{"id":"W2566941704","doi":"10.1007/s40037-016-0322-0","title":"Ensuring the quality of multiple-choice exams administered to small cohorts: A cautionary tale","year":2017,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Sherbrooke; McGill University Health Centre","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Medical education; Quality (philosophy); Medicine; Medical physics; Data science; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01125741,0.000148939,0.000362337,0.0002624695,0.0006324288,0.0001892675,0.001702037,0.0001140255,0.000633729],"category_scores_gemma":[0.7593633,0.000093424,0.000134558,0.0005191637,0.0004487066,0.0001462521,0.0002652207,0.0003130318,0.0000668897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001043889,"about_ca_system_score_gemma":0.0004794314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000980953,"about_ca_topic_score_gemma":0.0002496121,"domain_scores_codex":[0.9955795,0.0009242023,0.0007523228,0.0006566487,0.001837032,0.0002502509],"domain_scores_gemma":[0.9233038,0.07146601,0.001228811,0.002607324,0.0008869931,0.0005070355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00018934,0.001180967,0.5590965,0.0000229229,0.00004860334,0.00000123166,0.0158717,0.00002654622,0.0005122281,0.006157173,0.0054464,0.4114464],"study_design_scores_gemma":[0.0002604029,0.00008415258,0.9682247,0.00006747265,0.000007033393,0.000004936761,0.01926915,0.0001113923,0.00008228817,0.004296648,0.007471504,0.0001203158],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9665952,0.0003411476,0.004537075,0.01372741,0.001661608,0.0003349689,0.000009183571,0.00003185341,0.01276158],"genre_scores_gemma":[0.9927461,0.00003953331,0.004860581,0.0005859921,0.0004798937,0.0000487941,0.000003026741,0.000009063212,0.001227026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7481059,"threshold_uncertainty_score":0.6938888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5824138672067543,"score_gpt":0.5656129978868703,"score_spread":0.016800869319884,"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."}}