{"id":"W2148707490","doi":"10.1186/1472-6920-12-121","title":"Temporal stability of objective structured clinical exams: a longitudinal study employing item response theory","year":2012,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Generalizability theory; Objective structured clinical examination; Internal consistency; Competence (human resources); Reliability (semiconductor); Educational measurement; Consistency (knowledge bases); Psychology; Medicine; Medical education; Psychometrics; Statistics; Clinical psychology; Computer science; Mathematics; Social psychology; Developmental psychology; Curriculum; Artificial intelligence; Pedagogy","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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1035169,0.0001661316,0.0005716063,0.0003890398,0.0001392298,0.00005014435,0.0007803084,0.0001960447,0.001678036],"category_scores_gemma":[0.8037912,0.0001104773,0.0001749152,0.001793061,0.0003560031,0.0003033459,0.0002214895,0.0004074463,0.0000208383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008580535,"about_ca_system_score_gemma":0.002496725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001348154,"about_ca_topic_score_gemma":0.00007912155,"domain_scores_codex":[0.980445,0.01437155,0.001768961,0.0006221848,0.002419468,0.0003728297],"domain_scores_gemma":[0.6673352,0.3273461,0.001526907,0.001794072,0.0009749244,0.001022825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008362519,0.001207664,0.8862678,0.000008928533,0.00001703186,4.234479e-7,0.002317308,2.525456e-7,0.00000810097,0.0003409238,0.0003583614,0.108637],"study_design_scores_gemma":[0.0004733184,0.0003090175,0.961052,0.00002857221,0.00002336454,0.00000913865,0.02682257,0.00004794245,0.00002927928,0.01098333,0.0001118774,0.0001095928],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744554,0.0003676484,0.02061552,0.0001042875,0.003467131,0.0004734516,0.00000339067,0.00004146072,0.0004717085],"genre_scores_gemma":[0.9841602,0.000003147237,0.01506896,0.00009992248,0.0005510695,0.000032467,0.000002150512,0.00001005998,0.00007204556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7002743,"threshold_uncertainty_score":0.9992346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.664638114578315,"score_gpt":0.5950031946609595,"score_spread":0.06963491991735549,"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."}}