{"id":"W2131621623","doi":"10.1136/ebm0005","title":"Making GRADE accessible: a proposal for graphic display of evidence quality assessments","year":2011,"lang":"en","type":"article","venue":"Evidence-Based Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Grading (engineering); Outlier; Computer science; Quality of evidence; Quality (philosophy); Identification (biology); Information retrieval; Data mining; Artificial intelligence; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","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":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1905689,0.0004691556,0.004269008,0.0008409335,0.0001925632,0.0001763547,0.003287783,0.0001343853,0.006146297],"category_scores_gemma":[0.1700744,0.0001923479,0.001401664,0.003013141,0.000470997,0.001201875,0.0001452114,0.0002348117,0.000109517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005904537,"about_ca_system_score_gemma":0.0006883306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000133966,"about_ca_topic_score_gemma":0.00009273832,"domain_scores_codex":[0.9673402,0.01009363,0.01186061,0.001504083,0.008702399,0.0004990934],"domain_scores_gemma":[0.9583858,0.02455555,0.009802473,0.004302419,0.002666006,0.0002877764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006407481,0.0004577914,0.8745801,0.003433622,0.0005390449,0.00002393069,0.002091886,0.00003668062,0.005484181,0.02270504,0.03899305,0.05101392],"study_design_scores_gemma":[0.003267823,0.003693606,0.8143818,0.03847116,0.003720053,0.0000234214,0.003865621,0.02001025,0.005018555,0.09632849,0.009805558,0.001413606],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1934515,0.01822316,0.7562556,0.01965136,0.002326524,0.007252998,0.00004715642,0.00005056322,0.002741121],"genre_scores_gemma":[0.9637139,0.0001277036,0.03367792,0.0007777049,0.000227485,0.000269514,0.000004867155,0.00001978116,0.001181163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7702623,"threshold_uncertainty_score":0.9947622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9670815865336823,"score_gpt":0.6774248858922133,"score_spread":0.289656700641469,"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."}}