{"id":"W2315260934","doi":"10.1080/10401334.2016.1146608","title":"Using Automatic Item Generation to Improve the Quality of MCQ Distractors","year":2016,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Medical Council of Canada; University of Alberta","funders":"","keywords":"Test (biology); Computer science; Item bank; Quality (philosophy); Process (computing); Field (mathematics); Construct (python library); Multiple choice; Item response theory; Cognition; Applied psychology; Psychology; Psychometrics; Clinical psychology; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05268605,0.001850414,0.001143406,0.004118999,0.0007807636,0.001906304,0.002745517,0.00119867,0.004840648],"category_scores_gemma":[0.2472918,0.0006836294,0.0008980651,0.002823759,0.001196159,0.00183233,0.002625359,0.001302839,0.002487073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001107139,"about_ca_system_score_gemma":0.001544112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001022936,"about_ca_topic_score_gemma":0.001641735,"domain_scores_codex":[0.9527334,0.03348096,0.00346082,0.002840307,0.007016127,0.0004684435],"domain_scores_gemma":[0.5839249,0.3034526,0.01974368,0.03998945,0.05198971,0.0008996883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001416979,0.0009124599,0.05924514,0.001172563,0.0001915369,0.000257183,0.003064697,0.005939142,0.01899812,0.001371696,0.004861325,0.9025692],"study_design_scores_gemma":[0.002081795,0.008403296,0.237198,0.002525823,0.0009335843,0.003983918,0.002909256,0.4383803,0.2374221,0.01374589,0.05165948,0.0007565438],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2461615,0.0009895073,0.7348295,0.0008838655,0.0002135135,0.005578467,0.0006336145,0.006909456,0.003800547],"genre_scores_gemma":[0.340771,0.0001780017,0.6541241,0.0003456156,0.00007735874,0.002373317,0.0006708978,0.0005679681,0.0008917656],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05268605,"threshold_uncertainty_score":0.2786338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5912255297888322,"score_gpt":0.5498694737714378,"score_spread":0.04135605601739445,"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."}}