{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04107627,0.001295104,0.00222852,0.003164802,0.008244418,0.006687458,0.004150317,0.01085994,0.005212804],"category_scores_gemma":[0.2016889,0.001050407,0.001578622,0.005045661,0.01537316,0.01540862,0.004873789,0.009961688,0.000954547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00252133,"about_ca_system_score_gemma":0.001294242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002526675,"about_ca_topic_score_gemma":0.001995458,"domain_scores_codex":[0.967478,0.02330098,0.0013465,0.002270826,0.004569087,0.001034527],"domain_scores_gemma":[0.8215755,0.1601243,0.003802569,0.005852664,0.007502695,0.001142219],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001634204,0.00003722926,0.001461973,0.0002130646,0.00007233881,0.0009066187,0.002872131,0.004267856,0.0001312387,0.9500809,0.01494855,0.02484462],"study_design_scores_gemma":[0.00002540206,0.000006518391,0.0002778601,0.00008295096,0.000007040322,0.0001806031,0.0004199092,0.004903016,0.00005554282,0.9883994,0.005621218,0.00002054616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04832118,0.01372127,0.6191606,0.1969403,0.001435665,0.0002975413,0.0005840005,0.000554028,0.1189855],"genre_scores_gemma":[0.7482536,0.006176961,0.2192751,0.01431379,0.002697793,0.0006533566,0.0004149919,0.0003989504,0.00781529],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9589238,"threshold_uncertainty_score":0.2172346,"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."}}