{"id":"W2123930017","doi":"10.1111/j.1365-2923.2009.03438.x","title":"The effect of differential rater function over time (DRIFT) on objective structured clinical examination ratings","year":2009,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Summative assessment; Formative assessment; Confidence interval; Psychology; Differential (mechanical device); Objective structured clinical examination; Function (biology); Statistics; Medicine; Mathematics; Psychiatry; Engineering","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":[],"category_scores_codex":[0.002082426,0.0001928881,0.0003440826,0.0001698429,0.0001939203,0.00002790921,0.0001519142,0.0003425966,0.001012383],"category_scores_gemma":[0.01156859,0.0001186359,0.0001232461,0.0004785927,0.00025255,0.00009782561,0.0000162069,0.0006790827,0.000063933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001812988,"about_ca_system_score_gemma":0.0006806405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008986315,"about_ca_topic_score_gemma":0.000001511867,"domain_scores_codex":[0.9970022,0.0005105842,0.0007832783,0.0003373113,0.001139448,0.0002271493],"domain_scores_gemma":[0.9982905,0.0005289828,0.0003276762,0.0004089176,0.0003454685,0.0000984044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007205709,0.0005524865,0.00573063,0.00004166424,0.00005238459,6.203582e-7,0.0002394248,6.586062e-7,0.001401719,0.0008125823,0.05427067,0.9361766],"study_design_scores_gemma":[0.002287524,0.003977402,0.9811811,0.0003004188,0.0001941227,0.00001445313,0.00009307846,0.002397757,0.003681516,0.0004091957,0.005317201,0.00014621],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873574,0.00004546832,0.0007108035,0.006268797,0.003103955,0.000767217,9.1843e-7,0.00005543268,0.001689964],"genre_scores_gemma":[0.9925745,0.00001743866,0.0001179972,0.004330115,0.00154102,0.00006050566,0.0002237325,0.00001675809,0.001117994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9754505,"threshold_uncertainty_score":0.9999008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004772557387152924,"score_gpt":0.3426991420525827,"score_spread":0.3379265846654297,"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."}}