{"id":"W4206415959","doi":"10.1097/00001888-900000000-97702","title":"Ensuring the Quality of Multiple-Choice Tests","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Quality (philosophy); MEDLINE; Computer science; Psychology; Political science; Law","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5191211,0.00167093,0.004481489,0.004403962,0.001901702,0.01022641,0.006732293,0.007019106,0.006154187],"category_scores_gemma":[0.9031622,0.002093645,0.002642395,0.004666855,0.01066032,0.008113527,0.00676388,0.009494579,0.002388693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003926695,"about_ca_system_score_gemma":0.01900506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00209904,"about_ca_topic_score_gemma":0.001545828,"domain_scores_codex":[0.3143508,0.5873681,0.0311324,0.01202027,0.05293873,0.00218966],"domain_scores_gemma":[0.02845794,0.8966915,0.01422567,0.03579866,0.02339297,0.00143319],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007344615,0.0005383732,0.03127466,0.00642332,0.002893442,0.000510531,0.006373358,0.02640473,0.003991805,0.1860218,0.02944482,0.6987786],"study_design_scores_gemma":[0.00257071,0.001419557,0.01490445,0.001893976,0.0006578739,0.001016461,0.0008291554,0.1614724,0.01098049,0.7662028,0.03768972,0.0003623558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01271152,0.001884436,0.9676254,0.01153062,0.0007520921,0.001284091,0.0004868607,0.0009048082,0.002820105],"genre_scores_gemma":[0.3176241,0.001298517,0.6705414,0.003520019,0.001274243,0.003593142,0.0005522254,0.0005540527,0.001042271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4808789,"threshold_uncertainty_score":0.5930094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7559799505273994,"score_gpt":0.6478034277877435,"score_spread":0.1081765227396559,"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."}}