{"id":"W3010352759","doi":"10.1016/j.jclinepi.2020.01.026","title":"Guideline developers in the United States were inconsistent in applying criteria for appropriate Grading of Recommendations, Assessment, Development and Evaluation use","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Clinical practice guidelines implementation","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Guideline; Grading (engineering); Medicine; Certainty; Family medicine; MEDLINE; Evidence-based medicine; Actuarial science; Alternative medicine; Political science; Pathology; Business; Engineering; Mathematics","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08343998,0.0001328834,0.001343014,0.0002309741,0.00004021465,0.00001121037,0.0001319806,0.0001487656,0.00003129003],"category_scores_gemma":[0.2033437,0.00009007043,0.0001518392,0.0002712071,0.00009029059,0.0002073451,0.00005850523,0.0006940364,4.48186e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037736,"about_ca_system_score_gemma":0.0007287228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001086786,"about_ca_topic_score_gemma":0.0001145675,"domain_scores_codex":[0.982784,0.005651936,0.01078741,0.0002652474,0.0002883598,0.0002229993],"domain_scores_gemma":[0.9255963,0.06840535,0.004666317,0.0001646044,0.0009825455,0.0001849127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00205031,0.0004267005,0.7252236,0.0001768625,0.0002304221,0.00001229484,0.001143292,0.00148735,0.0001063144,0.0004573343,0.008233767,0.2604517],"study_design_scores_gemma":[0.01431122,0.001647831,0.6462986,0.0004909669,0.000438837,0.00007517759,0.008914749,0.2258871,0.00002843161,0.004742573,0.09696199,0.0002025042],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8234761,0.00007592385,0.03547913,0.1397555,0.0002348408,0.0009590128,0.000006845553,0.000003378248,0.000009185875],"genre_scores_gemma":[0.6256011,0.0006953991,0.3513726,0.02185068,0.0001900188,0.00004395905,0.0002336065,0.00001137061,0.000001247281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3158935,"threshold_uncertainty_score":0.9437914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7909520812482255,"score_gpt":0.6593998138296027,"score_spread":0.1315522674186228,"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."}}