{"id":"W4386793875","doi":"10.1093/biomet/asad057","title":"<i>E</i>-values as unnormalized weights in multiple testing","year":2023,"lang":"en","type":"article","venue":"Biometrika","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Normalization (sociology); Statistics; Statistical hypothesis testing; Multiple comparisons problem","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":[0.005230894,0.0001977479,0.0006063039,0.001166963,0.00008711524,0.00004886244,0.000342785,0.0001921985,0.0002375515],"category_scores_gemma":[0.4471984,0.0001672582,0.0001113526,0.00830516,0.0001348672,0.0000702713,0.0002012191,0.0002255098,0.0008000454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000610873,"about_ca_system_score_gemma":0.00005531207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000874603,"about_ca_topic_score_gemma":0.000006066396,"domain_scores_codex":[0.9969677,0.0006114981,0.000971614,0.0004221298,0.0005112895,0.0005157683],"domain_scores_gemma":[0.8691643,0.1299129,0.0002063195,0.0004464524,0.0001126862,0.0001573872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008877532,0.002066408,0.1824758,0.00139378,0.000392185,0.001221719,0.001477673,0.00001269888,0.03617268,0.1664677,0.03112982,0.5763018],"study_design_scores_gemma":[0.002075131,0.0001305709,0.01195003,0.0001381777,0.00002722764,0.000004886273,0.00005666858,0.001445573,0.004430844,0.9750994,0.004360463,0.0002810649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9755667,0.0001258671,0.007233842,0.0004099922,0.001793555,0.001061259,0.0001130596,0.001231191,0.01246456],"genre_scores_gemma":[0.1368351,0.00003798561,0.8616139,0.0001272638,0.000296724,0.00006127603,0.000004500504,0.00005412549,0.0009691264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8543801,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7188583237540784,"score_gpt":0.5729042471527536,"score_spread":0.1459540766013249,"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."}}