{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.04226877,0.0001433488,0.0003594992,0.00004452072,0.0002072733,0.0003245642,0.001379488,0.0001187771,0.003085907],"category_scores_gemma":[0.01741883,0.00007031157,0.0004220457,0.0002642553,0.00019373,0.0002230991,0.0002038992,0.0003340106,0.001920563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003009092,"about_ca_system_score_gemma":0.00003772812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008466822,"about_ca_topic_score_gemma":0.00001738311,"domain_scores_codex":[0.9948904,0.001652563,0.001352339,0.0005907789,0.001187801,0.0003261382],"domain_scores_gemma":[0.9864279,0.01151136,0.0003370123,0.001200675,0.0003734171,0.0001496188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003966103,0.0003785827,0.02179337,0.000007106759,0.00006579011,4.332457e-7,0.0005409369,0.00004188346,0.001271131,0.0009599559,0.3262363,0.6486648],"study_design_scores_gemma":[0.001247757,0.000250597,0.1578628,0.00003261921,0.00008037842,0.000001770869,0.002322701,0.01406492,0.0001876784,0.3759171,0.4476895,0.0003421009],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4332545,0.000288938,0.4985467,0.04424181,0.002091902,0.00280295,0.000005005877,0.0001454735,0.01862262],"genre_scores_gemma":[0.7491208,0.00002978513,0.1291483,0.005772831,0.001484296,0.0004911034,0.000002826453,0.00003785951,0.1139122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6483228,"threshold_uncertainty_score":0.9988565,"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."}}