{
  "bench_report": {
    "bench_version": 1,
    "track": "binary_symmetric_power_regression",
    "model": "local_mlp_head",
    "metric_direction": "lower is better",
    "n_seeds": 8,
    "baseline": {
      "best_cfg": {
        "lr": 0.01
      },
      "sweep": [
        {
          "cfg": {
            "lr": 0.001
          },
          "mean": 0.1037276852875948
        },
        {
          "cfg": {
            "lr": 0.003
          },
          "mean": 0.007304377853870392
        },
        {
          "cfg": {
            "lr": 0.01
          },
          "mean": 0.004617542843334377
        }
      ],
      "full": {
        "mean": 0.004571487399516627,
        "std": 0.0009398261599528283,
        "per_seed": [
          0.004156868439167738,
          0.006239068228751421,
          0.0032845954410731792,
          0.004789639264345169,
          0.004069721791893244,
          0.00436969893053174,
          0.0038355558644980192,
          0.005826751235872507
        ],
        "n": 8
      }
    },
    "idea": {
      "best_config": {
        "lr": 0.01
      },
      "per_seed": [
        0.0036381708923727274,
        0.0029435837641358376,
        0.004084695130586624,
        0.009996835142374039,
        0.004572708159685135,
        0.02756613865494728,
        0.006751858629286289,
        0.004224956501275301
      ],
      "mean": 0.007972368359332904,
      "std": 0.007699778199581965
    },
    "comparison": {
      "delta_mean": 0.003400880959816277,
      "idea_wins": 3,
      "n_pairs": 8,
      "per_seed_diffs": [
        -0.0005186975467950106,
        -0.0032954844646155834,
        0.0008000996895134449,
        0.00520719587802887,
        0.0005029863677918911,
        0.02319643972441554,
        0.00291630276478827,
        -0.0016017947345972061
      ],
      "p_value": 0.3091,
      "mde": 0.007036725002667524,
      "mde_rel_pct": 153.92637860954318,
      "verdict": "no significant win",
      "system_worked": false
    },
    "protocol": {
      "seeds": [
        0,
        1,
        2,
        3,
        4,
        5,
        6,
        7
      ],
      "baseline_grid": [
        {
          "lr": 0.001
        },
        {
          "lr": 0.003
        },
        {
          "lr": 0.01
        }
      ],
      "idea_grid": [
        {
          "lr": 0.001
        },
        {
          "lr": 0.003
        },
        {
          "lr": 0.01
        }
      ],
      "selection": "baseline best on seeds 0-3; idea evaluated at same selected lr"
    },
    "mechanism_signature": {
      "predicted_equivariance_error": 0.0,
      "observed_trained_feature_equivariance_error": 2.1827872842550278e-11,
      "predicted_composition_error": 0.0,
      "observed_representation_composition_error": 1.1368683772161603e-13,
      "confirmed": true,
      "note": "Signature is retested numerically at NN-scale on the trained idea model's feature map; task metric remains independent."
    }
  },
  "all_sweeps": {
    "baseline": {
      "0.001": [
        0.1355224996805191,
        0.11009717732667923,
        0.055855073034763336,
        0.11343599110841751,
        0.07716862857341766,
        0.07487080246210098,
        0.10096120834350586,
        0.059963226318359375
      ],
      "0.003": [
        0.00825435295701027,
        0.008851638063788414,
        0.004908436443656683,
        0.007203083951026201,
        0.003927994519472122,
        0.009901680983603,
        0.005368529818952084,
        0.005688884295523167
      ],
      "0.01": [
        0.004156868439167738,
        0.006239068228751421,
        0.0032845954410731792,
        0.004789639264345169,
        0.004069721791893244,
        0.00436969893053174,
        0.0038355558644980192,
        0.005826751235872507
      ]
    },
    "idea": {
      "0.001": [
        0.0154461320489645,
        0.03856436163187027,
        0.03455395624041557,
        0.015390957705676556,
        0.039948124438524246,
        0.09389373660087585,
        0.025615643709897995,
        0.02203393168747425
      ],
      "0.003": [
        0.00696675106883049,
        0.009506145492196083,
        0.015012294054031372,
        0.007092596031725407,
        0.009301144629716873,
        0.02316836081445217,
        0.015946412459015846,
        0.011056053452193737
      ],
      "0.01": [
        0.0036381708923727274,
        0.0029435837641358376,
        0.004084695130586624,
        0.009996835142374039,
        0.004572708159685135,
        0.02756613865494728,
        0.006751858629286289,
        0.004224956501275301
      ]
    }
  },
  "custom_track": {
    "name": "binary_symmetric_power_regression",
    "file": "bench_symmetric_power.py",
    "domain": "planar_equivariance"
  },
  "math_check": {
    "max_polynomial_abs_error": 4.263256414560601e-14,
    "max_composition_abs_error": 1.1368683772161603e-13,
    "max_rotation_invariant_abs_error": 2.1827872842550278e-11
  }
}