{"id":"W4386407038","doi":"10.2196/46482","title":"Artificial Intelligence in Medical Education: Comparative Analysis of ChatGPT, Bing, and Medical Students in Germany","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Medical education; German; Psychology; Medicine; Geography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00275766,0.0001856815,0.0006460432,0.001791816,0.00006105866,0.00002513713,0.0003750434,0.0004810558,0.003071749],"category_scores_gemma":[0.00421068,0.0001730808,0.00009033317,0.00451725,0.0003683868,0.000128413,0.0001105048,0.000700095,0.00009393723],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002320482,"about_ca_system_score_gemma":0.008351706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002083133,"about_ca_topic_score_gemma":0.004059679,"domain_scores_codex":[0.9947472,0.0002382489,0.001432152,0.0004872042,0.00271771,0.0003775269],"domain_scores_gemma":[0.9978173,0.0005039718,0.0002013717,0.0003206368,0.0002675699,0.0008891385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001455007,0.004430716,0.4530787,0.0002408916,0.0001140959,0.00002720452,0.02401931,0.00000791143,0.00001834293,0.003943497,0.002368416,0.5116054],"study_design_scores_gemma":[0.0001198977,0.0002367691,0.9211098,0.001974386,0.0001741033,0.00004016565,0.02663692,0.04385274,0.0003107553,0.003490372,0.001757313,0.0002967698],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699277,0.0004314037,0.00007859997,0.02729678,0.001000078,0.0006557603,0.000001662599,0.00004099904,0.0005670355],"genre_scores_gemma":[0.9949685,0.0008435702,0.00006248839,0.002927796,0.0004895899,0.0003792618,0.0001675213,0.00001171322,0.000149597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5113086,"threshold_uncertainty_score":0.9978396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1132779861705955,"score_gpt":0.5313391288631245,"score_spread":0.418061142692529,"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."}}