{"id":"W4410335814","doi":"10.1136/bmj-2024-083864","title":"Core GRADE 4: rating certainty of evidence—risk of bias, publication bias, and reasons for rating up certainty","year":2025,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Certainty; Rating system; Publication bias; Computer science; Medicine; Actuarial science; Information retrieval; Business; Mathematics; Meta-analysis; Internal medicine; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2791581,0.002985766,0.01132378,0.02348137,0.002785302,0.01295956,0.006960983,0.008010263,0.01507419],"category_scores_gemma":[0.7004082,0.002590413,0.01999334,0.01315279,0.004375329,0.00705571,0.0100443,0.01157629,0.003964422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01019696,"about_ca_system_score_gemma":0.01529301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005961159,"about_ca_topic_score_gemma":0.006026146,"domain_scores_codex":[0.4837122,0.2153858,0.2175797,0.007047097,0.07345372,0.002821489],"domain_scores_gemma":[0.2611338,0.4922599,0.09691964,0.02633239,0.1180938,0.005260474],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003952014,0.0001587201,0.01166548,0.3633825,0.02077612,0.0003973502,0.003005774,0.002696232,0.001076681,0.02136561,0.2007564,0.3707672],"study_design_scores_gemma":[0.005412926,0.001356398,0.01931121,0.3443218,0.02988509,0.002760211,0.00267889,0.01701439,0.003842687,0.1310175,0.4402798,0.002119112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01526366,0.26504,0.3619451,0.07358716,0.03857708,0.1309671,0.04680708,0.005412275,0.06240074],"genre_scores_gemma":[0.1624998,0.07883672,0.5723968,0.01672072,0.006037348,0.140149,0.01415983,0.002167806,0.007031994],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7208419,"threshold_uncertainty_score":0.8889264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9061735351014505,"score_gpt":0.5893847595293616,"score_spread":0.3167887755720888,"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."}}