{"id":"W2971543728","doi":"10.1136/bmjopen-2018-024625","title":"Empirical evaluation of SUCRA-based treatment ranks in network meta-analysis: quantifying robustness using Cohen’s kappa","year":2019,"lang":"en","type":"article","venue":"BMJ Open","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":87,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; St. Joseph’s Healthcare Hamilton; University of Toronto; McMaster University; Children's Hospital of Eastern Ontario; Impact","funders":"","keywords":"Kappa; Medicine; Robustness (evolution); Meta-analysis; Statistics; Mathematics; Combinatorics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.2871295,0.0003560669,0.009374266,0.0006647059,0.0000879476,0.0008531655,0.002074184,0.0001171948,0.02902068],"category_scores_gemma":[0.006244834,0.0001675346,0.004931671,0.004547008,0.00003338055,0.0003552214,0.0002305505,0.00009160592,0.0004321162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001780249,"about_ca_system_score_gemma":0.0005277554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004228035,"about_ca_topic_score_gemma":0.001620745,"domain_scores_codex":[0.9435644,0.0348956,0.01095687,0.001438469,0.00876381,0.0003808247],"domain_scores_gemma":[0.9840156,0.003853046,0.005855338,0.004664284,0.001507455,0.0001043026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000358506,0.00009787075,0.1719946,0.00002201928,0.01751127,0.00000186008,0.0001673365,0.8087661,0.0000096524,0.00005572944,0.0006686947,0.000669035],"study_design_scores_gemma":[0.0008487331,0.00004226148,0.01711627,0.00002367434,0.1154927,0.000001302203,0.0003865206,0.865047,0.00002070551,0.0002770827,0.0005521994,0.000191575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9365904,0.002018272,0.03195667,0.0007995216,0.0002873011,0.02254442,0.00002461243,0.000004607708,0.005774244],"genre_scores_gemma":[0.9845153,0.000001303725,0.01334282,0.0001427857,0.00003316284,0.0008128408,0.00002345905,0.00001305226,0.001115274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2808846,"threshold_uncertainty_score":0.9718669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9733493916709587,"score_gpt":0.6926810856945466,"score_spread":0.2806683059764121,"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."}}