{
  "bench_version": 1,
  "track": "correlated_token_moe_regression",
  "model": "matched_custom",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.001,
      "epochs": 20
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 20
        },
        "mean": 0.05792584456503391
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 20
        },
        "mean": 0.0597206624224782
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 20
        },
        "mean": 0.06360050570219755
      }
    ],
    "full": {
      "mean": 0.05597660783678293,
      "std": 0.004513427280072455,
      "per_seed": [
        0.04968653619289398,
        0.060288313776254654,
        0.06273896247148514,
        0.05898956581950188,
        0.051729243248701096,
        0.05691293999552727,
        0.056976065039634705,
        0.05049123615026474
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.043164961505681276,
    "std": 0.004883880354277062,
    "per_seed": [
      0.03658263012766838,
      0.043850693851709366,
      0.04236328974366188,
      0.04947901517152786,
      0.041660089045763016,
      0.051025427877902985,
      0.04368860274553299,
      0.03666994348168373
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.012811646331101656,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.013103906065225601,
      -0.016437619924545288,
      -0.020375672727823257,
      -0.009510550647974014,
      -0.01006915420293808,
      -0.005887512117624283,
      -0.013287462294101715,
      -0.013821292668581009
    ],
    "p_value": 0.0081,
    "mde": 0.0037133339468910474,
    "mde_rel_pct": 6.633724497415811,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "mechanism_signature": {
    "quantity": "mean absolute prediction change under swapping two trained-task tokens",
    "prediction": "equivariant/invariant system has zero change while flattened baseline is nonzero",
    "baseline_per_seed": [
      0.02555830031633377,
      0.036283940076828,
      0.041776224970817566,
      0.06388069689273834,
      0.04568406194448471,
      0.04635582119226456,
      0.057599522173404694,
      0.04444808512926102
    ],
    "idea_per_seed": [
      1.4726538211107254e-08,
      1.4726538211107254e-08,
      9.284121915698051e-09,
      1.7113052308559418e-08,
      1.3271346688270569e-08,
      9.080395102500916e-09,
      1.2281816452741623e-08,
      1.0826624929904938e-08
    ],
    "baseline_mean": 0.04519833158701658,
    "idea_mean": 1.2663804227486253e-08,
    "confirmed": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001,
        "epochs": 20
      },
      "mean": 0.0434781601652503,
      "std": 0.004274304660454058,
      "per_seed": [
        0.038152437657117844,
        0.046353816986083984,
        0.04167266935110092,
        0.04806140437722206,
        0.04175148531794548,
        0.05084418132901192,
        0.042754773050546646,
        0.038234513252973557
      ]
    },
    {
      "cfg": {
        "lr": 0.003,
        "epochs": 20
      },
      "mean": 0.043164961505681276,
      "std": 0.004883880354277062,
      "per_seed": [
        0.03658263012766838,
        0.043850693851709366,
        0.04236328974366188,
        0.04947901517152786,
        0.041660089045763016,
        0.051025427877902985,
        0.04368860274553299,
        0.03666994348168373
      ]
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 20
      },
      "mean": 0.04354450246319175,
      "std": 0.004289397371544806,
      "per_seed": [
        0.03576800599694252,
        0.04776814952492714,
        0.04307476058602333,
        0.04668940603733063,
        0.04327880218625069,
        0.04976873844861984,
        0.0428813174366951,
        0.039126839488744736
      ]
    }
  ],
  "track_justification": "The registered correlated-token track contains exchangeable multi-token correlations; built-in tracks do not."
}