{
  "bench_version": 1,
  "track": "vision",
  "model": "cnn_small",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.003
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.8537499755620956
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.846249982714653
      },
      {
        "cfg": {
          "lr": 0.01
        },
        "mean": 0.8699999898672104
      }
    ],
    "full": {
      "mean": 0.8537499830126762,
      "std": 0.032475961531880884,
      "per_seed": [
        0.8899999856948853,
        0.8399999737739563,
        0.8700000047683716,
        0.7849999666213989,
        0.8700000047683716,
        0.8499999642372131,
        0.8899999856948853,
        0.8349999785423279
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.8706249967217445,
    "std": 0.046464878782190286,
    "per_seed": [
      0.7599999904632568,
      0.8550000190734863,
      0.8849999904632568,
      0.9100000262260437,
      0.8549999594688416,
      0.9100000262260437,
      0.8999999761581421,
      0.8899999856948853
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.0168750137090683,
    "idea_wins": 2,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.12999999523162842,
      0.01500004529953003,
      0.014999985694885254,
      0.12500005960464478,
      -0.01500004529953003,
      0.060000061988830566,
      0.009999990463256836,
      0.05500000715255737
    ],
    "p_value": 0.50765,
    "mde": 0.061319939059687474,
    "mde_rel_pct": 7.182423458833265,
    "verdict": "no significant win",
    "system_worked": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "mean": 0.8587500005960464
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "mean": 0.8525000065565109
    },
    {
      "cfg": {
        "lr": 0.01
      },
      "mean": 0.885000005364418
    }
  ],
  "protocol_note": "shared lr grid; 8 paired seeds; 400/200 CIFAR subset; 4 epochs",
  "mechanism_signature": {
    "prediction": "trained anchored layer should reduce channel covariance while preserving designated-channel fidelity",
    "baseline_offdiag_cov": null,
    "idea_offdiag_cov_observed": 1.9903746843338013,
    "idea_max_unit_variance_error_observed": 0.9999727606773376,
    "idea_min_fidelity_observed": -0.0010492571163922548,
    "rho_min": 0.8,
    "confirmed": false
  }
}