{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5788688,0.000264211,0.01218411,0.0001546945,0.00007910374,0.00003274429,0.002019454,0.000230539,0.00197236],"category_scores_gemma":[0.9765955,0.00007471815,0.004672891,0.0005220926,0.0003883357,0.0004531388,0.0001838665,0.0003946295,0.00002688043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004521907,"about_ca_system_score_gemma":0.0004999209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001587113,"about_ca_topic_score_gemma":0.00003720784,"domain_scores_codex":[0.7647042,0.1340588,0.0963514,0.0006938799,0.003714233,0.0004774763],"domain_scores_gemma":[0.1053199,0.8136297,0.07533126,0.002004087,0.003489361,0.0002256842],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001421203,0.0001667902,0.1101366,0.002073432,0.0007464418,0.000002293255,0.0002599317,0.0001180856,0.00009271824,0.007280022,0.07479164,0.8029108],"study_design_scores_gemma":[0.004430236,0.004281042,0.6273815,0.05742972,0.002121696,0.0001734203,0.001866991,0.002928906,0.0002242034,0.2110396,0.08744843,0.0006742526],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2422038,0.005150465,0.6721424,0.07494522,0.002915331,0.002204981,0.0003081776,0.000003952121,0.0001256571],"genre_scores_gemma":[0.9387789,0.005623503,0.04754533,0.007508301,0.0001843973,0.00001735283,3.914453e-7,0.000009476757,0.0003323648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8022366,"threshold_uncertainty_score":0.99894,"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."}}