{"id":"W2886516149","doi":"10.1136/bmjebm-2018-111024.40","title":"40 How fragile is the evidence base? a meta-epidemiologic study of the fragilityindex derived from 374 randomised trials","year":2018,"lang":"en","type":"article","venue":"","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Fragility; Randomized controlled trial; Meta-analysis; Sample size determination; False positive paradox; Medicine; Statistics; Index (typography); Computer science; Mathematics; Internal medicine","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","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","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":[0.1236638,0.0003702838,0.003962186,0.0001429189,0.000578113,0.000119791,0.001284354,0.0002218382,0.007694352],"category_scores_gemma":[0.1044481,0.0002158712,0.0009839339,0.0003693134,0.0003754989,0.0004416765,0.000270531,0.0003050469,0.0006101987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001990916,"about_ca_system_score_gemma":0.0001784634,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008816908,"about_ca_topic_score_gemma":0.001484908,"domain_scores_codex":[0.9817071,0.009098092,0.007406441,0.001025226,0.0002325482,0.0005306123],"domain_scores_gemma":[0.9459751,0.04330856,0.007664992,0.002627652,0.0002531784,0.0001704767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003714386,0.002300271,0.497458,0.0004340662,0.01711797,0.000002070629,0.06029989,0.0004076193,0.0004139906,0.01718992,0.3999048,0.0007570373],"study_design_scores_gemma":[0.04786921,0.00182631,0.6667724,0.0003565515,0.003059623,0.000005154269,0.04170156,0.03575674,0.001845718,0.1458216,0.05272293,0.002262168],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8660358,0.004243983,0.005654147,0.1164523,0.001010666,0.005142647,0.0003325847,0.00005233472,0.001075511],"genre_scores_gemma":[0.9691905,0.0001235572,0.0009522169,0.02757028,0.0005381994,0.0006689652,0.00000437812,0.00002621436,0.0009256505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3471819,"threshold_uncertainty_score":0.9977835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7901114122054491,"score_gpt":0.492930718443132,"score_spread":0.2971806937623171,"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."}}