{"id":"W2171240927","doi":"10.1017/s1481803500007260","title":"Development, implementation and reliability assessment of an emergency physician performance evaluation tool","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Emergency Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Providence Health Care","funders":"","keywords":"Emergency department; Reliability (semiconductor); Medicine; Emergency physician; Test (biology); Family medicine; Nursing","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":[0.08782002,0.0008767362,0.001023101,0.003568348,0.001315337,0.002479934,0.002208656,0.001151646,0.001065382],"category_scores_gemma":[0.157492,0.0009997698,0.001466501,0.00186153,0.0008744506,0.002205833,0.002370276,0.001875972,0.0006002774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002400326,"about_ca_system_score_gemma":0.009543047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004096414,"about_ca_topic_score_gemma":0.004194588,"domain_scores_codex":[0.9330107,0.03537159,0.01152559,0.002599295,0.01614482,0.001348143],"domain_scores_gemma":[0.7721022,0.1204686,0.01101611,0.01273389,0.08072812,0.002951058],"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":[0.002589989,0.0107867,0.3185314,0.0007555737,0.0003955208,0.0002551649,0.006490421,0.003902936,0.01149407,0.001590393,0.005578865,0.6376289],"study_design_scores_gemma":[0.002455757,0.02353731,0.7979164,0.001000144,0.001176666,0.001139933,0.005639461,0.0929184,0.04928856,0.001881335,0.02261548,0.0004306457],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7994649,0.0004300068,0.162219,0.001464427,0.0004541218,0.0276413,0.0008624443,0.001743495,0.005720185],"genre_scores_gemma":[0.6252822,0.0002371413,0.3576988,0.0003484094,0.0001052232,0.01291733,0.00142606,0.000235231,0.001749536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9121799,"threshold_uncertainty_score":0.4644423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06895638828832289,"score_gpt":0.440788674023625,"score_spread":0.3718322857353021,"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."}}