{"id":"W4406031787","doi":"10.48550/arxiv.2501.00532","title":"Variability-Aware Machine Learning Model Selection: Feature Modeling, Instantiation, and Experimental Case Study","year":2024,"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":"Feature selection; Computer science; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Model selection; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.008801261,0.000933956,0.0007169098,0.001141784,0.0007594827,0.001863069,0.002502658,0.002019834,0.001680574],"category_scores_gemma":[0.02170205,0.0004079502,0.001023901,0.001661266,0.001405103,0.00163635,0.001712581,0.001972761,0.0004312178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001380847,"about_ca_system_score_gemma":0.001067097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003266101,"about_ca_topic_score_gemma":0.004246129,"domain_scores_codex":[0.9936928,0.004050984,0.0003870496,0.000639915,0.0009438057,0.0002855579],"domain_scores_gemma":[0.9733653,0.02055277,0.0008602854,0.003326811,0.001489401,0.0004054568],"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":[0.001459851,0.007194238,0.0431626,0.001831629,0.0004703206,0.003554809,0.003790014,0.5911102,0.01323736,0.03518044,0.01257766,0.2864309],"study_design_scores_gemma":[0.0003658149,0.001486699,0.00599087,0.0001196468,0.000123726,0.0007279394,0.0008757176,0.9437227,0.02362131,0.0130357,0.009834049,0.00009584058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6795738,0.0007112026,0.3068942,0.001096816,0.0000852452,0.001397572,0.001023922,0.001679229,0.007538044],"genre_scores_gemma":[0.7326093,0.0002667544,0.2637486,0.000169661,0.0000303573,0.000811182,0.0009390955,0.0001195678,0.001305498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008801261,"threshold_uncertainty_score":0.0465461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05974465071298773,"score_gpt":0.226961230082864,"score_spread":0.1672165793698762,"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."}}