{
  "bench_version": 1,
  "track": "correlated_multitask_regression",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "epochs": 18
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 18
        },
        "mean": 0.33924729377031326
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 18
        },
        "mean": 0.2891158163547516
      },
      {
        "cfg": {
          "lr": 0.006,
          "epochs": 18
        },
        "mean": 0.2687482498586178
      }
    ],
    "full": {
      "mean": 0.26368178986012936,
      "std": 0.012707367791430902,
      "per_seed": [
        0.28817808628082275,
        0.2641679346561432,
        0.27657756209373474,
        0.24606941640377045,
        0.26166772842407227,
        0.26569777727127075,
        0.2544151544570923,
        0.2526806592941284
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.2741883806884289,
    "std": 0.00900021034383701,
    "per_seed": [
      0.28664544224739075,
      0.2656421661376953,
      0.2874869704246521,
      0.2784552276134491,
      0.273226797580719,
      0.2612801492214203,
      0.2741454243659973,
      0.2666248679161072
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.010506590828299522,
    "idea_wins": 2,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.0015326440334320068,
      0.001474231481552124,
      0.010909408330917358,
      0.03238581120967865,
      0.011559069156646729,
      -0.004417628049850464,
      0.01973026990890503,
      0.01394420862197876
    ],
    "p_value": 0.0552,
    "mde": 0.010123642152049727,
    "mde_rel_pct": 3.839340652769324,
    "verdict": "no significant win",
    "system_worked": false
  },
  "mechanism_signature": {
    "signature": {
      "prediction": "copula dependence on uniform/standardized scale captures positive cross-output residual dependence",
      "predicted_mean_offdiag_corr": 0.11426236107945442,
      "observed_mean_offdiag_residual_corr": 0.17040012543923766,
      "abs_error": 0.05613776435978324,
      "confirmed": true,
      "per_seed": [
        {
          "seed": 0,
          "observed_residual_corr_mean": 0.17705640620883495,
          "predicted_copula_corr_mean": 0.11108794808387756,
          "baseline_mse": 0.28817808628082275,
          "idea_mse": 0.28664544224739075
        },
        {
          "seed": 1,
          "observed_residual_corr_mean": 0.15009457541756535,
          "predicted_copula_corr_mean": 0.13055425882339478,
          "baseline_mse": 0.2641679346561432,
          "idea_mse": 0.2656421661376953
        },
        {
          "seed": 2,
          "observed_residual_corr_mean": 0.17330186510250142,
          "predicted_copula_corr_mean": 0.10499031096696854,
          "baseline_mse": 0.27657756209373474,
          "idea_mse": 0.2874869704246521
        },
        {
          "seed": 3,
          "observed_residual_corr_mean": 0.14522062344436665,
          "predicted_copula_corr_mean": 0.09687795490026474,
          "baseline_mse": 0.24606941640377045,
          "idea_mse": 0.2784552276134491
        },
        {
          "seed": 4,
          "observed_residual_corr_mean": 0.15387426022763864,
          "predicted_copula_corr_mean": 0.1175244003534317,
          "baseline_mse": 0.26166772842407227,
          "idea_mse": 0.273226797580719
        },
        {
          "seed": 5,
          "observed_residual_corr_mean": 0.1745235061227068,
          "predicted_copula_corr_mean": 0.11502358317375183,
          "baseline_mse": 0.26569777727127075,
          "idea_mse": 0.2612801492214203
        },
        {
          "seed": 6,
          "observed_residual_corr_mean": 0.19859785188941909,
          "predicted_copula_corr_mean": 0.12316668778657913,
          "baseline_mse": 0.2544151544570923,
          "idea_mse": 0.2741454243659973
        },
        {
          "seed": 7,
          "observed_residual_corr_mean": 0.19053191510086853,
          "predicted_copula_corr_mean": 0.1148737445473671,
          "baseline_mse": 0.2526806592941284,
          "idea_mse": 0.2666248679161072
        }
      ]
    },
    "idea_sweep": [
      {
        "lr": 0.001,
        "result": {
          "mean": 0.35608335956931114,
          "std": 0.01715514284052541,
          "per_seed": [
            0.34133413434028625,
            0.32555291056632996,
            0.3722515404224396,
            0.3699086010456085,
            0.3756076693534851,
            0.3562084138393402,
            0.3673454523086548,
            0.3404581546783447
          ],
          "n": 8
        }
      },
      {
        "lr": 0.003,
        "result": {
          "mean": 0.31745627894997597,
          "std": 0.012492207053464112,
          "per_seed": [
            0.30626440048217773,
            0.2969795763492584,
            0.3294920027256012,
            0.3298030495643616,
            0.3205186724662781,
            0.31924760341644287,
            0.3326553404331207,
            0.30468958616256714
          ],
          "n": 8
        }
      },
      {
        "lr": 0.006,
        "result": {
          "mean": 0.2741883806884289,
          "std": 0.00900021034383701,
          "per_seed": [
            0.28664544224739075,
            0.2656421661376953,
            0.2874869704246521,
            0.2784552276134491,
            0.273226797580719,
            0.2612801492214203,
            0.2741454243659973,
            0.2666248679161072
          ],
          "n": 8
        }
      }
    ],
    "custom_track": {
      "name": "correlated_multitask_regression",
      "file": "/home/maxwelhelp/all/math2nn/bench/custom_tracks/correlated_multitask_regression.py",
      "domain": "multi_task_learning"
    }
  }
}