{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04211424,0.00008417641,0.00030798,0.0002632119,0.0002450813,0.00002712571,0.0002312947,0.00003957217,0.00004623717],"category_scores_gemma":[0.3835528,0.00003441628,0.00002531928,0.0004721742,0.0001052996,0.00008161987,0.00006417088,0.0003806615,0.000001831378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002670274,"about_ca_system_score_gemma":0.00001619942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007598299,"about_ca_topic_score_gemma":0.00001589773,"domain_scores_codex":[0.9953025,0.002961829,0.0007129223,0.0002665562,0.0005982818,0.0001578867],"domain_scores_gemma":[0.9537168,0.04551022,0.0003916947,0.0002650598,0.0000580968,0.00005808776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000006014888,0.000008289615,0.1778515,0.000006991746,0.000003663602,5.304261e-7,0.003271273,0.0001579135,0.06005569,0.000242098,0.000175814,0.7582202],"study_design_scores_gemma":[0.0006324736,0.0002567199,0.9535796,0.00028946,0.00001082956,0.000006568889,0.006206157,0.03528107,0.0001572116,0.001366316,0.002084066,0.000129516],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9193488,0.0001114537,0.07720145,0.002407549,0.0002838825,0.000082576,5.087986e-7,0.00002625974,0.0005374884],"genre_scores_gemma":[0.9879853,0.000003938508,0.01136533,0.0001117643,0.0001811251,0.000001783463,2.684932e-7,0.000004703465,0.0003457693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7757281,"threshold_uncertainty_score":0.986345,"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."}}