{"id":"W4404603191","doi":"10.1214/24-aos2434","title":"On the existence of powerful p-values and e-values for composite hypotheses","year":2024,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Composite number; Mathematics; Statistics; Psychology; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0002643008,0.00006288054,0.00009425456,0.00001820517,0.00008606645,0.00006625189,0.0004016084,0.00001166344,0.000002780448],"category_scores_gemma":[0.00006817436,0.00003261554,0.00002453721,0.0001175988,0.0001945386,0.00004669634,0.00007683514,0.00004958191,0.000002901715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001256409,"about_ca_system_score_gemma":0.00001355817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007204615,"about_ca_topic_score_gemma":7.021849e-7,"domain_scores_codex":[0.9994816,0.00003281897,0.0001467025,0.0001175523,0.0001245821,0.00009675274],"domain_scores_gemma":[0.9967948,0.002752815,0.00006335771,0.0002800782,0.00009029107,0.00001865354],"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":[0.000006204478,0.00001564839,0.00000298798,0.00003571757,0.00001597167,4.652079e-7,0.0004196579,0.0001073132,0.0006288295,0.958859,0.02610979,0.01379836],"study_design_scores_gemma":[0.00002875266,0.000190771,0.0005458658,0.00009573848,0.00001116309,0.000002454128,0.00004472924,0.08733535,0.00685616,0.9030637,0.001768578,0.00005677166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09091081,0.00222392,0.8871565,0.01722273,0.0001607405,0.0004892084,0.000537113,0.00005209245,0.001246921],"genre_scores_gemma":[0.9738038,0.000508301,0.02462534,0.000685077,0.00003681235,0.00001226794,0.000002009775,0.000006747664,0.0003195961],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.882893,"threshold_uncertainty_score":0.1330023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1020206208146769,"score_gpt":0.3544260630360375,"score_spread":0.2524054422213606,"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."}}