{
  "bench_version": 1,
  "track": "dynamics",
  "model": "cyclic_rnn",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0
        },
        "mean": 0.073138820938766
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.01337075512856245
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0
        },
        "mean": 0.004462164011783898
      }
    ],
    "full": {
      "mean": 0.004087189445272088,
      "std": 0.0010007874399045344,
      "per_seed": [
        0.005726089235395193,
        0.0033913287334144115,
        0.004283653572201729,
        0.004447584506124258,
        0.0049942112527787685,
        0.0028478815220296383,
        0.002599592786282301,
        0.004407173953950405
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.004080623359186575,
    "std": 0.0010004881538153208,
    "per_seed": [
      0.005722619593143463,
      0.003379821078851819,
      0.004280869383364916,
      0.004445591010153294,
      0.004983154591172934,
      0.0028435608837753534,
      0.0025958793703466654,
      0.0043934909626841545
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -6.566086085513234e-06,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -3.469642251729965e-06,
      -1.1507654562592506e-05,
      -2.784188836812973e-06,
      -1.9934959709644318e-06,
      -1.1056661605834961e-05,
      -4.320638254284859e-06,
      -3.7134159356355667e-06,
      -1.368299126625061e-05
    ],
    "p_value": 0.0081,
    "mde": 3.91188445758878e-06,
    "mde_rel_pct": 0.0957108670877467,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "note": "trained-model zero-input Fourier perturbation; q=0",
    "signature": {
      "q": 0,
      "kappa": 0.15,
      "rows": [
        {
          "system": "baseline",
          "weights": [
            1.1289324760437012,
            1.1723648309707642,
            1.1778165102005005,
            1.2012455463409424
          ],
          "modes": [
            {
              "mode": 1,
              "predicted": -0.09919014415880456,
              "observed": -0.04295965945097118
            },
            {
              "mode": 2,
              "predicted": -0.3536465652791994,
              "observed": -0.17734158165416888
            },
            {
              "mode": 3,
              "predicted": -0.6558346787734254,
              "observed": -0.42319134910019884
            }
          ]
        },
        {
          "system": "idea",
          "weights": [
            1.1295150518417358,
            1.173497200012207,
            1.1802256107330322,
            1.20441734790802
          ],
          "modes": [
            {
              "mode": 1,
              "predicted": -0.09940500360509097,
              "observed": -0.04295041987070078
            },
            {
              "mode": 2,
              "predicted": -0.3544018135383647,
              "observed": -0.17730516519047812
            },
            {
              "mode": 3,
              "predicted": -0.6571983150619246,
              "observed": -0.42311798056693856
            }
          ]
        }
      ],
      "max_relative_error": 0.5679249704438308,
      "confirmed": false,
      "task_metric_seed0": {
        "baseline": 0.005726089235395193,
        "idea": 0.005722619593143463
      }
    }
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "weight_decay": 0.0
      },
      "mean": 0.07314319256693125
    },
    {
      "cfg": {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      "mean": 0.013368312735110521
    },
    {
      "cfg": {
        "lr": 0.01,
        "weight_decay": 0.0
      },
      "mean": 0.004457225266378373
    }
  ],
  "protocol": {
    "paired_seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ],
    "train_samples": 400,
    "test_samples": 200,
    "epochs": 18,
    "architecture": "same CyclicRNN; barrier only differs"
  }
}