{
  "bench_version": 1,
  "track": "tabular",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.006,
      "weight_decay": 0.0001
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0
        },
        "mean": 6.582355260848999
      },
      {
        "cfg": {
          "lr": 0.0015,
          "weight_decay": 0.0001
        },
        "mean": 6.403406500816345
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0
        },
        "mean": 6.050842046737671
      },
      {
        "cfg": {
          "lr": 0.003,
          "weight_decay": 0.0001
        },
        "mean": 5.60420548915863
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0
        },
        "mean": 5.5363428592681885
      },
      {
        "cfg": {
          "lr": 0.006,
          "weight_decay": 0.0001
        },
        "mean": 4.698180794715881
      }
    ],
    "full": {
      "mean": 4.819164454936981,
      "std": 0.17166144964543392,
      "per_seed": [
        4.596839904785156,
        4.635165214538574,
        4.646710395812988,
        4.914007663726807,
        5.076730251312256,
        4.984879016876221,
        4.754410743713379,
        4.944572448730469
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 6.840818226337433,
    "std": 0.17257722313102455,
    "per_seed": [
      6.538304328918457,
      6.585258960723877,
      6.972299098968506,
      6.974996089935303,
      6.823678970336914,
      7.017618656158447,
      6.853421211242676,
      6.960968494415283
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": 2.0216537714004517,
    "idea_wins": 0,
    "n_pairs": 8,
    "per_seed_diffs": [
      1.9414644241333008,
      1.9500937461853027,
      2.3255887031555176,
      2.060988426208496,
      1.7469487190246582,
      2.0327396392822266,
      2.099010467529297,
      2.0163960456848145
    ],
    "p_value": 0.0081,
    "mde": 0.13669161157539178,
    "mde_rel_pct": 2.8364172431459234,
    "verdict": "idea worse (significant)",
    "system_worked": false
  },
  "mechanism_signature": {
    "prediction": "nonzero replica circulation when k1!=k2",
    "k1": 0.2,
    "k2": 0.05,
    "observed_epoch_area_seed0": -1.9684885011277033e-08,
    "observed_mean_replica_separation": 0.07705571800470352,
    "confirmed": true
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.0015,
        "weight_decay": 0.0001
      },
      "result": {
        "mean": 6.842114150524139,
        "std": 0.19106420610526897,
        "per_seed": [
          6.48126745223999,
          6.709563732147217,
          7.120368957519531,
          6.81691312789917,
          6.813747406005859,
          7.096852779388428,
          6.863407611846924,
          6.834792137145996
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003,
        "weight_decay": 0.0001
      },
      "result": {
        "mean": 6.840818226337433,
        "std": 0.17257722313102455,
        "per_seed": [
          6.538304328918457,
          6.585258960723877,
          6.972299098968506,
          6.974996089935303,
          6.823678970336914,
          7.017618656158447,
          6.853421211242676,
          6.960968494415283
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.006,
        "weight_decay": 0.0001
      },
      "result": {
        "mean": 6.841454744338989,
        "std": 0.2586476832475316,
        "per_seed": [
          7.215710163116455,
          6.548867702484131,
          7.098788261413574,
          7.125370502471924,
          6.484438896179199,
          6.837231636047363,
          6.688592910766602,
          6.732637882232666
        ],
        "n": 8
      }
    }
  ],
  "protocol_notes": {
    "epochs": 15,
    "batch": 128,
    "paired_seeds": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7
    ],
    "track_rationale": "tabular is the prescribed structural track for optimizer modifications",
    "equal_budget_note": "same epochs and minibatch budget per replica; the idea uses two replicas and thus approximately 2x parameter-update compute"
  }
}