{"id":"W4406427891","doi":"10.2196/62779","title":"Detecting Artificial Intelligence–Generated Versus Human-Written Medical Student Essays: Semirandomized Controlled Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Randomized controlled trial; Psychology; Computer science; Medicine; World Wide Web; Internal medicine","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":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003351128,0.0003120716,0.0009268119,0.0004744276,0.0004766381,0.00009347392,0.000370394,0.0005243807,0.003118599],"category_scores_gemma":[0.01187192,0.0002597497,0.0002191783,0.0009989357,0.0001994818,0.0001070527,0.00008746539,0.001002793,0.0001385033],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004622843,"about_ca_system_score_gemma":0.006230851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006504042,"about_ca_topic_score_gemma":0.0006733203,"domain_scores_codex":[0.9946,0.0006025307,0.001841735,0.0006471187,0.00180089,0.0005076986],"domain_scores_gemma":[0.9963197,0.001270579,0.0002772077,0.0005392136,0.0007849552,0.0008083822],"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":[0.01638262,0.01432338,0.01119554,0.00019414,0.0005791196,0.00004262241,0.009337729,0.000005950179,0.0004862555,0.003626332,0.004297291,0.939529],"study_design_scores_gemma":[0.08545982,0.01377779,0.02460531,0.009524912,0.005427503,0.0002060399,0.7442656,0.03707668,0.03144524,0.03376501,0.01044657,0.00399949],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9682286,0.0005125724,0.001317615,0.01657547,0.005975856,0.00411346,6.551745e-7,0.0001955355,0.003080229],"genre_scores_gemma":[0.9923708,0.00008225557,0.00008050138,0.002626422,0.001885161,0.002118875,0.00007013692,0.00002801942,0.0007378175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9355295,"threshold_uncertainty_score":0.9999855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1007353124654197,"score_gpt":0.509232481821237,"score_spread":0.4084971693558173,"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."}}