{"id":"W2091307601","doi":"10.1111/j.1743-498x.2012.00607.x","title":"A method for identifying extreme OSCE examiners","year":2013,"lang":"en","type":"article","venue":"The Clinical Teacher","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Psychology; Cohort; Applied psychology; Standard deviation; Quality assurance; Inter-rater reliability; Objective structured clinical examination; Statistics; Computer science; Medicine; Rating scale; Mathematics; Developmental 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0300862,0.001701311,0.0009736946,0.008257353,0.001858803,0.002759158,0.002569665,0.002152946,0.01962399],"category_scores_gemma":[0.1031909,0.001178675,0.001154452,0.004203912,0.001535731,0.0016351,0.003791877,0.002011776,0.009810215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063055,"about_ca_system_score_gemma":0.00352713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001534211,"about_ca_topic_score_gemma":0.003502536,"domain_scores_codex":[0.9568449,0.01503063,0.0065461,0.007041698,0.01365414,0.0008826332],"domain_scores_gemma":[0.881077,0.04892347,0.01136827,0.0153467,0.04172745,0.001557079],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001391658,0.0004390139,0.03469344,0.001190921,0.0001770538,0.0004941524,0.003197141,0.001814837,0.02645583,0.01339662,0.03406093,0.8826884],"study_design_scores_gemma":[0.002269547,0.003326448,0.1810708,0.00264129,0.001029135,0.01157655,0.006284677,0.1628789,0.1121142,0.05299463,0.4621607,0.001653009],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01575686,0.000175672,0.9646878,0.000424616,0.0004625721,0.005779516,0.001293636,0.003580104,0.007839248],"genre_scores_gemma":[0.02605966,0.00007137284,0.9624862,0.0001760158,0.00008071715,0.006549834,0.0005485751,0.0003038898,0.003723845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9699138,"threshold_uncertainty_score":0.1591129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.753723718068258,"score_gpt":0.5667969616218294,"score_spread":0.1869267564464286,"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."}}