{"id":"W2139032973","doi":"10.1145/3321699","title":"On the Computability of Conditional Probability","year":2019,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Office of Naval Research Global; Army Research Office; Office of Naval Research; Defense Advanced Research Projects Agency; John Templeton Foundation; National Science Foundation","keywords":"Conditional probability distribution; Inference; Computability; Joint probability distribution; Regular conditional probability; Conditional probability; Probabilistic logic; Computer science; Conditional variance; Probability distribution; Mathematics; Fiducial inference; Bayesian network; Frequentist inference; Theoretical computer science; Artificial intelligence; Bayesian inference; Posterior probability; Bayesian probability; Econometrics; Statistics; Autoregressive conditional heteroskedasticity","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002580513,0.0001252254,0.0002945288,0.00004491006,0.00009048981,0.00005518012,0.005999052,0.00004893986,0.0001171581],"category_scores_gemma":[0.002481371,0.00006002069,0.0003438161,0.0003374401,0.0002084127,0.000217503,0.001749228,0.0004323097,0.00002591609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301059,"about_ca_system_score_gemma":0.0002163133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005971735,"about_ca_topic_score_gemma":0.000001718934,"domain_scores_codex":[0.9977316,0.0004914398,0.0005888405,0.0002129276,0.0007993425,0.0001759042],"domain_scores_gemma":[0.9938651,0.002233077,0.000641035,0.002733657,0.0004679102,0.00005923906],"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":[0.0003207915,0.00422486,0.203135,0.0002915794,0.0004347122,0.00001428062,0.002963485,0.0869167,0.004472645,0.6521288,0.02503377,0.02006346],"study_design_scores_gemma":[0.0003016799,0.0002810073,0.2015773,0.00003083551,0.000007543074,0.00006335497,0.00001354811,0.01137016,0.001279894,0.7846275,0.0003729443,0.00007425504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9592385,0.0000314934,0.01884145,0.01985209,0.001205476,0.0003565767,0.000005184768,0.00001450048,0.000454772],"genre_scores_gemma":[0.9833047,7.65899e-7,0.01607222,0.0004994948,0.00008965466,0.000001354906,1.419396e-7,0.000003923995,0.00002777887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1324988,"threshold_uncertainty_score":0.999379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02452586075170043,"score_gpt":0.2397436997901926,"score_spread":0.2152178390384922,"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."}}