{"id":"W4388180784","doi":"10.1016/j.jclinepi.2023.10.005","title":"GRADE guidance 37: rating imprecision in a body of evidence on test accuracy","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Certainty; Test (biology); Grading (engineering); Sample size determination; Rating scale; Statistics; Sample (material); Computer science; Confidence interval; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2587964,0.004365397,0.01196177,0.03563461,0.003899497,0.01938218,0.02041687,0.01876192,0.04252231],"category_scores_gemma":[0.7189426,0.005612631,0.0251626,0.01969921,0.006182947,0.01081689,0.01315806,0.02163688,0.02547486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01974135,"about_ca_system_score_gemma":0.05183514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.029808,"about_ca_topic_score_gemma":0.02152315,"domain_scores_codex":[0.4778402,0.2491661,0.1432968,0.00902413,0.1164395,0.004233284],"domain_scores_gemma":[0.2160346,0.4190676,0.05965903,0.02167958,0.278097,0.005462156],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001070907,0.0001136553,0.002130844,0.1125382,0.003133534,0.0002357417,0.001753488,0.001950709,0.0006806101,0.02642036,0.6478879,0.2020841],"study_design_scores_gemma":[0.001975484,0.0004712293,0.004887333,0.2459259,0.005769376,0.0008157908,0.0008582269,0.003223388,0.001607351,0.03781889,0.6959065,0.000740548],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003845834,0.1874448,0.3115149,0.1191431,0.0453221,0.09544121,0.07439592,0.0108232,0.152069],"genre_scores_gemma":[0.03718314,0.1075997,0.6626801,0.03053981,0.004856566,0.1066132,0.0299468,0.004135437,0.01644524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7412037,"threshold_uncertainty_score":0.914036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9563425643518924,"score_gpt":0.7288577227698326,"score_spread":0.2274848415820597,"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."}}