{"id":"W2790069858","doi":"10.1111/bju.14210","title":"The fragility of statistically significant findings from randomised controlled trials in the urological literature","year":2018,"lang":"en","type":"article","venue":"British Journal of Urology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Fragility; Interquartile range; Medicine; Statistical significance; Randomized controlled trial; Index (typography); 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6695982,0.003998724,0.01209668,0.03030644,0.003055548,0.01585237,0.00708024,0.008380541,0.008379839],"category_scores_gemma":[0.9098355,0.003446978,0.02543298,0.02413111,0.01381031,0.01762844,0.01136599,0.009070544,0.001018662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006266281,"about_ca_system_score_gemma":0.00545034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009273293,"about_ca_topic_score_gemma":0.001151195,"domain_scores_codex":[0.1779572,0.5182161,0.1963799,0.03419382,0.0704417,0.002811222],"domain_scores_gemma":[0.02083652,0.889586,0.06419843,0.01813693,0.006639829,0.0006023416],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"observational","study_design_scores_codex":[0.01695413,0.0003025993,0.1471129,0.2632353,0.3221995,0.003980287,0.004560977,0.01078251,0.001971167,0.02678213,0.01509819,0.1870203],"study_design_scores_gemma":[0.01049302,0.007658056,0.113607,0.2042954,0.2780318,0.01074072,0.00399445,0.02620955,0.007372924,0.2584111,0.07756387,0.001622083],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.06715796,0.6188826,0.2261001,0.03959384,0.01008908,0.01248055,0.007916798,0.001766625,0.01601249],"genre_scores_gemma":[0.8113178,0.02741555,0.1197076,0.01512817,0.005342183,0.01621961,0.003399361,0.0006729848,0.0007968305],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3304018,"threshold_uncertainty_score":0.4074444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3911992363867021,"score_gpt":0.4647731608935597,"score_spread":0.07357392450685768,"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."}}