{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "eps": 0.7,
      "iters": 12
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "eps": 0.7,
          "iters": 12
        },
        "mean": 0.9074711948633194
      },
      {
        "cfg": {
          "lr": 0.003,
          "eps": 0.7,
          "iters": 12
        },
        "mean": 0.915537878870964
      },
      {
        "cfg": {
          "lr": 0.006,
          "eps": 0.7,
          "iters": 12
        },
        "mean": 0.8664272725582123
      }
    ],
    "full": {
      "mean": 0.9269421473145485,
      "std": 0.08130362337327321,
      "per_seed": [
        0.9268826246261597,
        0.8607907891273499,
        0.8572450280189514,
        0.8207906484603882,
        1.0688729286193848,
        0.9266430139541626,
        1.0371272563934326,
        0.9171848893165588
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.9356912449002266,
    "std": 0.05696883264914271,
    "per_seed": [
      0.9681993126869202,
      0.8495118021965027,
      0.900809645652771,
      0.961909830570221,
      0.9716687798500061,
      0.9182450175285339,
      1.038270115852356,
      0.876915454864502
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.0087490975856781,
    "idea_wins": 4,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0413166880607605,
      -0.011278986930847168,
      0.04356461763381958,
      0.14111918210983276,
      -0.09720414876937866,
      -0.008397996425628662,
      0.0011428594589233398,
      -0.040269434452056885
    ],
    "p_value": 0.75565,
    "mde": 0.05842531038665775,
    "mde_rel_pct": 6.303015841487215,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "lr": 0.006,
      "eps": 0.5,
      "iters": 12
    },
    {
      "lr": 0.006,
      "eps": 0.7,
      "iters": 12
    },
    {
      "lr": 0.006,
      "eps": 1.0,
      "iters": 12
    }
  ],
  "track_justification": "Sequence forecast contains multi-token correlations and directly exercises attention.",
  "mechanism_signature": {
    "predicted_max_marginal_error": 0.0001,
    "observed_mean_row_marginal_error": 0.007857249001972377,
    "observed_mean_column_marginal_error": 1.1294105761727735e-08,
    "observed_min_attention_mean": 1.0011145091900235e-14,
    "confirmed": false
  }
}