{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.00430093941395171
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.0033809992601163685
      },
      {
        "cfg": {
          "lr": 0.006
        },
        "mean": 0.002017002771026455
      }
    ],
    "full": {
      "mean": 0.0022443737179855816,
      "std": 0.0006826101486098914,
      "per_seed": [
        0.0008340506465174258,
        0.0019196165958419442,
        0.002481805393472314,
        0.0028325384482741356,
        0.0020983400754630566,
        0.0018523626495152712,
        0.003032150212675333,
        0.0029041257221251726
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.00194204316358082,
    "std": 0.0005946512584653817,
    "per_seed": [
      0.0025444745551794767,
      0.0021839358378201723,
      0.0014850844163447618,
      0.0013838530285283923,
      0.002973762573674321,
      0.002029680646955967,
      0.0018950217636302114,
      0.001040532486513257
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.00030233055440476164,
    "idea_wins": 4,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.001710423908662051,
      0.0002643192419782281,
      -0.000996720977127552,
      -0.0014486854197457433,
      0.0008754224982112646,
      0.00017731799744069576,
      -0.0011371284490451217,
      -0.0018635932356119156
    ],
    "p_value": 0.51515,
    "mde": 0.0010443640298036328,
    "mde_rel_pct": 46.532536958283075,
    "verdict": "no significant win",
    "system_worked": false
  },
  "mechanism_signature": {
    "math_check": {
      "checked": true,
      "L": 0.7,
      "delta": 0.767539284296568,
      "sample_min": 0.36195731104790524,
      "cloud_min": 0.3268021435301365,
      "bound": -0.17532018795969234
    },
    "mechanism_signature": {
      "prediction": "adaptive reachable-state selection should reduce empirical coverage radius at equal simulator budget",
      "observed": {
        "baseline_delta": 0.7605222459149111,
        "idea_delta": 0.3445205023070951,
        "baseline_pool_mse": 1.55548095703125,
        "idea_pool_mse": 1.5370749235153198,
        "baseline_min_sample_residual": -0.5907788276672363,
        "idea_min_sample_residual": -0.6713848114013672
      },
      "relative_delta_reduction_pct": 54.699483919417034,
      "confirmed": true
    },
    "idea_grid_results": [
      [
        0.012647395371459424,
        {
          "lr": 0.001
        }
      ],
      [
        0.003680584253743291,
        {
          "lr": 0.003
        }
      ],
      [
        0.0018993369594682008,
        {
          "lr": 0.006
        }
      ]
    ],
    "selected_idea_cfg": {
      "lr": 0.006
    },
    "budget": {
      "epochs": 12,
      "train_samples": 400,
      "pool_samples": 1600
    }
  }
}