{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005529192,0.0003293755,0.0002632202,0.0002775739,0.0004406136,0.0003732473,0.0005690288,0.0003215086,0.000008841436],"category_scores_gemma":[0.00004720725,0.0003634417,0.00008259142,0.0005352189,0.00003635686,0.0003595296,0.002200095,0.002053828,0.00001185789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000213529,"about_ca_system_score_gemma":0.0001906356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006603777,"about_ca_topic_score_gemma":0.0001451788,"domain_scores_codex":[0.9975625,0.0003677096,0.0001978226,0.001532263,0.0001218062,0.0002179567],"domain_scores_gemma":[0.998755,0.00005641123,0.0001493456,0.000757933,0.0001479415,0.0001333951],"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":[0.00001619631,0.000188187,0.006640508,0.00007241854,0.0000697331,0.0005780191,0.00159598,0.9671291,0.00001566918,0.02337938,0.00004165073,0.0002732174],"study_design_scores_gemma":[0.0003348454,0.00009290203,0.0000404723,0.00003132103,0.00008074629,0.0001794481,0.0007855353,0.9925045,0.000008275933,0.005554804,0.00004305508,0.0003440577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4795622,0.0001178482,0.5191584,0.00009631508,0.0001522318,0.0002480201,0.00001114217,0.0003694259,0.0002843966],"genre_scores_gemma":[0.9966443,0.00003115413,0.002183201,0.00002714291,0.00005704107,0.000003612244,0.00005455218,0.00002403184,0.0009749184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5170822,"threshold_uncertainty_score":0.9998817,"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."}}