{"id":"W2994295740","doi":"10.1097/acm.0000000000003096","title":"Multiple Choice Questions in a Nutshell: Theory, Practice, and Postexam Item Analysis","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Linguistic research and analysis","field":"Arts and Humanities","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"MEDLINE; Item response theory; Psychology; Psychometrics; Clinical psychology; Political science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001472008,0.000135154,0.0003882933,0.0005793397,0.0001048323,0.00003171441,0.0001905463,0.00007855894,0.002833386],"category_scores_gemma":[0.01256961,0.00009429096,0.00005226049,0.0003411382,0.0002878482,0.0001998627,0.00006012942,0.0005749116,0.0001123542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003223887,"about_ca_system_score_gemma":0.0000398989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004025632,"about_ca_topic_score_gemma":0.001333324,"domain_scores_codex":[0.9984286,0.0002351387,0.0003892543,0.0003016374,0.0003588608,0.000286493],"domain_scores_gemma":[0.9947091,0.004597838,0.000127681,0.0002454073,0.0001688713,0.0001511047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001478914,0.0000527781,0.4072776,0.0001194896,0.001280692,0.00003855238,0.09139632,0.00002064527,0.0002920924,0.4914885,0.004833008,0.003052528],"study_design_scores_gemma":[0.003323348,0.0004019063,0.03300619,0.0004338366,0.002524606,0.00001244744,0.05703015,0.01201562,0.00001944862,0.03313834,0.8575649,0.0005292024],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8511192,0.005934056,0.0001591715,0.0111279,0.0003666205,0.0005134557,0.00002565831,0.00008690946,0.130667],"genre_scores_gemma":[0.9742694,0.0008956037,0.00002196515,0.001195714,0.0008750606,0.0000138953,0.00003873769,0.00001122378,0.02267836],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8527319,"threshold_uncertainty_score":0.9980782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02970922156502332,"score_gpt":0.3319677149104039,"score_spread":0.3022584933453806,"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."}}