{"id":"W2995623611","doi":"10.1145/3371081","title":"Reductions for safety proofs","year":2019,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Security and Verification in Computing","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematical proof; Correctness; Computer science; Programming language; Class (philosophy); Context (archaeology); Soundness; Commutative property; Theoretical computer science; Mathematics; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004119488,0.00009438387,0.0001177301,0.00006034359,0.0001696563,0.0001218116,0.002300342,0.00004730167,0.000002671434],"category_scores_gemma":[0.0007902417,0.00006927361,0.0001027005,0.0003626547,0.00004084179,0.0002152078,0.0004854046,0.0001162047,0.000006573019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002744559,"about_ca_system_score_gemma":0.00002367404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005035125,"about_ca_topic_score_gemma":3.002296e-7,"domain_scores_codex":[0.9991101,0.000004979509,0.0001974603,0.0002860417,0.0001994788,0.0002019398],"domain_scores_gemma":[0.9988986,0.0001202276,0.0002092102,0.0005475826,0.0001948732,0.00002948506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004949734,0.0002418151,0.004547678,0.000433742,0.00006077345,1.08706e-7,0.005819609,0.00004007748,0.01551287,0.6712234,0.003898903,0.2981715],"study_design_scores_gemma":[0.002468249,0.001357256,0.01129943,0.001160348,0.00008440717,0.00008079493,0.007074194,0.00969699,0.5680558,0.08350742,0.3139535,0.001261528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9369231,0.0005160589,0.01162497,0.03115009,0.002193299,0.004258521,0.000009834858,0.001087979,0.01223608],"genre_scores_gemma":[0.8338829,0.000002923483,0.1651657,0.0001433748,0.0001081489,0.00006376836,8.365601e-7,0.00001037515,0.0006219343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.587716,"threshold_uncertainty_score":0.4274645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574506963475064,"score_gpt":0.2756575389875628,"score_spread":0.2599124693528121,"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."}}