{"id":"W2999637266","doi":"10.21315/eimj2019.11.4.1","title":"Simplified Guidelines for Multiple-Choice Question Writing to Increase Faculty Compliance and Ensure Valid Student Results","year":2019,"lang":"en","type":"article","venue":"Education in Medicine Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Quality (philosophy); Asset (computer security); Multiple choice; Compliance (psychology); Guideline; Point (geometry); Information retrieval; Medical education; Mathematics education; Medicine; Psychology; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003383993,0.0001935413,0.0004024384,0.0005189441,0.0001580718,0.00003983941,0.0001447611,0.0001160692,0.0001104655],"category_scores_gemma":[0.03542571,0.0001592196,0.00003727625,0.0005422704,0.00006254599,0.0001623402,0.00002987859,0.0005251123,0.00001873253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003719052,"about_ca_system_score_gemma":0.0007082807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002068206,"about_ca_topic_score_gemma":0.00002721231,"domain_scores_codex":[0.9973185,0.0001015458,0.001315295,0.0003556734,0.0006186135,0.0002903573],"domain_scores_gemma":[0.9955871,0.0006234322,0.0004194953,0.000296172,0.002805174,0.0002685945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0004446261,0.0004859367,0.3777942,0.0003263636,0.0000373556,0.000001686407,0.003182817,0.0001127249,0.003246535,0.0003365275,0.5401511,0.07388015],"study_design_scores_gemma":[0.006121996,0.0005354865,0.8266978,0.003675853,0.00007355458,0.0003034169,0.01180652,0.00126204,0.00007510299,0.0002748608,0.1489718,0.0002016756],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9136741,0.0003034208,0.002876906,0.07823425,0.002572382,0.001338306,0.000009326984,0.00002997655,0.000961325],"genre_scores_gemma":[0.9026195,0.00009927691,0.07224774,0.01382246,0.006298943,0.0001553055,0.0004205378,0.00004290252,0.004293367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4489036,"threshold_uncertainty_score":0.9726993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1567674210767465,"score_gpt":0.5293930246191422,"score_spread":0.3726256035423957,"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."}}