{
  "bench_version": 1,
  "track": "sequence",
  "model": "routed_transformer",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.0015,
      "temperature": 0.7
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "temperature": 0.7
        },
        "mean": 0.9060439914464951
      },
      {
        "cfg": {
          "lr": 0.003,
          "temperature": 1.0
        },
        "mean": 0.9140874296426773
      },
      {
        "cfg": {
          "lr": 0.006,
          "temperature": 1.4
        },
        "mean": 0.934324100613594
      }
    ],
    "full": {
      "mean": 0.9060439914464951,
      "std": 0.051469292649903194,
      "per_seed": [
        0.8886425495147705,
        0.8025451302528381,
        0.9336193799972534,
        0.9243031740188599,
        0.9763924479484558,
        0.8652306199073792,
        0.9555761218070984,
        0.9020425081253052
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.9105898216366768,
    "std": 0.05785899431586753,
    "per_seed": [
      0.888859212398529,
      0.8320866227149963,
      0.8571396470069885,
      0.9573379158973694,
      1.0206561088562012,
      0.8799188733100891,
      0.9532520771026611,
      0.8954681158065796
    ],
    "n": 8,
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "temperature": 0.7,
          "delta": 0.08,
          "tau": 1.5
        },
        "mean": 0.910589799284935
      },
      {
        "cfg": {
          "lr": 0.0015,
          "temperature": 0.7,
          "delta": 0.12,
          "tau": 2.0
        },
        "mean": 0.9105898216366768
      },
      {
        "cfg": {
          "lr": 0.0015,
          "temperature": 0.7,
          "delta": 0.2,
          "tau": 3.0
        },
        "mean": 0.9105898290872574
      }
    ]
  },
  "comparison": {
    "delta_mean": 0.004545830190181732,
    "idea_wins": 3,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.00021666288375854492,
      0.029541492462158203,
      -0.07647973299026489,
      0.03303474187850952,
      0.04426366090774536,
      0.014688253402709961,
      -0.002324044704437256,
      -0.006574392318725586
    ],
    "p_value": 0.7749,
    "mde": 0.03139995443589797,
    "mde_rel_pct": 3.465610360239583,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "dwell >= delta/L_h",
    "delta_eta": 0.12,
    "L_h_observed": 0.27114981412887573,
    "predicted_min_dwell": 0.4425597722997692,
    "observed_switch_statistics": [
      {
        "switches": 0,
        "h_deriv": 0.24736255407333374
      },
      {
        "switches": 191,
        "h_deriv": 0.20790597796440125
      },
      {
        "switches": 0,
        "h_deriv": 0.09646739065647125
      },
      {
        "switches": 322,
        "h_deriv": 0.27114981412887573
      },
      {
        "switches": 0,
        "h_deriv": 0.23078395426273346
      },
      {
        "switches": 174,
        "h_deriv": 0.19567811489105225
      },
      {
        "switches": 0,
        "h_deriv": 0.0626426488161087
      },
      {
        "switches": 0,
        "h_deriv": 0.10217791795730591
      }
    ],
    "confirmed": false,
    "note": "The bench forward pass records switches but does not expose per-example dwell intervals."
  }
}