{"id":"W7161978291","doi":"10.82308/12415","title":"Use of Large Language Models for Family medicine education and examination","year":2025,"lang":"en","type":"dissertation","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"English language","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.007810569,0.001568104,0.0007778232,0.002128793,0.001199974,0.003815065,0.001909632,0.001736159,0.01112613],"category_scores_gemma":[0.0297571,0.0008547442,0.002501654,0.001095316,0.0005251462,0.00482905,0.002449937,0.002657817,0.004892191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00288892,"about_ca_system_score_gemma":0.00303583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03189874,"about_ca_topic_score_gemma":0.04358005,"domain_scores_codex":[0.9949039,0.00376469,0.00020653,0.0006675402,0.0003147786,0.000142624],"domain_scores_gemma":[0.9714217,0.02491508,0.0004951368,0.001293397,0.001469838,0.0004048354],"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":[0.002351757,0.001608589,0.03624078,0.001070738,0.00122649,0.001497034,0.004729574,0.2263895,0.006073252,0.02844662,0.03267823,0.6576874],"study_design_scores_gemma":[0.0001025416,0.0001424474,0.002884392,0.000139368,0.0001621182,0.0001988702,0.0006535314,0.9631366,0.001728254,0.01749576,0.01328259,0.00007346403],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1299979,0.002306307,0.8117711,0.005457317,0.0007753256,0.001027702,0.007344305,0.02294994,0.01837009],"genre_scores_gemma":[0.6009338,0.0008800315,0.3751858,0.0007988549,0.0002214141,0.001072311,0.009219824,0.001041806,0.01064608],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03189874,"threshold_uncertainty_score":0.06342614,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2160418163628776,"score_gpt":0.4876830809789099,"score_spread":0.2716412646160323,"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."}}