{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02820178,0.000155748,0.0004813343,0.0001937774,0.000643572,0.0000108933,0.001364135,0.00007422794,0.0001662455],"category_scores_gemma":[0.1189983,0.00007807248,0.00004011296,0.0006159001,0.000940516,0.0004565798,0.0001217232,0.0005735967,0.00001703131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001859423,"about_ca_system_score_gemma":0.00105913,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0126191,"about_ca_topic_score_gemma":0.004686626,"domain_scores_codex":[0.9935081,0.003163464,0.001444936,0.0002918787,0.001006257,0.0005853658],"domain_scores_gemma":[0.9471802,0.04986984,0.001434068,0.001178973,0.0002430261,0.000093854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002827707,0.00003745691,0.9238759,0.002159402,0.000003525954,0.00001698231,0.03715555,0.0002430417,0.02395497,0.0004586092,0.002243657,0.009568155],"study_design_scores_gemma":[0.002310734,0.0009452152,0.9511296,0.03466395,0.0000164291,0.000002001102,0.004719594,0.002338934,0.003078262,0.0002973958,0.0003869593,0.0001109571],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8581573,0.00042221,0.0004053331,0.1383186,0.000309282,0.001814905,0.000003509931,0.00001078687,0.0005580104],"genre_scores_gemma":[0.9919708,0.00007595345,0.0002655678,0.007229463,0.0001649281,0.0002521677,5.684907e-7,0.000008324554,0.00003221922],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1338135,"threshold_uncertainty_score":0.993956,"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."}}