{"id":"W4396685708","doi":"10.2196/58126","title":"Use of Multiple-Choice Items in Summative Examinations: Questionnaire Survey Among German Undergraduate Dental Training Programs","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Medical Education and Admissions","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Respondent; Summative assessment; Multiple choice; German; Medicine; Test (biology); Dentistry; Medical education; Family medicine; Psychology; Mathematics education; Formative assessment; Significant difference","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01450063,0.000405035,0.0005205912,0.00300424,0.0004045177,0.0008304952,0.0006654229,0.0005914273,0.001462754],"category_scores_gemma":[0.02622544,0.0003317644,0.0004654366,0.002025753,0.0007388104,0.0007024164,0.001592615,0.0005972125,0.0004068552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00117513,"about_ca_system_score_gemma":0.001594484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002105783,"about_ca_topic_score_gemma":0.002869538,"domain_scores_codex":[0.9898893,0.004659875,0.001280516,0.0005383838,0.00278816,0.0008437477],"domain_scores_gemma":[0.9808472,0.007661439,0.005705087,0.0006590806,0.002876674,0.002250687],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001913552,0.0007061811,0.9211073,0.0005945836,0.00005871442,0.0002683881,0.006323093,0.0002629062,0.00151918,0.0001258884,0.001610537,0.0672319],"study_design_scores_gemma":[0.00001805067,0.0006811813,0.9887788,0.0002010387,0.00003008509,0.0003866395,0.005703325,0.0006420023,0.001104858,0.00004362157,0.002382862,0.00002744304],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982896,0.0002949786,0.0004426684,0.0001504383,0.00001064268,0.0001453087,0.0001601817,0.00001574017,0.0004904541],"genre_scores_gemma":[0.9973128,0.0004207232,0.001474292,0.00009009462,0.00001064161,0.0001497111,0.0002725208,0.000005314317,0.000263651],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9854994,"threshold_uncertainty_score":0.07668757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08486289422007673,"score_gpt":0.4210586528993991,"score_spread":0.3361957586793224,"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."}}