{"id":"W2884750441","doi":"10.1214/18-aoas1160sf","title":"When should modes of inference disagree? Some simple but challenging examples","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Frequentist inference; Fiducial inference; Inference; Bayes' theorem; Computer science; Simple (philosophy); Bayesian inference; Statistical inference; Artificial intelligence; Machine learning; Predictive inference; Econometrics; Bayesian probability; Mathematics; Epistemology; Statistics; Philosophy","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":[0.0004608606,0.0001635996,0.0002787034,0.00006142143,0.0001333627,0.00005157742,0.001140447,0.00005912687,0.00002179097],"category_scores_gemma":[0.00006886381,0.0001226219,0.00002973701,0.0001258335,0.0003683847,0.0001405558,0.0003219028,0.0001373658,0.00001798332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004843427,"about_ca_system_score_gemma":0.00007152157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001311001,"about_ca_topic_score_gemma":0.00001892667,"domain_scores_codex":[0.9986288,0.00003657332,0.0003947426,0.0002583133,0.0003644543,0.0003171225],"domain_scores_gemma":[0.99825,0.0004705744,0.0002358984,0.0007174834,0.0002508388,0.00007517046],"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":[0.00001778738,0.00004004002,0.00001276996,0.00003833204,0.00002317681,5.713977e-7,0.001839447,0.000864953,0.004208587,0.9540402,0.0009571902,0.03795691],"study_design_scores_gemma":[0.00009179841,0.0001237631,0.00023699,0.00002622551,0.000009766789,6.315678e-7,0.0001703508,0.1873469,0.0249234,0.7866876,0.0002267367,0.0001558753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01584931,0.00009459157,0.9814124,0.000528627,0.0000438615,0.0001078904,0.0001713109,0.00005292252,0.001739088],"genre_scores_gemma":[0.9320842,0.0001430212,0.06729458,0.0003545003,0.00007450771,0.000007511873,0.000009514114,0.00001052543,0.00002163047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9162349,"threshold_uncertainty_score":0.5000375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2025395505903315,"score_gpt":0.3616324196098393,"score_spread":0.1590928690195079,"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."}}