{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003,
      "delta": 0.0001
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "delta": 0.0001
        },
        "mean": 1.0469075739383698
      },
      {
        "cfg": {
          "lr": 0.003,
          "delta": 0.0001
        },
        "mean": 1.004875659942627
      },
      {
        "cfg": {
          "lr": 0.01,
          "delta": 0.0001
        },
        "mean": 1.015213631093502
      }
    ],
    "full": {
      "mean": 1.004875659942627,
      "std": 0.08302304230055646,
      "per_seed": [
        1.0032966136932373,
        0.8694341778755188,
        1.1456023454666138,
        1.081549882888794,
        0.9330782294273376,
        0.9555575847625732,
        1.0619580745697021,
        0.9885283708572388
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 1.0048756524920464,
    "std": 0.0830230295635864,
    "per_seed": [
      1.0032966136932373,
      0.8694342374801636,
      1.1456023454666138,
      1.0815497636795044,
      0.9330782294273376,
      0.9555575847625732,
      1.0619581937789917,
      0.9885282516479492
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -7.450580596923828e-09,
    "idea_wins": 2,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.0,
      5.960464477539063e-08,
      0.0,
      -1.1920928955078125e-07,
      0.0,
      0.0,
      1.1920928955078125e-07,
      -1.1920928955078125e-07
    ],
    "p_value": 1.0,
    "mde": 6.759130857174038e-08,
    "mde_rel_pct": 6.726335532457765e-06,
    "verdict": "no measurable effect",
    "system_worked": false
  },
  "mechanism_signature": {
    "idea_config": {
      "lr": 0.003,
      "delta": 0.0001
    },
    "idea_sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "delta": 0.0001
        },
        "result": {
          "mean": 1.046907588839531,
          "std": 0.07630641547099135,
          "per_seed": [
            1.033826470375061,
            0.9115373492240906,
            1.1899056434631348,
            1.0792663097381592,
            0.9867245554924011,
            1.0289349555969238,
            1.0983328819274902,
            1.0467325448989868
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.003,
          "delta": 0.0001
        },
        "result": {
          "mean": 1.0048756524920464,
          "std": 0.0830230295635864,
          "per_seed": [
            1.0032966136932373,
            0.8694342374801636,
            1.1456023454666138,
            1.0815497636795044,
            0.9330782294273376,
            0.9555575847625732,
            1.0619581937789917,
            0.9885282516479492
          ],
          "n": 8
        }
      },
      {
        "cfg": {
          "lr": 0.01,
          "delta": 0.0001
        },
        "result": {
          "mean": 1.0152136087417603,
          "std": 0.07053051427342504,
          "per_seed": [
            1.039136290550232,
            0.8907526731491089,
            1.1310786008834839,
            1.0511094331741333,
            1.0021077394485474,
            0.9427624940872192,
            1.071175456047058,
            0.9935861825942993
          ],
          "n": 8
        }
      }
    ],
    "mechanism_signature": {
      "prediction": "quotient attention suppresses row/column nuisance sensitivity while retaining interaction sensitivity",
      "baseline": {
        "kind": "baseline",
        "rowcol_plan_rms": 4.0958703095839155e-10,
        "interaction_plan_rms": 1.726159410964101e-07
      },
      "idea": {
        "kind": "idea",
        "rowcol_plan_rms": 2.545942379583721e-06,
        "interaction_plan_rms": 5.0314388317929115e-06
      },
      "predicted_ratio_bound": 1.0,
      "observed_ratio": 6200.737450574088,
      "confirmed": false
    }
  }
}