{"id":"W4404691850","doi":"10.4171/owr/2024/24","title":"Game-theoretic Statistical Inference: Optional Sampling, Universal Inference, and Multiple Testing Based on E-values","year":2024,"lang":"en","type":"article","venue":"Oberwolfach Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inference; Statistical inference; Computer science; Martingale (probability theory); Notation; Statistical hypothesis testing; Artificial intelligence; Machine learning; Interpretation (philosophy); Meaning (existential); Game theory; Theoretical computer science; Data science; Mathematical economics; Mathematics; Epistemology; Statistics; Programming language","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":[0.07642431,0.001564017,0.002687487,0.001995305,0.001113587,0.005180595,0.003358512,0.003592082,0.005553714],"category_scores_gemma":[0.1520732,0.001015844,0.002765966,0.001854244,0.009281101,0.008474466,0.00587507,0.006783575,0.0008529274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0029493,"about_ca_system_score_gemma":0.003327727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001443361,"about_ca_topic_score_gemma":0.001237421,"domain_scores_codex":[0.9570509,0.03548664,0.001140179,0.002488072,0.003068194,0.0007660937],"domain_scores_gemma":[0.8187635,0.1665361,0.00301347,0.007003431,0.002647871,0.00203561],"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":[0.0002017629,0.00005958591,0.00091261,0.00025505,0.0001704605,0.0001710632,0.0002590324,0.0129692,0.0002700205,0.887181,0.00880151,0.08874885],"study_design_scores_gemma":[0.0000448442,0.00005340918,0.0002676994,0.0001309194,0.00002992879,0.00007499226,0.00004795209,0.05128774,0.0002576165,0.9391842,0.008589959,0.00003072641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00259241,0.002835228,0.9783634,0.01113294,0.0009692291,0.00009252821,0.00006372022,0.0001121198,0.003838551],"genre_scores_gemma":[0.213129,0.006322171,0.7558823,0.008061255,0.004887368,0.001323687,0.0002515461,0.0003507022,0.009792007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07642431,"threshold_uncertainty_score":0.4041752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4245189506016742,"score_gpt":0.526775350920045,"score_spread":0.1022564003183708,"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."}}