{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01348716,0.0009450323,0.0008708917,0.001279527,0.0008586636,0.002503223,0.002776965,0.002484492,0.001662715],"category_scores_gemma":[0.0298795,0.0004994581,0.001459586,0.001935525,0.001735735,0.002079941,0.001913248,0.002301377,0.0004441055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001655752,"about_ca_system_score_gemma":0.001265981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002721155,"about_ca_topic_score_gemma":0.003271673,"domain_scores_codex":[0.9905166,0.006184582,0.0005185566,0.0009410089,0.001468649,0.00037051],"domain_scores_gemma":[0.9617816,0.02974024,0.001119259,0.004982783,0.001942531,0.0004336012],"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":[0.001239641,0.005461733,0.04212296,0.001686464,0.0005041762,0.003491544,0.003603697,0.577961,0.01145393,0.05829212,0.009742341,0.2844404],"study_design_scores_gemma":[0.0002800823,0.001040774,0.005118784,0.0001403965,0.0001511066,0.0007597453,0.0006448954,0.935464,0.01975605,0.02559339,0.01094656,0.00010412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4427808,0.001241836,0.54194,0.001642468,0.00009660174,0.001396163,0.0009734654,0.001373547,0.008555131],"genre_scores_gemma":[0.6854534,0.0003885132,0.3109632,0.0002019149,0.00004146765,0.0008291783,0.0008073483,0.0001219417,0.001192931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01348716,"threshold_uncertainty_score":0.07132775,"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."}}