{"id":"W4409223223","doi":"10.1109/access.2025.3558218","title":"Variability-Aware Machine Learning Model Selection: Feature Modeling, Instantiation, and Experimental Case Study","year":2025,"lang":"en","type":"article","venue":"IEEE Access","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; Feature selection; Artificial intelligence; Selection (genetic algorithm); Machine learning; Feature (linguistics); Data modeling; Software engineering","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":[0.000456218,0.0001451177,0.0001409205,0.0001496207,0.0005287778,0.0005466748,0.0004607094,0.00006757634,0.000004355644],"category_scores_gemma":[0.00006154873,0.0001379564,0.00002233796,0.0005323833,0.00001601956,0.001029065,0.0002567748,0.000363379,0.000001475664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005619958,"about_ca_system_score_gemma":0.0000827973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006057448,"about_ca_topic_score_gemma":0.0001393887,"domain_scores_codex":[0.9987275,0.0002140485,0.0001935847,0.0005448555,0.0001695256,0.0001504615],"domain_scores_gemma":[0.9993231,0.0000567254,0.00007580341,0.0003775798,0.0001139395,0.00005280422],"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":[0.00003515086,0.0007577068,0.1822797,0.00007082373,0.00007662823,0.0000959091,0.004521071,0.7925534,0.0007298535,0.005712418,0.0006790048,0.01248826],"study_design_scores_gemma":[0.0004252151,0.00004918737,0.0004658103,0.000009015122,0.00001235536,0.00008693662,0.000239676,0.9979302,0.0002009535,0.0003504586,0.00009915227,0.0001310696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3542248,0.0000843517,0.6445854,0.0003140086,0.0001265992,0.0001760914,0.000001868823,0.0001789872,0.0003078303],"genre_scores_gemma":[0.9959444,0.000005346714,0.003468541,0.0001346495,0.00003362535,0.00003842396,0.00001058488,0.000007457205,0.0003569797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6417196,"threshold_uncertainty_score":0.5625699,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02973009908300829,"score_gpt":0.3413248294311608,"score_spread":0.3115947303481525,"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."}}