{"id":"W4414092373","doi":"10.1561/3600000002","title":"Hypothesis Testing with E-values","year":2025,"lang":"en","type":"article","venue":"Foundations and Trends® in Statistics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistical hypothesis testing; Variety (cybernetics); Null hypothesis; Alternative hypothesis; Core (optical fiber); Test statistic; Value (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.05753712,0.003019739,0.004176016,0.005552365,0.001425646,0.009090366,0.004981235,0.006309239,0.02532682],"category_scores_gemma":[0.2278777,0.00152284,0.003190525,0.007275864,0.0127263,0.01280756,0.007057464,0.01343998,0.01100253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00270673,"about_ca_system_score_gemma":0.004602686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005522826,"about_ca_topic_score_gemma":0.0003283532,"domain_scores_codex":[0.903146,0.07085274,0.006636626,0.007337449,0.01131277,0.0007145238],"domain_scores_gemma":[0.6355097,0.3314436,0.007693088,0.01705994,0.007209214,0.001084626],"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":[0.0004648608,0.000155723,0.002014182,0.004184741,0.0007738852,0.0007173285,0.001242103,0.01167703,0.001093262,0.7024999,0.05475386,0.2204231],"study_design_scores_gemma":[0.0001214802,0.0002451887,0.000423988,0.001346699,0.0000944346,0.0003423613,0.0002874902,0.01561104,0.0009657721,0.9002785,0.08018779,0.00009521829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001646893,0.01055851,0.9503572,0.008724477,0.004306812,0.0006642858,0.00139005,0.001272668,0.02107905],"genre_scores_gemma":[0.06834828,0.01183587,0.8886709,0.008667273,0.005604375,0.007042452,0.002113998,0.0008624097,0.006854543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05753712,"threshold_uncertainty_score":0.304289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03986766164455913,"score_gpt":0.3050822617816032,"score_spread":0.2652146001370441,"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."}}