{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.264630239456892
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.012804438127204776
      },
      {
        "cfg": {
          "lr": 0.006
        },
        "mean": 0.013572414871305227
      }
    ],
    "full": {
      "mean": 0.013181458110921085,
      "std": 0.006411194717789758,
      "per_seed": [
        0.01743449829518795,
        0.00642412668094039,
        0.02289336547255516,
        0.004465762060135603,
        0.010089418850839138,
        0.00904592964798212,
        0.013677984476089478,
        0.02142057940363884
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.01246260676998645,
    "std": 0.006610495470253576,
    "per_seed": [
      0.013938470743596554,
      0.006079694721847773,
      0.00940709188580513,
      0.00654940539970994,
      0.016593003645539284,
      0.009614327922463417,
      0.009874203242361546,
      0.027644656598567963
    ],
    "n": 8,
    "best_cfg": {
      "lr": 0.003
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.2671995013952255
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.008993665687739849
      },
      {
        "cfg": {
          "lr": 0.006
        },
        "mean": 0.010689508053474128
      }
    ]
  },
  "comparison": {
    "delta_mean": -0.0007188513409346342,
    "idea_wins": 4,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0034960275515913963,
      -0.00034443195909261703,
      -0.01348627358675003,
      0.002083643339574337,
      0.006503584794700146,
      0.0005683982744812965,
      -0.003803781233727932,
      0.006224077194929123
    ],
    "p_value": 0.778,
    "mde": 0.005384277405441072,
    "mde_rel_pct": 40.847358161234816,
    "verdict": "no significant win",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "trained-model gain weighting lowers normalized local certificate versus q=0",
    "observed_normalized_mu": 17.170748114585876,
    "observed_unscaled_mu": 18.16585087776184,
    "relative_reduction": 0.05477875877502347,
    "clusters_from_trained_models": [
      [
        0,
        1,
        5
      ],
      [
        2,
        4
      ],
      [
        3,
        6,
        7
      ]
    ],
    "confirmed": true
  }
}