{"id":"W4389072684","doi":"10.48550/arxiv.2311.14214","title":"Extending Variability-Aware Model Selection with Bias Detection in Machine Learning Projects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Heuristics; Selection (genetic algorithm); Model selection; Machine learning; Selection bias; Process (computing); Feature selection; Artificial intelligence; Data mining; Sample (material); Code (set theory); Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001107615,0.0003002966,0.000276428,0.0007217944,0.0002661927,0.0001766887,0.0007770973,0.0002671197,0.000004045722],"category_scores_gemma":[0.0002264874,0.0003201372,0.00007664951,0.001631844,0.00004149076,0.0005437798,0.0007910023,0.001522056,0.00003296669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004687873,"about_ca_system_score_gemma":0.0002363791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001264573,"about_ca_topic_score_gemma":0.001348697,"domain_scores_codex":[0.9972958,0.000546229,0.0002266286,0.00144397,0.0001414884,0.0003458712],"domain_scores_gemma":[0.9985206,0.0001907912,0.0003278103,0.0007396601,0.0001307911,0.00009039102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004359576,0.00005458235,0.04118597,0.0001036127,0.00002060442,0.00003407551,0.0002542314,0.9474856,0.00008539536,0.00793073,0.000004548074,0.002797116],"study_design_scores_gemma":[0.0003301071,0.00008125354,0.007529756,0.0001150426,0.00002547046,0.000006704461,0.00004477374,0.9859505,0.0000878766,0.005433662,0.0000512472,0.0003435603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.164437,0.000004976042,0.8339351,0.00007475303,0.0001477101,0.0003050383,0.00000528825,0.0007896292,0.0003004672],"genre_scores_gemma":[0.9955151,0.00006152975,0.002957862,0.00001167418,0.00004014879,0.00000625026,0.00007775106,0.00003129797,0.001298361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8310781,"threshold_uncertainty_score":0.9999251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1334173804204707,"score_gpt":0.2154775260294495,"score_spread":0.08206014560897887,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}