{"id":"W2603520596","doi":"10.1136/ebmed-2017-110668","title":"Rating the certainty in evidence in the absence of a single estimate of effect","year":2017,"lang":"en","type":"article","venue":"Evidence-Based Medicine","topic":"Health Policy Implementation Science","field":"Health Professions","cited_by":675,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Certainty; Grading (engineering); Meta-analysis; Computer science; Econometrics; Psychology; Actuarial science; Mathematics; Economics; Medicine; Engineering","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":[],"domain":null,"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4318945,0.002995816,0.01263793,0.027402,0.002038905,0.01303516,0.00641451,0.01097642,0.006963977],"category_scores_gemma":[0.8051954,0.002792445,0.01899253,0.01138143,0.006631623,0.0141322,0.01203993,0.01054376,0.001686012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005904675,"about_ca_system_score_gemma":0.008958176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003611693,"about_ca_topic_score_gemma":0.004771421,"domain_scores_codex":[0.4091236,0.2345431,0.2805566,0.01204744,0.06165636,0.002072882],"domain_scores_gemma":[0.1845463,0.6737552,0.0675102,0.02144679,0.0493724,0.003369021],"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":[0.006023416,0.0002223394,0.02281801,0.364826,0.05988569,0.001348702,0.008896084,0.004998556,0.003042337,0.03855469,0.06712187,0.4222624],"study_design_scores_gemma":[0.00500846,0.00223389,0.01872773,0.3392673,0.06679119,0.005041557,0.007361478,0.01344047,0.006365508,0.2726915,0.2603091,0.002761838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.03698652,0.426051,0.32303,0.1048259,0.02899355,0.02530569,0.01847712,0.001390276,0.03493989],"genre_scores_gemma":[0.3033439,0.10908,0.5122558,0.02278981,0.007059347,0.03526894,0.006537536,0.0004893165,0.003175389],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5681055,"threshold_uncertainty_score":0.7005752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7369926022121754,"score_gpt":0.6868045677958105,"score_spread":0.05018803441636499,"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."}}