{
  "bench_version": 1,
  "track": "sequence",
  "model": "transformer_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.001,
      "epochs": 10
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 10
        },
        "mean": 0.482548501342535
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 10
        },
        "mean": 0.6393650658428669
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 10
        },
        "mean": 1.4253769740462303
      }
    ],
    "full": {
      "mean": 0.482548501342535,
      "std": 0.03354559876849172,
      "per_seed": [
        0.4842072129249573,
        0.42341384291648865,
        0.4566255807876587,
        0.5167749524116516,
        0.49487417936325073,
        0.4824545681476593,
        0.5386028289794922,
        0.4634348452091217
      ],
      "n": 8
    }
  },
  "idea": {
    "best_cfg": {
      "lr": 0.001,
      "epochs": 10
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 10
        },
        "mean": 0.4744987264275551
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 10
        },
        "mean": 0.5909863151609898
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 10
        },
        "mean": 1.119819551706314
      }
    ],
    "mean": 0.4744987264275551,
    "std": 0.052674658740946755,
    "per_seed": [
      0.49082696437835693,
      0.3496098220348358,
      0.49417421221733093,
      0.4901917278766632,
      0.519122302532196,
      0.44667643308639526,
      0.5286210179328918,
      0.47676733136177063
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.008049774914979935,
    "idea_wins": 4,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.006619751453399658,
      -0.07380402088165283,
      0.03754863142967224,
      -0.026583224534988403,
      0.024248123168945312,
      -0.03577813506126404,
      -0.009981811046600342,
      0.013332486152648926
    ],
    "p_value": 0.57185,
    "mde": 0.030369881877730317,
    "mde_rel_pct": 6.293643394028983,
    "verdict": "no significant win",
    "system_worked": false
  },
  "track_match": "sequence has multi-token correlations and transformer attention; therefore it is structurally matched",
  "attention_audit": {
    "masked_edges": 94,
    "dense_edges": 1024,
    "per_seed": [
      {
        "seed": 0,
        "test_mse": 0.49082696437835693,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 1,
        "test_mse": 0.3496098220348358,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 2,
        "test_mse": 0.49417421221733093,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 3,
        "test_mse": 0.4901917278766632,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 4,
        "test_mse": 0.519122302532196,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 5,
        "test_mse": 0.44667643308639526,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 6,
        "test_mse": 0.5286210179328918,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      },
      {
        "seed": 7,
        "test_mse": 0.47676733136177063,
        "edges": 94,
        "n_tokens": 32,
        "max_shared_keys": 1
      }
    ]
  },
  "mechanism_signature": {
    "prediction": "hierarchical repaired attention has linear active-edge count and K2,2 maximum common-neighbor count <=1",
    "observed_edges": 94,
    "observed_dense_edges": 1024,
    "edge_reduction": 10.893617021276595,
    "observed_edge_scaling_exponent": 1.0,
    "observed_max_shared_keys": 1,
    "trained_model_test_mse_mean": 0.4744987264275551,
    "confirmed": true
  }
}