{"id":"W2290537467","doi":"10.1002/j.0022-0337.2016.80.3.tb06090.x","title":"Three Modeling Applications to Promote Automatic Item Generation for Examinations in Dentistry","year":2016,"lang":"en","type":"article","venue":"Journal of Dental Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Test (biology); Item bank; Cognition; Domain (mathematical analysis); Item response theory; Information retrieval; Artificial intelligence; Psychology; Psychometrics; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01613286,0.002190168,0.0007316194,0.004398033,0.0009235849,0.002403026,0.001800476,0.001490006,0.004692456],"category_scores_gemma":[0.06699918,0.001541486,0.001780587,0.002761731,0.0008078838,0.001906694,0.00295674,0.00155434,0.001390502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001697476,"about_ca_system_score_gemma":0.001988649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002167689,"about_ca_topic_score_gemma":0.004051283,"domain_scores_codex":[0.9885992,0.007699834,0.0008168895,0.0008748297,0.001788613,0.0002206467],"domain_scores_gemma":[0.9388635,0.04598346,0.002149421,0.007307588,0.005192947,0.0005031399],"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":[0.0007201944,0.0007902931,0.01630605,0.0006247203,0.0002153484,0.0004169191,0.005532193,0.02489303,0.01807399,0.02034848,0.005590085,0.9064888],"study_design_scores_gemma":[0.0005476491,0.001030342,0.01482253,0.0006379597,0.0003641279,0.001221932,0.00113582,0.8320386,0.05500918,0.0450303,0.04780957,0.0003520035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01735216,0.00006315952,0.9726357,0.0003280805,0.00002947129,0.001233913,0.0001783367,0.00666068,0.001518494],"genre_scores_gemma":[0.03845617,0.00004479007,0.9592643,0.00004492423,0.000007889633,0.00129056,0.0001831417,0.0002141021,0.0004940129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01613286,"threshold_uncertainty_score":0.08531976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05606173401711519,"score_gpt":0.4016301752193924,"score_spread":0.3455684412022772,"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."}}