{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02342753,0.001383617,0.00103701,0.002265583,0.001381952,0.002779076,0.0009926198,0.002380855,0.01062049],"category_scores_gemma":[0.1141821,0.0006228532,0.0008899465,0.001466653,0.000774293,0.007032157,0.003506356,0.001640046,0.00449223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001185106,"about_ca_system_score_gemma":0.0009901716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006275369,"about_ca_topic_score_gemma":0.0006693253,"domain_scores_codex":[0.9765958,0.01687258,0.00157183,0.001655401,0.002265529,0.001039004],"domain_scores_gemma":[0.7777095,0.1850247,0.0119112,0.01304522,0.009663283,0.002646177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005168079,0.002852985,0.2491122,0.003653411,0.0002394219,0.001590662,0.1429749,0.008389732,0.06080496,0.01169618,0.0489488,0.4645688],"study_design_scores_gemma":[0.0008086191,0.005430251,0.2312523,0.002321773,0.0004976403,0.002300234,0.157444,0.191629,0.05870295,0.03678593,0.311787,0.001040138],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.8543211,0.0004396999,0.1232872,0.001826858,0.0001292322,0.001391074,0.003091097,0.007281402,0.008232238],"genre_scores_gemma":[0.9105004,0.0002602439,0.07523412,0.00101067,0.0001594653,0.00216654,0.004628378,0.0009694568,0.005070721],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02342753,"threshold_uncertainty_score":0.1238981,"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."}}