{"id":"W4417514379","doi":"10.2196/75607","title":"Comparing ChatGPT and DeepSeek for Assessment of Multiple-Choice Questions in Orthopedic Medical Education: Cross-Sectional Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Orthopedic surgery; Correctness; MEDLINE","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":[0.03133062,0.0005849141,0.000801057,0.002167133,0.0007377347,0.001382188,0.0007839503,0.001029414,0.001443084],"category_scores_gemma":[0.0733615,0.0008702037,0.001348037,0.001434153,0.0008405585,0.002271081,0.002120415,0.001571115,0.0005570546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001216496,"about_ca_system_score_gemma":0.001676891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003222074,"about_ca_topic_score_gemma":0.005289866,"domain_scores_codex":[0.9807444,0.01011518,0.001951983,0.001806741,0.00461975,0.0007619873],"domain_scores_gemma":[0.9023421,0.05082737,0.01984846,0.004684464,0.01811051,0.004187073],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004485213,0.001046635,0.98163,0.0001198571,0.0001710646,0.00005089341,0.003729933,0.0001633796,0.0002692944,0.00006513434,0.0004291129,0.01187633],"study_design_scores_gemma":[0.00007114896,0.003415347,0.9897189,0.00008434713,0.0001118217,0.0002095786,0.00331717,0.001610575,0.0005259839,0.00007095103,0.0008307105,0.00003345275],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981511,0.0001170558,0.0008299894,0.00005439132,0.00002402888,0.000260219,0.0001675513,0.00001374755,0.0003819886],"genre_scores_gemma":[0.9969515,0.0001053355,0.001540104,0.0001131179,0.00002292452,0.000642905,0.0003229833,0.00001509107,0.000285886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03133062,"threshold_uncertainty_score":0.1656941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3338253063029052,"score_gpt":0.6309721321600598,"score_spread":0.2971468258571546,"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."}}