{
  "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": 0.0007079141651047394
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.00019564990725484677
      },
      {
        "cfg": {
          "lr": 0.006
        },
        "mean": 4.179111101620947e-05
      }
    ],
    "full": {
      "mean": 3.971884348175081e-05,
      "std": 7.221693826148878e-06,
      "per_seed": [
        4.624741632142104e-05,
        5.4139207350090146e-05,
        2.856133687600959e-05,
        3.82164835173171e-05,
        4.160348544246517e-05,
        3.6566088965628296e-05,
        3.5268141800770536e-05,
        3.714858758030459e-05
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 8.592086487624329e-05,
    "std": 7.508073923840228e-05,
    "per_seed": [
      0.00011502060806378722,
      6.843992014182732e-05,
      0.00027265894459560513,
      4.1655894165160134e-05,
      7.501575601054356e-05,
      4.787765283253975e-05,
      3.653249950730242e-05,
      3.0165643693180755e-05
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 4.6202021394492476e-05,
    "idea_wins": 1,
    "n_pairs": 8,
    "per_seed_diffs": [
      6.877319174236618e-05,
      1.4300712791737169e-05,
      0.00024409760771959554,
      3.439410647843033e-06,
      3.3412270568078384e-05,
      1.1311563866911456e-05,
      1.2643577065318823e-06,
      -6.982943887123838e-06
    ],
    "p_value": 0.03865,
    "mde": 6.977709898395673e-05,
    "mde_rel_pct": 175.67756980642312,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "math_check": {
    "joint_min_eig": 0.542706194000172,
    "schur_min_eig": 0.6700584265307041,
    "psd": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "result": {
        "mean": 8.592086487624329e-05,
        "std": 7.508073923840228e-05,
        "per_seed": [
          0.00011502060806378722,
          6.843992014182732e-05,
          0.00027265894459560513,
          4.1655894165160134e-05,
          7.501575601054356e-05,
          4.787765283253975e-05,
          3.653249950730242e-05,
          3.0165643693180755e-05
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "result": {
        "mean": 0.00017516915022497415,
        "std": 0.00014182129868597662,
        "per_seed": [
          0.00031262406264431775,
          4.148928201175295e-05,
          0.0004854888829868287,
          8.179861470125616e-05,
          0.00012095236161258072,
          5.18705346621573e-05,
          0.00014855564222671092,
          0.0001585738209541887
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.006
      },
      "result": {
        "mean": 0.0001611893669632991,
        "std": 0.00019513377033064536,
        "per_seed": [
          1.1867330613313243e-05,
          0.000506327603943646,
          1.7718439266900532e-05,
          0.00010111019219039008,
          0.0004840953042730689,
          2.954796582343988e-05,
          8.626402268419042e-05,
          5.2584076911443844e-05
        ],
        "n": 8
      }
    }
  ],
  "budget": {
    "epochs": 18,
    "batch": 128,
    "n_train": 1600,
    "n_test": 500
  },
  "mechanism_signature": {
    "prediction": "joint Gaussian head yields calibrated predictive variance; 95% interval coverage near nominal 0.95",
    "observed_nll": -2.5754659175872803,
    "observed_coverage95": 1.0,
    "observed_mean_variance": 0.0008512148051522672,
    "confirmed": true
  }
}