{"id":"W4205512329","doi":"10.1145/3498677","title":"Reasoning about “reasoning about reasoning”: semantics and contextual equivalence for probabilistic programs with nested queries and recursion","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Soundness; Computer science; Operational semantics; Probabilistic logic; Equivalence (formal languages); Theoretical computer science; Inference; Semantics (computer science); Recursion (computer science); Denotational semantics; Programming language; Artificial intelligence; Mathematics; Discrete mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001275388,0.0004142477,0.0004932958,0.0001313063,0.001119003,0.0006222057,0.001904236,0.00009897428,0.000002408318],"category_scores_gemma":[0.003312173,0.0002919399,0.0001062343,0.0006794087,0.0004828484,0.0004985385,0.002091269,0.0004343041,3.943783e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008854147,"about_ca_system_score_gemma":0.00009476437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006520621,"about_ca_topic_score_gemma":0.00002148136,"domain_scores_codex":[0.997317,0.00005346956,0.0003959845,0.0009003798,0.0006088031,0.0007243271],"domain_scores_gemma":[0.9978362,0.000319752,0.0006486509,0.0006072367,0.000425229,0.0001629284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006705784,0.0006416976,0.1291863,0.002255147,0.0002079985,0.00002083794,0.04142818,0.00002846811,0.001839717,0.4386811,0.0004343867,0.3846056],"study_design_scores_gemma":[0.03530352,0.06967597,0.2014684,0.04930678,0.003343301,0.009501772,0.2346286,0.1073219,0.06014045,0.09256092,0.119636,0.01711246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908284,0.003532693,0.001050276,0.0009886902,0.0001881507,0.002213122,0.00001004706,0.0004752229,0.0007134025],"genre_scores_gemma":[0.9038032,0.00005226089,0.09486443,0.00008379747,0.00008217182,0.0005738407,0.000006096528,0.0000488181,0.0004854105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3674931,"threshold_uncertainty_score":0.9999533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01557696947963156,"score_gpt":0.2556624228237966,"score_spread":0.2400854533441651,"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."}}