{"id":"W2557904139","doi":"10.1177/0363546516674469","title":"The Fragility of Statistically Significant Findings From Randomized Trials in Sports Surgery: A Systematic Survey","year":2016,"lang":"en","type":"article","venue":"The American Journal of Sports Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":169,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Interquartile range; Randomized controlled trial; Fragility; Physical therapy; Sample size determination; Surgery; Internal medicine; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.791953,0.0003309431,0.02393302,0.0005161396,0.00008751385,0.00008901367,0.001802625,0.00003448577,0.002757556],"category_scores_gemma":[0.6362208,0.00007394025,0.002393299,0.001676336,0.001770142,0.00009775096,0.00005795528,0.0002259553,0.00001865664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004997771,"about_ca_system_score_gemma":0.000289349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004708272,"about_ca_topic_score_gemma":0.00003736748,"domain_scores_codex":[0.799004,0.1258352,0.0592085,0.0007045931,0.01473659,0.0005111531],"domain_scores_gemma":[0.2653472,0.6450193,0.08177761,0.003972233,0.003502915,0.0003807115],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.04061938,0.0002225566,0.7534578,0.0006582202,0.003016033,0.0003798624,0.003956845,0.00002421656,0.0004857914,0.001193658,0.04934293,0.1466427],"study_design_scores_gemma":[0.01082513,0.0001622448,0.9410787,0.01019004,0.002342714,0.00006070152,0.003177869,0.0001556381,0.00002370269,0.03152615,0.0002480501,0.0002090305],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9653803,0.001969045,0.02503571,0.005715364,0.0005481248,0.001248609,0.00003372898,0.000001593168,0.00006753293],"genre_scores_gemma":[0.9979177,0.001150824,0.0003639224,0.0001651992,0.0001150984,0.00001406876,0.000001452988,0.00001175675,0.0002600225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5336568,"threshold_uncertainty_score":0.998154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5139008644722142,"score_gpt":0.4852435311609176,"score_spread":0.02865733331129655,"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."}}