{"id":"W4411552822","doi":"10.1109/icse55347.2025.00066","title":"Answering User Questions About Machine Learning Models Through Standardized Model Cards","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004331752,0.0001619712,0.0001977546,0.0001210971,0.0003841349,0.0002944356,0.0006251387,0.00007377085,0.00001573578],"category_scores_gemma":[0.0001137357,0.0001449718,0.00007346515,0.0004519937,0.0000322817,0.001066426,0.0002998807,0.0003703448,0.00001649985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007534194,"about_ca_system_score_gemma":0.0001666143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005560202,"about_ca_topic_score_gemma":0.00006415508,"domain_scores_codex":[0.9986092,0.0001231903,0.0002632104,0.0004744792,0.0002682734,0.0002615911],"domain_scores_gemma":[0.9989846,0.00007443816,0.00006827137,0.000691794,0.0001258716,0.00005498112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005378387,0.00001776268,0.0003935389,0.00001212834,0.00001523024,7.912257e-7,0.0003018898,0.4132563,0.0002552311,0.575141,0.0006927167,0.009908052],"study_design_scores_gemma":[0.0003115663,0.00001378473,0.0002618275,0.00003441238,0.00001032049,0.000001620101,0.00001828296,0.9529563,0.0001700081,0.01896405,0.02710808,0.0001497531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007745959,0.0003726349,0.9227877,0.002010455,0.0001395021,0.0001114165,0.00001068763,0.0007439183,0.07304906],"genre_scores_gemma":[0.6904406,0.0001900407,0.2939449,0.0004742893,0.00002211937,0.0000286305,0.00003983465,0.00001240653,0.01484721],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.689666,"threshold_uncertainty_score":0.5911778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02847033369887263,"score_gpt":0.2992658017940166,"score_spread":0.270795468095144,"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."}}