{"id":"W2262777419","doi":"10.3352/jeehp.2016.13.6","title":"Calibrating the Medical Council of Canada’s Qualifying Examination Part I using an integrated item response theory framework: a comparison of models and designs","year":2016,"lang":"en","type":"article","venue":"Journal of Educational Evaluation for Health Professions","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Polytomous Rasch model; Item response theory; Calibration; Statistics; Set (abstract data type); Test (biology); Computer science; Type I and type II errors; Econometrics; Multiple choice; Psychology; Mathematics; Significant difference; Psychometrics; Programming language","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":[0.1427901,0.00009618183,0.0004048758,0.000231009,0.0005184228,0.00002390706,0.0003861212,0.0001065562,0.0002606368],"category_scores_gemma":[0.5221431,0.00004733292,0.00005595945,0.00070691,0.0001326739,0.0003873337,0.00004021937,0.0002443042,7.739854e-8],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007136277,"about_ca_system_score_gemma":0.04438976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001025505,"about_ca_topic_score_gemma":0.002235562,"domain_scores_codex":[0.9818676,0.01122417,0.002383324,0.0002017283,0.00410068,0.0002225563],"domain_scores_gemma":[0.674095,0.3098079,0.00600661,0.0003969487,0.009329663,0.000363798],"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":[0.003576893,0.001541402,0.04949702,0.000303457,0.0002057733,4.992464e-7,0.07685661,0.02113978,0.00223407,0.07484759,0.01813458,0.7516623],"study_design_scores_gemma":[0.001476082,0.0007535015,0.08482438,0.003052074,0.00007378865,0.00003660316,0.07649538,0.4724783,0.00017733,0.3594216,0.001025222,0.0001857546],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5656958,0.0006908517,0.4087528,0.02345448,0.0009149691,0.0004218635,0.00002940799,0.000001980658,0.00003787065],"genre_scores_gemma":[0.951415,0.00001586673,0.04803224,0.0002993594,0.0001278313,0.0000165629,0.000001977556,0.000006640643,0.0000845068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7514766,"threshold_uncertainty_score":0.9610277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8970046108208954,"score_gpt":0.6521780930522075,"score_spread":0.2448265177686879,"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."}}