{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "epochs": 10,
      "lam": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 10,
          "lam": 0.0
        },
        "mean": 0.022081697126850486
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 10,
          "lam": 0.0
        },
        "mean": 0.0036966767656849697
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 10,
          "lam": 0.0
        },
        "mean": 0.0033956777187995613
      }
    ],
    "full": {
      "mean": 0.0028021317266393453,
      "std": 0.001671312456779879,
      "per_seed": [
        0.001397879095748067,
        0.004815699998289347,
        0.0011151251383125782,
        0.006254006642848253,
        0.001966016599908471,
        0.002434998285025358,
        0.0020769357215613127,
        0.0023563923314213753
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.002574730635387823,
    "std": 0.0013220860264022514,
    "per_seed": [
      0.0030565059278160334,
      0.0013654178474098444,
      0.003834570525214076,
      0.005198074039071798,
      0.0012422980507835746,
      0.0024880883283913136,
      0.002220690716058016,
      0.0011921996483579278
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.0002274010912515223,
    "idea_wins": 4,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0016586268320679665,
      -0.0034502821508795023,
      0.002719445386901498,
      -0.001055932603776455,
      -0.0007237185491248965,
      5.309004336595535e-05,
      0.00014375499449670315,
      -0.0011641926830634475
    ],
    "p_value": 0.72035,
    "mde": 0.0015692337631269659,
    "mde_rel_pct": 56.00142734934808,
    "verdict": "no significant win",
    "system_worked": false
  },
  "math_check": {
    "c2_input_composition_max_abs": 0.0,
    "c2_output_composition_max_abs": 0.0,
    "exact_transform_identity": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "epochs": 10,
        "lam": 0.05
      },
      "mean": 0.022260770318098366
    },
    {
      "cfg": {
        "lr": 0.001,
        "epochs": 10,
        "lam": 0.2
      },
      "mean": 0.022491522133350372
    },
    {
      "cfg": {
        "lr": 0.001,
        "epochs": 10,
        "lam": 1.0
      },
      "mean": 0.020668090670369565
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 10,
        "lam": 0.05
      },
      "mean": 0.0037502831255551428
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 10,
        "lam": 0.2
      },
      "mean": 0.0036739293136633933
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 10,
        "lam": 1.0
      },
      "mean": 0.00422825881105382
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 10,
        "lam": 0.05
      },
      "mean": 0.0037559740303549916
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 10,
        "lam": 0.2
      },
      "mean": 0.003363642084877938
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 10,
        "lam": 1.0
      },
      "mean": 0.0034596045152284205
    }
  ],
  "structural_match": "controlled pendulum rollout has sign-equivariant local dynamics",
  "mechanism_signature": {
    "mean_prediction_abs": 0.7621783018112183,
    "trained_model_c2_penalty": 0.0005555228563025594,
    "prediction_metric_seed0": 0.0030565059278160334,
    "expected_c2_penalty_direction": "lower is more equivariant",
    "confirmed": true
  }
}