{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1205838,0.001328493,0.002568247,0.003694966,0.002000003,0.004804449,0.004154099,0.002510859,0.004592695],"category_scores_gemma":[0.344669,0.001567987,0.001468918,0.004509666,0.003775927,0.007659061,0.004362927,0.005024324,0.001725583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001821977,"about_ca_system_score_gemma":0.003676847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001217264,"about_ca_topic_score_gemma":0.00291181,"domain_scores_codex":[0.8675611,0.1028111,0.008679184,0.005865356,0.01422164,0.0008615721],"domain_scores_gemma":[0.5462509,0.377213,0.01128881,0.03231017,0.03174787,0.001189263],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001253855,0.002540262,0.1273093,0.001857127,0.0009977729,0.0001696666,0.02595535,0.004233758,0.005114103,0.0786386,0.01414674,0.7377834],"study_design_scores_gemma":[0.0008451719,0.002424047,0.3683079,0.003310511,0.001090447,0.001188417,0.02218657,0.143282,0.02921431,0.3814858,0.04591304,0.0007517125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2102111,0.0007243236,0.7665388,0.003918817,0.0003672308,0.004271275,0.0006967041,0.001507663,0.01176416],"genre_scores_gemma":[0.4234112,0.0002282384,0.56677,0.0006934299,0.00009082524,0.005673639,0.0004049178,0.0002988307,0.002429032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8794162,"threshold_uncertainty_score":0.6377155,"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."}}