{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003,
      "epochs": 12
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "epochs": 12
        },
        "mean": 0.3423246815800667
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12
        },
        "mean": 0.32762672007083893
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 12
        },
        "mean": 0.5004829466342926
      }
    ],
    "full": {
      "mean": 0.32375194132328033,
      "std": 0.046624634658664434,
      "per_seed": [
        0.34710654616355896,
        0.2919960618019104,
        0.30691948533058167,
        0.3644847869873047,
        0.31837883591651917,
        0.24451658129692078,
        0.4092934727668762,
        0.3073197603225708
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.3292590510100126,
    "std": 0.057546800666266544,
    "per_seed": [
      0.34751513600349426,
      0.24287833273410797,
      0.32763731479644775,
      0.347289502620697,
      0.3484017848968506,
      0.23375016450881958,
      0.41173285245895386,
      0.37486732006073
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.005507109686732292,
    "idea_wins": 3,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.00040858983993530273,
      -0.04911772906780243,
      0.02071782946586609,
      -0.017195284366607666,
      0.03002294898033142,
      -0.010766416788101196,
      0.0024393796920776367,
      0.06754755973815918
    ],
    "p_value": 0.63405,
    "mde": 0.029104389124102455,
    "mde_rel_pct": 8.989718796787217,
    "verdict": "no significant win",
    "system_worked": false
  },
  "mechanism_signature": {
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "sigma": 0.35
        },
        "mean": 0.33411455154418945,
        "per_seed": [
          0.3964906334877014,
          0.2513992488384247,
          0.33635154366493225,
          0.35221678018569946
        ]
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "sigma": 0.7
        },
        "mean": 0.31633007153868675,
        "per_seed": [
          0.34751513600349426,
          0.24287833273410797,
          0.32763731479644775,
          0.347289502620697
        ]
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 12,
          "sigma": 1.4
        },
        "mean": 0.3244466111063957,
        "per_seed": [
          0.3361342251300812,
          0.26523905992507935,
          0.3481976091861725,
          0.3482155501842499
        ]
      }
    ],
    "best_idea_cfg": {
      "lr": 0.003,
      "epochs": 12,
      "sigma": 0.7
    },
    "mechanism_signature": {
      "prediction": "Laplacian rows are normalized, nonnegative, and larger sigma gives less selective attention",
      "trained_model_observed": {
        "row_sum_error": 2.384185791015625e-07,
        "min_attention": 1.5814957521342876e-07,
        "mean_entropy_first_two_seeds": 2.5159993171691895,
        "learned_sigma_first_two_seeds": [
          0.7006007432937622,
          0.7081389427185059
        ]
      },
      "predicted": {
        "row_sum_error": 0.0,
        "min_attention": 0.0
      },
      "confirmed": true
    },
    "operation_accounting": {
      "dot_qk_channel_multiplications_per_pair": 32,
      "lap_qk_channel_multiplications_per_pair": 0,
      "lap_abs_subtracts_per_pair": 32
    }
  },
  "runtime_note": "400 train/200 test, 12 epochs, batch 128, 8 paired seeds"
}