{"id":"W4366386744","doi":"10.1136/bmjebm-2022-112111","title":"Rapid reviews methods series: Guidance on assessing the certainty of evidence","year":2023,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"Public Health Agency","keywords":"Grading (engineering); Systematic review; Computer science; Rating system; Certainty; Management science; Medicine; Actuarial science; MEDLINE; Engineering; Mathematics; Business; Political science","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":"not_applicable","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":"not_applicable","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","insufficient_payload"],"category_scores_codex":[0.5669478,0.0005660722,0.005928846,0.0007524002,0.0003408121,0.0003460063,0.003960373,0.0001704124,0.009986703],"category_scores_gemma":[0.7011788,0.0001853313,0.001808796,0.007838656,0.0006458579,0.0007350892,0.0002056498,0.0005176863,0.002264584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009005307,"about_ca_system_score_gemma":0.0004389672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005547887,"about_ca_topic_score_gemma":0.00001238749,"domain_scores_codex":[0.881878,0.08236209,0.02071065,0.002047578,0.01226977,0.0007318844],"domain_scores_gemma":[0.7892361,0.1769673,0.01677387,0.01309238,0.003497257,0.0004330639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005273949,0.00002156759,0.003209366,0.0007753078,0.00008857375,0.00002065081,0.0006504897,0.000473132,0.00250013,0.0009153329,0.6121005,0.3791922],"study_design_scores_gemma":[0.0003842938,0.0006628396,0.01737933,0.03232053,0.000745789,0.00002351068,0.002297088,0.01545462,0.001448854,0.004735726,0.9241154,0.000432001],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.00785054,0.1790927,0.3232855,0.4683611,0.004029092,0.01049595,0.00001284842,0.0001112488,0.006761008],"genre_scores_gemma":[0.3598139,0.07536746,0.3703447,0.0829935,0.007066392,0.004559278,0.00004340591,0.0002873362,0.09952403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3853676,"threshold_uncertainty_score":0.9985123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9546345879208633,"score_gpt":0.6949051985894442,"score_spread":0.2597293893314191,"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."}}