{
  "bench_version": 1,
  "track": "token_expert_sequence",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.01,
      "epochs": 25
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001,
          "epochs": 25
        },
        "mean": 0.0012499999720603228
      },
      {
        "cfg": {
          "lr": 0.003,
          "epochs": 25
        },
        "mean": 0.0012499999720603228
      },
      {
        "cfg": {
          "lr": 0.01,
          "epochs": 25
        },
        "mean": 0.0006249999860301614
      }
    ],
    "full": {
      "mean": 0.0015624999650754035,
      "std": 0.0017399263244939971,
      "per_seed": [
        0.0,
        0.0024999999441206455,
        0.0,
        0.0,
        0.0024999999441206455,
        0.0024999999441206455,
        0.0,
        0.004999999888241291
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.4946874864399433,
    "std": 0.02705426452774727,
    "per_seed": [
      0.5399999618530273,
      0.5024999976158142,
      0.48499998450279236,
      0.5049999952316284,
      0.4449999928474426,
      0.5199999809265137,
      0.47999998927116394,
      0.47999998927116394
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 0.4931249864748679,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      0.5399999618530273,
      0.49999999767169356,
      0.48499998450279236,
      0.5049999952316284,
      0.442499992903322,
      0.517499980982393,
      0.47999998927116394,
      0.47499998938292265
    ],
    "p_value": 0.0081,
    "mde": 0.024702187634040935,
    "mde_rel_pct": 1580.9400439153835,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "predicted_effect": "occupation mismatch decreases as reset_rate increases",
    "mismatch_at_r": NaN,
    "mismatch_at_r_0.5": NaN,
    "observed_cycle_proxy": NaN,
    "confirmed": false
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 25,
        "r": 0.5
      },
      "result": {
        "mean": 0.4946874864399433,
        "std": 0.02705426452774727,
        "per_seed": [
          0.5399999618530273,
          0.5024999976158142,
          0.48499998450279236,
          0.5049999952316284,
          0.4449999928474426,
          0.5199999809265137,
          0.47999998927116394,
          0.47999998927116394
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 25,
        "r": 2.0
      },
      "result": {
        "mean": 0.4946874864399433,
        "std": 0.02705426452774727,
        "per_seed": [
          0.5399999618530273,
          0.5024999976158142,
          0.48499998450279236,
          0.5049999952316284,
          0.4449999928474426,
          0.5199999809265137,
          0.47999998927116394,
          0.47999998927116394
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.01,
        "epochs": 25,
        "r": 8.0
      },
      "result": {
        "mean": 0.4946874864399433,
        "std": 0.02705426452774727,
        "per_seed": [
          0.5399999618530273,
          0.5024999976158142,
          0.48499998450279236,
          0.5049999952316284,
          0.4449999928474426,
          0.5199999809265137,
          0.47999998927116394,
          0.47999998927116394
        ],
        "n": 8
      }
    }
  ],
  "custom_track": {
    "name": "token_expert_sequence",
    "file": "/home/maxwelhelp/all/math2nn/bench/custom_tracks/token_expert_sequence.py",
    "domain": "moe-routing"
  }
}