{"id":"W4414005603","doi":"10.2196/76702","title":"Development of a Clinical Clerkship Mentor Using Generative AI and Evaluation of Its Effectiveness in a Medical Student Trial Compared to Student Mentors: 2-Part Comparative Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Likert scale; Medical education; Rubric; CLARITY; Context (archaeology); Psychology; Scale (ratio); Medicine; Mathematics education","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":[0.01135708,0.0008239202,0.0008457212,0.0009200537,0.001105258,0.001197901,0.001534661,0.001388151,0.003619098],"category_scores_gemma":[0.01547954,0.000368097,0.0008695484,0.0004716284,0.0007996179,0.0008671258,0.001551784,0.001043269,0.0008279142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220092,"about_ca_system_score_gemma":0.001893066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001014447,"about_ca_topic_score_gemma":0.001790278,"domain_scores_codex":[0.9943255,0.003722616,0.00031984,0.0004164143,0.0007030091,0.000512698],"domain_scores_gemma":[0.9886298,0.003357101,0.001147148,0.001601358,0.001780252,0.003484235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.03742753,0.2291432,0.09440504,0.001995939,0.0005446647,0.001664797,0.01876655,0.003081941,0.01626894,0.0005170524,0.002258859,0.5939254],"study_design_scores_gemma":[0.01242825,0.8189856,0.122515,0.0002982639,0.0005591233,0.001248573,0.01070317,0.006561044,0.01766118,0.0001950264,0.008603374,0.0002414194],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966881,0.0000902742,0.0009755719,0.00005097647,0.00002715273,0.001654272,0.00004963687,0.00004309179,0.0004208819],"genre_scores_gemma":[0.9828273,0.000389787,0.01054328,0.0002070433,0.00009613518,0.004077415,0.000227219,0.00002683187,0.001604897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01135708,"threshold_uncertainty_score":0.06006271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4342178331578377,"score_gpt":0.6669062045329408,"score_spread":0.2326883713751031,"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."}}