "track": "dynamics",
  "model": "custom_equilibrium_rnn",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "iters": 24
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "iters": 8
        },
        "mean": 0.04040969908237457
      },
      {
        "cfg": {
          "lr": 0.003,
          "iters": 16
        },
        "mean": 0.008657814585603774
      },
      {
        "cfg": {
          "lr": 0.006,
          "iters": 24
        },
        "mean": 0.004971429007127881
      }
    ],
    "full": {
      "mean": 0.004260060406522825,
      "std": 0.0017312099173934859,
      "per_seed": [
        0.00337711232714355,
        0.007119504269212484,
        0.007134149316698313,
        0.002254950115457177,
        0.003825985360890627,
        0.003774178447201848,
        0.0037776767276227474,
        0.0028169266879558563
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.004260060406522825,
    "std": 0.0017312099173934859,
    "per_seed": [
      0.00337711232714355,
      0.007119504269212484,
      0.007134149316698313,
      0.002254950115457177,
      0.003825985360890627,
      0.003774178447201848,
      0.0037776767276227474,
      0.0028169266879558563
    ],
    "n": 8,
    "best_cfg": {
      "lr": 0.006,
      "iters": 24
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "iters": 8
        },
        "mean": 0.044312840327620506
      },
      {
        "cfg": {
          "lr": 0.003,
          "iters": 16
        },
        "mean": 0.008995423908345401
      },
      {
        "cfg": {
          "lr": 0.006,
          "iters": 24
        },
        "mean": 0.004260060406522825
      }
    ]
  },
  "comparison": {
    "delta_mean": 0.0,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0
    ],
    "p_value": 1.0,
    "mde": 0.0,
    "mde_rel_pct": 0.0,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "architecture_note": "Both arms train the same implicit tanh recurrent layer; baseline always iterates, idea certifies then falls back.",
  "runtime_sec": 50.54426717758179,
  "mechanism_signature": {
    "prediction": "trained-model local q below 0.8 predicts certification; q near/above 1 predicts fallback",
    "n_models": 8,
    "predicted_low_q_count": 0,
    "observed_certified_low_q_count": 0,
    "mean_q": 3.819756507873535,
    "min_q": 3.59490966796875,
    "max_q": 4.270003318786621,
    "q_values": [
      3.786127805709839,
      3.7302780151367188,
      3.6078004837036133,
      3.59490966796875,
      3.9719083309173584,
      4.270003318786621,
      3.7772746086120605,
      3.8197498321533203
    ],
    "certified_flags": [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0
    ],
    "confirmed": false
  }
}