{"id":"W4391093893","doi":"10.1109/bigdata59044.2023.10386105","title":"Extending Variability-Aware Model Selection with Bias Detection in Machine Learning Projects","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Heuristics; Selection (genetic algorithm); Model selection; Artificial intelligence; Process (computing); Feature selection; Selection bias; Data mining; Key (lock); Data modeling; Feature engineering; Deep learning; Database","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0238109,0.001482734,0.001663949,0.00259849,0.0008489043,0.003113667,0.003439341,0.002140187,0.001275536],"category_scores_gemma":[0.08851751,0.0009472345,0.002333353,0.002311273,0.001441346,0.004268544,0.004503414,0.003188684,0.0005176495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001481057,"about_ca_system_score_gemma":0.00301896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002397148,"about_ca_topic_score_gemma":0.0026574,"domain_scores_codex":[0.9819457,0.01076391,0.001066488,0.002219463,0.003363651,0.0006408343],"domain_scores_gemma":[0.9215949,0.05569641,0.005515856,0.01045946,0.005705109,0.001028312],"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":[0.0003940045,0.0004983087,0.02674338,0.0003457144,0.0004845913,0.0003364985,0.001251076,0.5523449,0.00598086,0.02642212,0.002504007,0.3826945],"study_design_scores_gemma":[0.00003072151,0.00008661183,0.0008019063,0.00003948536,0.00004144231,0.00005166145,0.00005526008,0.9717408,0.002275896,0.02385789,0.0009936295,0.00002474339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01440382,0.0001422495,0.9839202,0.0002358967,0.00001904609,0.00008867698,0.00004697251,0.0008082375,0.0003349928],"genre_scores_gemma":[0.3945784,0.0001671828,0.6029928,0.0002995843,0.00007059615,0.0003909864,0.0004038684,0.000416913,0.0006797196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0238109,"threshold_uncertainty_score":0.1259255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04510676513135061,"score_gpt":0.273076250363951,"score_spread":0.2279694852326004,"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."}}