{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02487231,0.001508992,0.001794157,0.002727089,0.0008974035,0.003239101,0.003613903,0.002327321,0.001232398],"category_scores_gemma":[0.09344416,0.0009947764,0.002452027,0.002517685,0.001641097,0.004429888,0.004982393,0.003608916,0.0005336501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001557307,"about_ca_system_score_gemma":0.002984741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243043,"about_ca_topic_score_gemma":0.002472911,"domain_scores_codex":[0.9803696,0.0122514,0.001028892,0.002389927,0.003317824,0.0006423135],"domain_scores_gemma":[0.9149766,0.06137297,0.005644672,0.01152246,0.005396122,0.001087198],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003649362,0.0004487593,0.02431611,0.000333705,0.000509927,0.0003075413,0.001112484,0.5782424,0.005022316,0.03404119,0.002731654,0.3525691],"study_design_scores_gemma":[0.00002946283,0.00007527925,0.0007023693,0.00003620611,0.00003790205,0.00004354174,0.00004524724,0.964155,0.001908627,0.03200025,0.0009436376,0.00002255898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01165067,0.000143681,0.9868173,0.0002527174,0.0000190141,0.00007158491,0.0000456221,0.0007036948,0.000295775],"genre_scores_gemma":[0.4011787,0.0001907718,0.5961559,0.0003502288,0.00009314667,0.0004061509,0.0004379176,0.000469634,0.0007175307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9751277,"threshold_uncertainty_score":0.131539,"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."}}