{"id":"W4379508361","doi":"10.2196/48163","title":"The Advent of Generative Language Models in Medical Education","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":203,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Stryker","keywords":"Credibility; Relevance (law); Computer science; Quality (philosophy); Knowledge management; Medical education; Medicine; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.01162317,0.0007503193,0.0005743576,0.001974404,0.000597742,0.00480915,0.001728348,0.002385373,0.006306913],"category_scores_gemma":[0.03836647,0.0009599444,0.001582753,0.001081473,0.003950125,0.004230748,0.00363382,0.004414493,0.001460483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00295132,"about_ca_system_score_gemma":0.002969204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005215722,"about_ca_topic_score_gemma":0.005610555,"domain_scores_codex":[0.9932452,0.004701484,0.0002670471,0.0004600324,0.001201894,0.0001244354],"domain_scores_gemma":[0.9574676,0.0379959,0.0006790506,0.002165682,0.001302348,0.0003895285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001030351,0.0001221023,0.003598251,0.001325949,0.0001775742,0.0002499718,0.003713489,0.08485151,0.002210173,0.6538051,0.01001224,0.2398307],"study_design_scores_gemma":[0.00007705964,0.000160068,0.0009915313,0.001463289,0.0001066516,0.0003918599,0.0004449502,0.1771138,0.003035321,0.6423917,0.1736694,0.000154459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007401343,0.008751198,0.9373734,0.01530665,0.0005802609,0.0002184808,0.0003086464,0.001010662,0.02904939],"genre_scores_gemma":[0.2530095,0.0121881,0.718327,0.004371813,0.0006894478,0.0006283114,0.0005619844,0.0004611996,0.009762577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01162317,"threshold_uncertainty_score":0.06146997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08147571299040592,"score_gpt":0.4922474816511003,"score_spread":0.4107717686606944,"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."}}