{"id":"W4410109395","doi":"10.1136/bmj-2024-081905","title":"Core GRADE 3: rating certainty of evidence—assessing inconsistency","year":2025,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Certainty; Computer science; Rating system; Information retrieval; Medicine; Data science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2012253,0.002979732,0.00993306,0.02618792,0.00266359,0.01032716,0.008143017,0.006363498,0.02418605],"category_scores_gemma":[0.6248022,0.002587043,0.02277438,0.01359199,0.00347079,0.007429803,0.009916488,0.009853386,0.004956981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008662282,"about_ca_system_score_gemma":0.01553556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007598879,"about_ca_topic_score_gemma":0.008908912,"domain_scores_codex":[0.6556277,0.1337046,0.1439025,0.006504796,0.05799967,0.002260651],"domain_scores_gemma":[0.3752043,0.4079768,0.07075755,0.0243676,0.1168405,0.004853304],"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":[0.004698802,0.000195933,0.01272466,0.3325533,0.0253418,0.0004251034,0.002495992,0.003509179,0.001014169,0.02002022,0.2384156,0.3586051],"study_design_scores_gemma":[0.006422404,0.001803552,0.02446651,0.2525372,0.04172729,0.003076089,0.002559054,0.0154622,0.004192891,0.1213974,0.5241899,0.00216543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01757474,0.2050341,0.3801777,0.04645519,0.02663572,0.1488579,0.07850465,0.007882631,0.08887738],"genre_scores_gemma":[0.1601759,0.07107125,0.5648748,0.01447824,0.003705786,0.1505542,0.02422961,0.002952531,0.007957779],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7987747,"threshold_uncertainty_score":0.9850314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.942893232330549,"score_gpt":0.6512890240102821,"score_spread":0.2916042083202669,"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."}}