{"id":"W2138928670","doi":"10.1177/0163278711425041","title":"A Comparison of Empirical Ranking Methods of Frequency and Severity Ratings of Clinical Presentations","year":2011,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; University of Calgary","funders":"","keywords":"Ranking (information retrieval); Statistics; Psychology; Medicine; MEDLINE; Econometrics; Clinical psychology; Computer science; Mathematics; Artificial intelligence; Biology","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":[0.1339853,0.0009208838,0.001004389,0.008798724,0.0007608257,0.002537142,0.001487013,0.0009215035,0.001925091],"category_scores_gemma":[0.4594454,0.0005082301,0.001442089,0.005370594,0.001961663,0.003054311,0.001891011,0.001047535,0.0005414248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001798116,"about_ca_system_score_gemma":0.001531363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002538118,"about_ca_topic_score_gemma":0.003240976,"domain_scores_codex":[0.7082744,0.2413931,0.01008902,0.005163827,0.03414984,0.0009298501],"domain_scores_gemma":[0.2634552,0.6761554,0.01767633,0.0145937,0.02751908,0.0006003421],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002515369,0.0009047591,0.4703291,0.002223912,0.003196855,0.0001294375,0.01196427,0.01281728,0.001289702,0.01529926,0.004441934,0.4748882],"study_design_scores_gemma":[0.00122013,0.006131861,0.6722809,0.002082192,0.0009824446,0.001137578,0.01997704,0.2454786,0.004559177,0.03264409,0.01262779,0.0008782769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6435356,0.004562436,0.3306856,0.001084915,0.0005143899,0.001788466,0.001091206,0.0005933652,0.01614407],"genre_scores_gemma":[0.9085012,0.0006964726,0.08849127,0.00009762553,0.0001231317,0.0008071265,0.0004901586,0.00007305875,0.0007199694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8660147,"threshold_uncertainty_score":0.7085904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.893414992052289,"score_gpt":0.7377671514789872,"score_spread":0.1556478405733018,"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."}}