{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0129606,0.001085755,0.001293921,0.002216872,0.002323795,0.007582733,0.003804005,0.003198717,0.003837334],"category_scores_gemma":[0.03091458,0.001342575,0.003967673,0.00188273,0.01354099,0.02087419,0.008108831,0.007335361,0.0007611463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004081069,"about_ca_system_score_gemma":0.003282509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006468284,"about_ca_topic_score_gemma":0.004342861,"domain_scores_codex":[0.9855656,0.006150609,0.001313823,0.002495881,0.00342848,0.001045603],"domain_scores_gemma":[0.9800044,0.01210257,0.001324931,0.003599219,0.002182928,0.0007860168],"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":[0.000012648,0.00002311026,0.0001461264,0.00003926632,0.00001583827,0.00005784564,0.000529174,0.003343848,0.000412628,0.990146,0.000335348,0.00493817],"study_design_scores_gemma":[0.00001349258,0.00001648049,0.00007910099,0.0000239597,0.00002066598,0.00007451977,0.0001090601,0.03093357,0.001075707,0.9637802,0.00385345,0.00001980826],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005623134,0.0001239884,0.9887266,0.001634271,0.00003906685,0.00006713065,0.00007024391,0.0004037924,0.003311841],"genre_scores_gemma":[0.3506384,0.0003424718,0.6426914,0.001098529,0.0002359869,0.0005037136,0.0003207183,0.0004471802,0.003721555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0129606,"threshold_uncertainty_score":0.06854302,"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."}}