{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001099327,0.00009658294,0.000174938,0.0002020023,0.00009303753,0.00001049983,0.000166345,0.0002162322,0.0005315054],"category_scores_gemma":[0.003035611,0.00006908,0.00005617943,0.0007684005,0.0001508197,0.00008972606,0.00003040172,0.0003497897,0.0001016204],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001736519,"about_ca_system_score_gemma":0.01149664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001108723,"about_ca_topic_score_gemma":0.0005598627,"domain_scores_codex":[0.9978862,0.0001303175,0.0005965577,0.000210179,0.0009318776,0.0002447982],"domain_scores_gemma":[0.9987042,0.000273011,0.0001153917,0.0002846544,0.0002466573,0.0003760973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00006931606,0.001120055,0.004672202,0.0001424689,0.00001110875,0.000003875192,0.01675758,0.00001030743,0.0001000858,0.00884011,0.04100419,0.9272687],"study_design_scores_gemma":[0.001206794,0.001427402,0.1858788,0.008398152,0.0001548515,0.0003194123,0.3821765,0.203685,0.01641214,0.116125,0.08298156,0.001234475],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9115736,0.001008666,0.00009520577,0.08242799,0.001766802,0.0006699356,9.002774e-7,0.00004821318,0.002408616],"genre_scores_gemma":[0.9926096,0.0009104835,0.0000923312,0.003165303,0.0009299843,0.0005913015,0.0001386684,0.00001464538,0.001547659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9260342,"threshold_uncertainty_score":0.9941072,"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."}}