{
  "bench_version": 1,
  "track": "bench_custom_masked_candidate_low_rank",
  "model": "mlp_tiny",
  "metric_direction": "lower is better",
  "n_seeds": 8,
  "baseline": {
    "best_cfg": {
      "lr": 0.001
    },
    "sweep": [
      {
        "cfg": {
          "lr": 0.001
        },
        "mean": 0.4420415982604027
      },
      {
        "cfg": {
          "lr": 0.003
        },
        "mean": 0.44252580031752586
      },
      {
        "cfg": {
          "lr": 0.006
        },
        "mean": 0.4765854626893997
      }
    ],
    "full": {
      "mean": 0.5450004562735558,
      "std": 0.2628610195034815,
      "per_seed": [
        0.7630048990249634,
        0.5563264489173889,
        0.2823181748390198,
        0.16651687026023865,
        1.0170692205429077,
        0.555262565612793,
        0.32614681124687195,
        0.6933586597442627
      ],
      "n": 8
    }
  },
  "idea": {
    "mean": 0.048654421931132674,
    "std": 0.02168288877569749,
    "per_seed": [
      0.06334998458623886,
      0.05048277601599693,
      0.03009387105703354,
      0.021304024383425713,
      0.09369651228189468,
      0.040802765637636185,
      0.031937580555677414,
      0.057567860931158066
    ],
    "n": 8
  },
  "comparison": {
    "delta_mean": -0.4963460343424231,
    "idea_wins": 8,
    "n_pairs": 8,
    "per_seed_diffs": [
      -0.6996549144387245,
      -0.505843672901392,
      -0.25222430378198624,
      -0.14521284587681293,
      -0.923372708261013,
      -0.5144597999751568,
      -0.29420923069119453,
      -0.6357907988131046
    ],
    "p_value": 0.0081,
    "mde": 0.21604011474214413,
    "mde_rel_pct": 39.64035483920873,
    "verdict": "idea better (significant)",
    "system_worked": true
  },
  "custom_track": {
    "name": "masked_candidate_low_rank",
    "file": "custom_candidate_track.py",
    "domain": "retrieval"
  },
  "idea_sweep": [
    {
      "cfg": {
        "lr": 0.001
      },
      "result": {
        "mean": 0.20586615707725286,
        "std": 0.14904708404374148,
        "per_seed": [
          0.2456769198179245,
          0.2300177961587906,
          0.06836631894111633,
          0.07623686641454697,
          0.5616698265075684,
          0.1149023026227951,
          0.13585276901721954,
          0.21420645713806152
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.003
      },
      "result": {
        "mean": 0.05824449914507568,
        "std": 0.02563097931151917,
        "per_seed": [
          0.07524535804986954,
          0.06290170550346375,
          0.03489440307021141,
          0.025365130975842476,
          0.11273353546857834,
          0.04778952896595001,
          0.04362767934799194,
          0.06339865177869797
        ],
        "n": 8
      }
    },
    {
      "cfg": {
        "lr": 0.006
      },
      "result": {
        "mean": 0.048654421931132674,
        "std": 0.02168288877569749,
        "per_seed": [
          0.06334998458623886,
          0.05048277601599693,
          0.03009387105703354,
          0.021304024383425713,
          0.09369651228189468,
          0.040802765637636185,
          0.031937580555677414,
          0.057567860931158066
        ],
        "n": 8
      }
    }
  ],
  "mechanism_signature": {
    "predicted_flop_ratio": 0.06976744186046512,
    "observed_first_layer_param_ratio": 0.06976744186046512,
    "observed_test_prediction_std": 2.4757130444049835,
    "target_std": 2.446375161409378,
    "reconstruction_relative_error": 0.1594924950357648,
    "confirmed": true
  },
  "track_rationale": "Custom track is structurally required: masked ambient candidate vectors generated from a shared low-rank action-feature subspace."
}