{
  "bench_version": 1,
  "track": "dynamics",
  "model": "rnn_small",
  "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": 0.00222656229743734
      },
      {
        "cfg": {
          "lr": 0.001,
          "weight_decay": 0.0001
        },
        "mean": 0.002201732073444873
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.0012092416291125119
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001
        },
        "mean": 0.0011863615218317136
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0
        },
        "mean": 0.0006035602564224973
      },
      {
        "cfg": {
          "lr": 0.01,
          "weight_decay": 0.0001
        },
        "mean": 0.0006214260865817778
      }
    ],
    "full": {
      "mean": 0.000540327702765353,
      "std": 0.00010833688702413184,
      "per_seed": [
        0.0005864710547029972,
        0.0004609658499248326,
        0.000695098948199302,
        0.0006717051728628576,
        0.0005945063894614577,
        0.00035726596252061427,
        0.0004858067259192467,
        0.0004708015185315162
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.000540327702765353,
    "std": 0.00010833688702413184,
    "per_seed": [
      0.0005864710547029972,
      0.0004609658499248326,
      0.000695098948199302,
      0.0006717051728628576,
      0.0005945063894614577,
      0.00035726596252061427,
      0.0004858067259192467,
      0.0004708015185315162
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.0,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0,
      0.0
    ],
    "p_value": 1.0,
    "mde": 0.0,
    "mde_rel_pct": 0.0,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "training enforces nonpositive expected barrier drift on continuation states; held-out drift should be lower than zero",
    "predicted_mean_drift": 0.00018591515208754572,
    "heldout_mean_drift": 0.00018507556751501397,
    "margin": 0.02,
    "confirmed": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "lam": 0.5
      },
      "result": {
        "mean": 0.0021250569116091356,
        "std": 0.000452414474028617,
        "per_seed": [
          0.0021977173164486885,
          0.0023012966848909855,
          0.0026522083207964897,
          0.0017550268676131964,
          0.002219437388703227,
          0.0011543183354660869,
          0.002609655261039734,
          0.0021107951179146767
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003,
        "lam": 1.0
      },
      "result": {
        "mean": 0.0011597898919717409,
        "std": 0.0003122565544309852,
        "per_seed": [
          0.0009158510947600007,
          0.001064310665242374,
          0.0017766037490218878,
          0.001080201007425785,
          0.0010183502454310656,
          0.0006965000065974891,
          0.0013033286668360233,
          0.0014231737004593015
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01,
        "lam": 2.0
      },
      "result": {
        "mean": 0.000540327702765353,
        "std": 0.00010833688702413184,
        "per_seed": [
          0.0005864710547029972,
          0.0004609658499248326,
          0.000695098948199302,
          0.0006717051728628576,
          0.0005945063894614577,
          0.00035726596252061427,
          0.0004858067259192467,
          0.0004708015185315162
        ],
        "n": 8
      }
    }
  ],
  "math_sanity": {
    "claim": "E[B_next]-B <= 0 implies failure probability <= B",
    "expected_B_next_state0": 0.69,
    "B_state0": 0.7,
    "drift_state0": -0.010000000000000009,
    "failure_probability": 0.6666666666666666,
    "bound_holds": true
  },
  "protocol_note": "Matched dynamics task and shared GRU predictor/barrier-head architecture; only auxiliary uniform stochastic barrier loss differs. All idea learning rates are included in baseline sweep."
}