{"id":"W4376106412","doi":"10.1016/j.ajpe.2023.100081","title":"Using Automatic Item Generation to Create Multiple-Choice Questions for Pharmacy Assessment","year":2023,"lang":"en","type":"article","venue":"American Journal of Pharmaceutical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Item bank; Pharmacy; Summative assessment; Multiple choice; Quality (philosophy); Computer science; Test (biology); Sample (material); Medical education; Scope (computer science); Worksheet; Set (abstract data type); Item response theory; Medicine; Formative assessment; Psychometrics; Psychology; Family medicine; Mathematics education; Clinical psychology","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"],"consensus_categories":[],"category_scores_codex":[0.006331572,0.0001457298,0.0003892645,0.001179584,0.0002492962,0.0002220801,0.0004738149,0.0000221434,0.0001167916],"category_scores_gemma":[0.1035714,0.0001144038,0.0001687138,0.003901522,0.00008994763,0.0003705342,0.00005861048,0.0002202502,0.00002598041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002167727,"about_ca_system_score_gemma":0.000772376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007029428,"about_ca_topic_score_gemma":0.000002249347,"domain_scores_codex":[0.9966643,0.0007290727,0.001099973,0.0002979808,0.0008788313,0.0003298653],"domain_scores_gemma":[0.9636298,0.03352683,0.0009465383,0.0002466689,0.001196642,0.0004535215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002895199,0.0001661038,0.05408727,0.000008550842,0.00003927566,0.000001456217,0.0002749328,0.004272552,0.02893939,0.0001398129,0.007029419,0.9050123],"study_design_scores_gemma":[0.0008063465,0.0003651513,0.1188309,0.00006882977,0.0001399161,0.00008357951,0.002363187,0.8318982,0.001764166,0.001378726,0.04205838,0.0002426018],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7884627,0.00006361169,0.2043434,0.004362909,0.002305236,0.0003027219,0.000007895667,0.00004027291,0.0001112313],"genre_scores_gemma":[0.789865,0.00003015797,0.208098,0.000971436,0.0009030456,0.00002701866,0.000003548706,0.00001517233,0.00008661481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9047697,"threshold_uncertainty_score":0.9039795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7467467061115505,"score_gpt":0.6691299934978945,"score_spread":0.07761671261365599,"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."}}