{
  "description": "Best FELM DCF results aggregated from multiple runs",
  "date_generated": "2026-01-16",
  "source_runs": {
    "felm_anneal": "results/felm_anneal/dataset/hyperparams.json",
    "felm_anneal_low_lambda_v2": "results/felm_anneal_low_lambda_v2/dataset/hyperparams.json",
    "felm_hone": "results/felm_hone/dataset/hyperparams.json"
  },
  "alpha_to_source": {
    "0.01": "felm_anneal",
    "0.02": "felm_anneal",
    "0.03": "felm_anneal",
    "0.04": "felm_anneal",
    "0.05": "felm_anneal",
    "0.06": "felm_anneal_low_lambda_v2",
    "0.07": "felm_anneal_low_lambda_v2",
    "0.08": "felm_anneal",
    "0.09": "felm_hone",
    "0.1": "felm_hone"
  },
  "alpha_to_features": {
    "0.01": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.02": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.03": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.04": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.05": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.06": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.07": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.08": [
      "frequency-score",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "nx_pagerank",
      "nx_reachability",
      "nx_out_degree"
    ],
    "0.09": [
      "frequency-score",
      "claim_index",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "has_unnecessary_dependencies",
      "problem_relevance",
      "uses_problem_data",
      "domain_science",
      "domain_reasoning",
      "nx_in_degree",
      "nx_out_degree",
      "nx_pagerank",
      "nx_betweenness",
      "nx_closeness",
      "nx_clustering",
      "nx_is_source",
      "nx_is_sink",
      "nx_reachability",
      "nx_depth_from_sources"
    ],
    "0.1": [
      "frequency-score",
      "claim_index",
      "coherent_to_ancestors",
      "inference_gap_size",
      "has_missing_dependencies",
      "has_unnecessary_dependencies",
      "problem_relevance",
      "uses_problem_data",
      "domain_science",
      "domain_reasoning",
      "nx_in_degree",
      "nx_out_degree",
      "nx_pagerank",
      "nx_betweenness",
      "nx_closeness",
      "nx_clustering",
      "nx_is_source",
      "nx_is_sink",
      "nx_reachability",
      "nx_depth_from_sources"
    ]
  },
  "results": {
    "0.01": {
      "alpha": 0.01,
      "target_coverage": 0.99,
      "source": "felm_anneal",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9915476190476191,
        "coverage_std": 0.015760064391671432,
        "avg_claims_retained": 0.7153174603174602,
        "avg_claims_retained_std": 0.19439424360066407,
        "precision": 0.2608035714285714,
        "precision_std": 0.09359210216558873
      },
      "baseline": {
        "coverage": 0.9918873239436619,
        "coverage_std": 0.006704935457718004,
        "avg_claims_retained": 0.4446760563380282,
        "avg_claims_retained_std": 0.17468878212716243,
        "precision": 0.13114084507042253,
        "precision_std": 0.046563578384589195
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.5,
        "lambda_": 1.2,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9915476190476191,
        "hard_coverage_std": 0.015760064391671432,
        "hard_avg_claims_retained_mean": 0.7153174603174602,
        "hard_avg_claims_retained_std": 0.19439424360066407,
        "hard_precision_mean": 0.2608035714285714,
        "hard_precision_std": 0.09359210216558873
      },
      "meets_coverage": true
    },
    "0.02": {
      "alpha": 0.02,
      "target_coverage": 0.98,
      "source": "felm_anneal",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9774603174603176,
        "coverage_std": 0.020982121749398376,
        "avg_claims_retained": 1.4280555555555556,
        "avg_claims_retained_std": 0.4606316849650614,
        "precision": 0.4873743386243386,
        "precision_std": 0.15545133977830713
      },
      "baseline": {
        "coverage": 0.9808450704225352,
        "coverage_std": 0.009643517052745727,
        "avg_claims_retained": 0.8967887323943661,
        "avg_claims_retained_std": 0.20397459885189215,
        "precision": 0.2575446009389671,
        "precision_std": 0.05132522708138355
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.0,
        "lambda_": 1.5,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9774603174603176,
        "hard_coverage_std": 0.020982121749398376,
        "hard_avg_claims_retained_mean": 1.4280555555555556,
        "hard_avg_claims_retained_std": 0.4606316849650614,
        "hard_precision_mean": 0.4873743386243386,
        "hard_precision_std": 0.15545133977830713
      },
      "meets_coverage": true
    },
    "0.03": {
      "alpha": 0.03,
      "target_coverage": 0.97,
      "source": "felm_anneal",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9732142857142858,
        "coverage_std": 0.024502964120548153,
        "avg_claims_retained": 1.4577380952380952,
        "avg_claims_retained_std": 0.3746905899990178,
        "precision": 0.5040410052910053,
        "precision_std": 0.09771194976933983
      },
      "baseline": {
        "coverage": 0.9710985915492957,
        "coverage_std": 0.011279008314819218,
        "avg_claims_retained": 1.180281690140845,
        "avg_claims_retained_std": 0.1856609439647076,
        "precision": 0.33245070422535217,
        "precision_std": 0.042476707374746105
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.25,
        "lambda_": 1.3,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9732142857142858,
        "hard_coverage_std": 0.024502964120548153,
        "hard_avg_claims_retained_mean": 1.4577380952380952,
        "hard_avg_claims_retained_std": 0.3746905899990178,
        "hard_precision_mean": 0.5040410052910053,
        "hard_precision_std": 0.09771194976933983
      },
      "meets_coverage": true
    },
    "0.04": {
      "alpha": 0.04,
      "target_coverage": 0.96,
      "source": "felm_anneal",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9647222222222223,
        "coverage_std": 0.034487277697772496,
        "avg_claims_retained": 1.6817460317460315,
        "avg_claims_retained_std": 0.355912253759144,
        "precision": 0.5549007936507937,
        "precision_std": 0.08089042865566827
      },
      "baseline": {
        "coverage": 0.9588732394366198,
        "coverage_std": 0.013079647060556534,
        "avg_claims_retained": 1.447492957746479,
        "avg_claims_retained_std": 0.17841908409564786,
        "precision": 0.40163380281690136,
        "precision_std": 0.03931126367158381
      },
      "hyperparams": {
        "temp": 0.5,
        "beta": 1,
        "gamma": 1.5,
        "lambda_": 1.45,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9647222222222223,
        "hard_coverage_std": 0.034487277697772496,
        "hard_avg_claims_retained_mean": 1.6817460317460315,
        "hard_avg_claims_retained_std": 0.355912253759144,
        "hard_precision_mean": 0.5549007936507937,
        "hard_precision_std": 0.08089042865566827
      },
      "meets_coverage": true
    },
    "0.05": {
      "alpha": 0.05,
      "target_coverage": 0.95,
      "source": "felm_anneal",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9534523809523809,
        "coverage_std": 0.03620150468970789,
        "avg_claims_retained": 1.8526984126984125,
        "avg_claims_retained_std": 0.39758074143016564,
        "precision": 0.5965702003023432,
        "precision_std": 0.09169126576443776
      },
      "baseline": {
        "coverage": 0.9509859154929577,
        "coverage_std": 0.014862992629039931,
        "avg_claims_retained": 1.6611830985915492,
        "avg_claims_retained_std": 0.1976028048345379,
        "precision": 0.45214741784037554,
        "precision_std": 0.038844472303419496
      },
      "hyperparams": {
        "temp": 0.5,
        "beta": 1,
        "gamma": 1.25,
        "lambda_": 1.45,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9534523809523809,
        "hard_coverage_std": 0.03620150468970789,
        "hard_avg_claims_retained_mean": 1.8526984126984125,
        "hard_avg_claims_retained_std": 0.39758074143016564,
        "hard_precision_mean": 0.5965702003023432,
        "hard_precision_std": 0.09169126576443776
      },
      "meets_coverage": true
    },
    "0.06": {
      "alpha": 0.06,
      "target_coverage": 0.94,
      "source": "felm_anneal_low_lambda_v2",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9491666666666667,
        "coverage_std": 0.039838167051758806,
        "avg_claims_retained": 1.9226587301587301,
        "avg_claims_retained_std": 0.4188284415837419,
        "precision": 0.6038770786092214,
        "precision_std": 0.08327533165270261
      },
      "baseline": {
        "coverage": 0.9394366197183099,
        "coverage_std": 0.016762338644295032,
        "avg_claims_retained": 1.9679999999999997,
        "avg_claims_retained_std": 0.23461035494430724,
        "precision": 0.5214323272971161,
        "precision_std": 0.04593742293818858
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.0,
        "lambda_": 1.0,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9491666666666667,
        "hard_coverage_std": 0.039838167051758806,
        "hard_avg_claims_retained_mean": 1.9226587301587301,
        "hard_avg_claims_retained_std": 0.4188284415837419,
        "hard_precision_mean": 0.6038770786092214,
        "hard_precision_std": 0.08327533165270261
      },
      "meets_coverage": true
    },
    "0.07": {
      "alpha": 0.07,
      "target_coverage": 0.9299999999999999,
      "source": "felm_anneal_low_lambda_v2",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9421031746031746,
        "coverage_std": 0.041659088502089124,
        "avg_claims_retained": 1.9847222222222225,
        "avg_claims_retained_std": 0.45195000881583347,
        "precision": 0.6110926870748299,
        "precision_std": 0.11778145514506322
      },
      "baseline": {
        "coverage": 0.9312676056338028,
        "coverage_std": 0.01731879002697396,
        "avg_claims_retained": 2.2001690140845067,
        "avg_claims_retained_std": 0.25667794209696926,
        "precision": 0.5760910798122065,
        "precision_std": 0.05309294787977286
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.25,
        "lambda_": 0.9,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9421031746031746,
        "hard_coverage_std": 0.041659088502089124,
        "hard_avg_claims_retained_mean": 1.9847222222222225,
        "hard_avg_claims_retained_std": 0.45195000881583347,
        "hard_precision_mean": 0.6110926870748299,
        "hard_precision_std": 0.11778145514506322
      },
      "meets_coverage": true
    },
    "0.08": {
      "alpha": 0.08,
      "target_coverage": 0.92,
      "source": "felm_anneal",
      "feature_set": "7_features",
      "features": [
        "frequency-score",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "nx_pagerank",
        "nx_reachability",
        "nx_out_degree"
      ],
      "learned": {
        "coverage": 0.9363888888888889,
        "coverage_std": 0.04032361142303625,
        "avg_claims_retained": 2.10952380952381,
        "avg_claims_retained_std": 0.3633810567311269,
        "precision": 0.6353406084656085,
        "precision_std": 0.07939856335930871
      },
      "baseline": {
        "coverage": 0.9214647887323943,
        "coverage_std": 0.018217666054599003,
        "avg_claims_retained": 2.4501971830985916,
        "avg_claims_retained_std": 0.23481517800994994,
        "precision": 0.6371147999105745,
        "precision_std": 0.05024683848853584
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.25,
        "lambda_": 1.5,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9363888888888889,
        "hard_coverage_std": 0.04032361142303625,
        "hard_avg_claims_retained_mean": 2.10952380952381,
        "hard_avg_claims_retained_std": 0.3633810567311269,
        "hard_precision_mean": 0.6353406084656085,
        "hard_precision_std": 0.07939856335930871
      },
      "meets_coverage": true
    },
    "0.09": {
      "alpha": 0.09,
      "target_coverage": 0.91,
      "source": "felm_hone",
      "feature_set": "20_features",
      "features": [
        "frequency-score",
        "claim_index",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "has_unnecessary_dependencies",
        "problem_relevance",
        "uses_problem_data",
        "domain_science",
        "domain_reasoning",
        "nx_in_degree",
        "nx_out_degree",
        "nx_pagerank",
        "nx_betweenness",
        "nx_closeness",
        "nx_clustering",
        "nx_is_source",
        "nx_is_sink",
        "nx_reachability",
        "nx_depth_from_sources"
      ],
      "learned": {
        "coverage": 0.9139285714285714,
        "coverage_std": 0.04530729530451504,
        "avg_claims_retained": 2.760357142857143,
        "avg_claims_retained_std": 0.444718557405786,
        "precision": 0.7079765419765419,
        "precision_std": 0.05769065357895684
      },
      "baseline": {
        "coverage": 0.9079999999999998,
        "coverage_std": 0.019979040793232657,
        "avg_claims_retained": 2.6562816901408444,
        "avg_claims_retained_std": 0.1811952994981004,
        "precision": 0.6821681198300918,
        "precision_std": 0.03279157111570292
      },
      "hyperparams": {
        "temp": 1.0,
        "beta": 1,
        "gamma": 1.0,
        "lambda_": 1.65,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9139285714285714,
        "hard_coverage_std": 0.04530729530451504,
        "hard_avg_claims_retained_mean": 2.760357142857143,
        "hard_avg_claims_retained_std": 0.444718557405786,
        "hard_precision_mean": 0.7079765419765419,
        "hard_precision_std": 0.05769065357895684
      },
      "meets_coverage": true
    },
    "0.1": {
      "alpha": 0.1,
      "target_coverage": 0.9,
      "source": "felm_hone",
      "feature_set": "20_features",
      "features": [
        "frequency-score",
        "claim_index",
        "coherent_to_ancestors",
        "inference_gap_size",
        "has_missing_dependencies",
        "has_unnecessary_dependencies",
        "problem_relevance",
        "uses_problem_data",
        "domain_science",
        "domain_reasoning",
        "nx_in_degree",
        "nx_out_degree",
        "nx_pagerank",
        "nx_betweenness",
        "nx_closeness",
        "nx_clustering",
        "nx_is_source",
        "nx_is_sink",
        "nx_reachability",
        "nx_depth_from_sources"
      ],
      "learned": {
        "coverage": 0.9053571428571429,
        "coverage_std": 0.04800168687197146,
        "avg_claims_retained": 2.846746031746032,
        "avg_claims_retained_std": 0.4311378112567819,
        "precision": 0.7341042568542568,
        "precision_std": 0.058453704655857086
      },
      "baseline": {
        "coverage": 0.9007887323943662,
        "coverage_std": 0.020213421880577218,
        "avg_claims_retained": 2.7548732394366198,
        "avg_claims_retained_std": 0.15754765135642929,
        "precision": 0.7018582606751622,
        "precision_std": 0.022396892802106768
      },
      "hyperparams": {
        "temp": 0.5,
        "beta": 1,
        "gamma": 1.25,
        "lambda_": 1.9,
        "violation_mode": "exponential",
        "squash_temp": 0.8,
        "cutoff_temp": 0.01,
        "lr": 0.015,
        "hard_coverage_mean": 0.9053571428571429,
        "hard_coverage_std": 0.04800168687197146,
        "hard_avg_claims_retained_mean": 2.846746031746032,
        "hard_avg_claims_retained_std": 0.4311378112567819,
        "hard_precision_mean": 0.7341042568542568,
        "hard_precision_std": 0.058453704655857086
      },
      "meets_coverage": true
    }
  }
}