{"id":"W3096180835","doi":"","title":"Testing with p*-values: Between p-values and e-values","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Frequentist inference; Statistics; Value (mathematics); Bayesian probability; Expected value; Combinatorics; Bayesian inference","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_narrow"],"consensus_categories":[],"category_scores_codex":[0.001766675,0.0006089791,0.001503146,0.000147144,0.0002168116,0.0001197038,0.0008091984,0.0004767915,0.0000762535],"category_scores_gemma":[0.03748275,0.000573292,0.0001982478,0.0005299925,0.0007401686,0.0001155395,0.001658791,0.001328396,0.00004396264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001262323,"about_ca_system_score_gemma":0.0001958661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005786454,"about_ca_topic_score_gemma":0.000002758906,"domain_scores_codex":[0.9957777,0.001161924,0.0006978537,0.001627511,0.0002428516,0.0004921702],"domain_scores_gemma":[0.960336,0.0371457,0.0007389145,0.001021866,0.000296736,0.0004608074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001717978,0.000877123,0.2591938,0.009285974,0.005415841,0.004725555,0.002826351,0.004777174,0.0001844755,0.6857853,0.006953838,0.01825666],"study_design_scores_gemma":[0.0009670703,0.0003170496,0.004957512,0.0007417072,0.001298689,0.000004817958,0.0002511463,0.007791996,0.0001066315,0.9828517,0.00002879016,0.0006828592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5668134,0.00006111959,0.4222335,0.0002670001,0.0004053386,0.001200821,0.0003171327,0.0007343329,0.007967322],"genre_scores_gemma":[0.5597694,0.00004653865,0.4390756,0.00007007761,0.0004801583,0.000001941458,0.000006362987,0.00007927728,0.0004705856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2970665,"threshold_uncertainty_score":0.9996719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6909092857363631,"score_gpt":0.4098744284431825,"score_spread":0.2810348572931806,"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."}}