{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.0015,
      "weight_decay": 0.0
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0
        },
        "mean": 0.13084225729107857
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 0.13562202639877796
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "mean": 0.1526990309357643
      }
    ],
    "full": {
      "mean": 0.1321341758593917,
      "std": 0.012441957039020079,
      "per_seed": [
        0.15123596787452698,
        0.11964408308267593,
        0.12323945015668869,
        0.12924952805042267,
        0.1238316223025322,
        0.11987392604351044,
        0.13868176937103271,
        0.1513170599937439
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.13770121987909079,
    "std": 0.012267757502007736,
    "per_seed": [
      0.14959165453910828,
      0.1260286271572113,
      0.1206536665558815,
      0.13636907935142517,
      0.1417829692363739,
      0.12556812167167664,
      0.142854243516922,
      0.1587613970041275
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.005567044019699097,
    "idea_wins": 2,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0016443133354187012,
      0.00638454407453537,
      -0.00258578360080719,
      0.0071195513010025024,
      0.017951346933841705,
      0.005694195628166199,
      0.004172474145889282,
      0.007444337010383606
    ],
    "p_value": 0.0386,
    "mde": 0.00529214319698178,
    "mde_rel_pct": 4.00512824374318,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.0015,
        "weight_decay": 0.0
      },
      "mean": 0.1338496170938015
    },
    {
      "cfg": {
        "lr": 0.003,
        "weight_decay": 0.0
      },
      "mean": 0.13636435382068157
    },
    {
      "cfg": {
        "lr": 0.006,
        "weight_decay": 0.0
      },
      "mean": 0.13316075690090656
    }
  ],
  "math_check": {
    "homogeneity_max_relative_error": 3.397532652615887e-05,
    "near_origin_amplification": 40.80571546736738,
    "predicted_amplification": 40.80571546736738,
    "admissible_d3": true,
    "relative_amplification_error": 0.0
  },
  "idea_best_cfg": {
    "lr": 0.006,
    "weight_decay": 0.0
  },
  "budget": {
    "epochs": 18,
    "n_train": 2000,
    "n_test": 500,
    "seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ]
  },
  "mechanism_signature": {
    "predicted_near_vs_far_kernel_ratio": 2571602743.0040903,
    "observed_attention_odds_ratio_after_bias": 455527.4706971457,
    "baseline_endpoint_recent_attention": 0.04563657566905022,
    "idea_endpoint_recent_attention": 0.9985866546630859,
    "confirmed": false
  }
}