{"id":"W2322140854","doi":"10.1016/j.jclinepi.2016.03.018","title":"Interpreting GRADE's levels of certainty or quality of the evidence: GRADE for statisticians, considering review information size or less emphasis on imprecision?","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University; Health Sciences Centre","funders":"","keywords":"Certainty; Grading (engineering); Systematic review; Guideline; Psychology; Quality (philosophy); Actuarial science; Management science; MEDLINE; Medicine; Epistemology; Economics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5928518,0.004138413,0.02597659,0.02592351,0.00290474,0.0159167,0.01206253,0.01628304,0.004538869],"category_scores_gemma":[0.8926945,0.004430708,0.02463839,0.01519533,0.01213398,0.01301619,0.00827143,0.0251064,0.001350036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007156287,"about_ca_system_score_gemma":0.01135282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009684548,"about_ca_topic_score_gemma":0.00937885,"domain_scores_codex":[0.3371265,0.4251465,0.1760756,0.01938237,0.04050365,0.001765318],"domain_scores_gemma":[0.09434861,0.7760399,0.05725915,0.03125582,0.03807176,0.003024755],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01259942,0.0003526801,0.03133644,0.2483091,0.1669751,0.0009063403,0.008762976,0.005615576,0.001727798,0.04886489,0.1418495,0.3327003],"study_design_scores_gemma":[0.01512232,0.003947512,0.02835289,0.1906918,0.1799578,0.003332824,0.004375285,0.03214702,0.004671582,0.3760412,0.1573807,0.003978989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.01998186,0.4352262,0.2728546,0.1899973,0.05349548,0.007558334,0.00796602,0.002203419,0.01071676],"genre_scores_gemma":[0.3896676,0.04656889,0.4528523,0.07283819,0.02070381,0.01232014,0.00237062,0.001112123,0.001566296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4071482,"threshold_uncertainty_score":0.5020863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9591089740372083,"score_gpt":0.7215801648802531,"score_spread":0.2375288091569552,"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."}}