{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001284247,0.0001195018,0.0001103036,0.0004030043,0.0002029281,0.0001398619,0.0002332899,0.00005894697,0.000006851787],"category_scores_gemma":[0.0002574956,0.00009727792,0.00002008063,0.001982282,0.0000127176,0.0005878714,0.00009884621,0.0003760745,0.00004693883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009427495,"about_ca_system_score_gemma":0.00006405341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003946157,"about_ca_topic_score_gemma":0.0005564966,"domain_scores_codex":[0.9985909,0.0002449915,0.0001817672,0.0004971054,0.0002329987,0.0002521955],"domain_scores_gemma":[0.9994104,0.0001403389,0.00008219336,0.0002690137,0.00005330005,0.00004478889],"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":[0.00005118146,0.0001100071,0.1422253,0.00008959033,0.00001360184,0.000008974945,0.001487522,0.5562099,0.007381282,0.01559733,0.00006191476,0.2767634],"study_design_scores_gemma":[0.000205938,0.00009013488,0.01691267,0.0000156342,0.000002194246,0.00001200126,0.00003756297,0.9810008,0.0008347388,0.000513353,0.0002444359,0.0001305301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08112372,0.000002580184,0.9158353,0.0003492353,0.00004979578,0.0001669509,5.627479e-7,0.001101362,0.001370545],"genre_scores_gemma":[0.9859785,0.000009016117,0.01284888,0.00002744101,0.00002317455,0.00004450221,0.0000262324,0.00001206848,0.001030111],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9048548,"threshold_uncertainty_score":0.3966878,"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."}}