{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.0015,
      "epochs": 12
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "epochs": 12
        },
        "mean": 0.42323087900877
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12
        },
        "mean": 0.4927415996789932
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12
        },
        "mean": 0.721754178404808
      }
    ],
    "full": {
      "mean": 0.44760169088840485,
      "std": 0.0483900971330472,
      "per_seed": [
        0.3936149477958679,
        0.3890821635723114,
        0.40740370750427246,
        0.5028226971626282,
        0.4323761761188507,
        0.4885129928588867,
        0.5237836837768555,
        0.4432171583175659
      ],
      "n": 8
    }
  },
  "idea": {
    "config": {
      "lr": 0.0015,
      "epochs": 12
    },
    "per_seed": [
      0.36546337604522705,
      0.33078253269195557,
      0.3787442743778229,
      0.4493727684020996,
      0.35211890935897827,
      0.4167359173297882,
      0.4435553252696991,
      0.30875149369239807
    ],
    "details": [
      {
        "seed": 0,
        "metric": 0.36546337604522705,
        "final_train_loss": 0.3290974372625351
      },
      {
        "seed": 1,
        "metric": 0.33078253269195557,
        "final_train_loss": 0.3341557741165161
      },
      {
        "seed": 2,
        "metric": 0.3787442743778229,
        "final_train_loss": 0.3714332640171051
      },
      {
        "seed": 3,
        "metric": 0.4493727684020996,
        "final_train_loss": 0.35627098798751833
      },
      {
        "seed": 4,
        "metric": 0.35211890935897827,
        "final_train_loss": 0.3012402510643005
      },
      {
        "seed": 5,
        "metric": 0.4167359173297882,
        "final_train_loss": 0.34340501070022583
      },
      {
        "seed": 6,
        "metric": 0.4435553252696991,
        "final_train_loss": 0.3110033637285233
      },
      {
        "seed": 7,
        "metric": 0.30875149369239807,
        "final_train_loss": 0.2961388397216797
      }
    ],
    "mean": 0.3806905746459961
  },
  "comparison": {
    "delta_mean": -0.06691111624240875,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.02815157175064087,
      -0.058299630880355835,
      -0.028659433126449585,
      -0.053449928760528564,
      -0.08025726675987244,
      -0.07177707552909851,
      -0.08022835850715637,
      -0.13446566462516785
    ],
    "p_value": 0.0081,
    "mde": 0.028554757083691817,
    "mde_rel_pct": 6.379501611581497,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "quantity": "trained gate vs one-step Fisher-KPP prediction",
    "predicted_gate_rmse": 0.4042392542224135,
    "observed_front_index_mean": 0.37890625,
    "tolerance": 0.15,
    "confirmed": false
  },
  "math_sanity": {
    "speed_scaling": [
      {
        "D": 0.1,
        "r": 1.0,
        "predicted": 0.6324555320336759,
        "observed": 0.6649048996195985,
        "relative_error": 0.05130695510177757
      },
      {
        "D": 0.25,
        "r": 1.0,
        "predicted": 1.0,
        "observed": 0.9468693074772295,
        "relative_error": 0.05313069252277047
      },
      {
        "D": 0.5,
        "r": 1.0,
        "predicted": 1.4142135623730951,
        "observed": 1.268869715478862,
        "relative_error": 0.1027736197426516
      }
    ],
    "stability_boundary": [
      {
        "r": -0.5,
        "predicted": -0.5,
        "observed": -0.5063520554424232,
        "abs_error": 0.006352055442423232
      },
      {
        "r": 0.0,
        "predicted": 0.0,
        "observed": -1.083053609166525e-14,
        "abs_error": 1.083053609166525e-14
      },
      {
        "r": 0.5,
        "predicted": 0.5,
        "observed": 0.49384613004092737,
        "abs_error": 0.006153869959072633
      }
    ]
  },
  "protocol_note": "8 paired seeds; baseline sweep and idea sweep use identical lr/epoch union; n_train=400."
}