{"id":"W3098557859","doi":"10.1145/3368089.3409757","title":"ARDiff: scaling program equivalence checking via iterative abstraction and refinement of common code","year":2020,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Equivalence (formal languages); Symbolic execution; Computer science; Symbolic trajectory evaluation; Abstraction; Programming language; Program analysis; Formal equivalence checking; Abstraction model checking; Model checking; Theoretical computer science; Symbolic data analysis; Static analysis; Algorithm; Mathematics; Discrete mathematics; Software","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":[],"consensus_categories":[],"category_scores_codex":[0.0001876192,0.0000893864,0.0001377076,0.00003300787,0.00006452346,0.00008245379,0.0002198478,0.00003187703,0.00000444272],"category_scores_gemma":[0.00009282629,0.00007824679,0.00002555389,0.0001704539,0.00003876,0.0001962944,0.0001833726,0.00009795789,0.000001690749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001510764,"about_ca_system_score_gemma":0.00001104329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006300687,"about_ca_topic_score_gemma":0.000002261294,"domain_scores_codex":[0.999223,0.00002703584,0.0002080914,0.0002490835,0.0001669908,0.0001258051],"domain_scores_gemma":[0.9994532,0.0001324754,0.0001104084,0.000179654,0.0000613378,0.00006295204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000134894,0.0001679753,0.01154193,0.0001808261,0.00002238303,0.00001298526,0.003898865,0.0001079898,0.006336107,0.001741381,0.002685364,0.9732907],"study_design_scores_gemma":[0.0004199176,0.0009673089,0.01889018,0.0003883821,0.00001901246,0.00003934759,0.00003823682,0.8744522,0.08896014,0.01387908,0.001497166,0.0004490228],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08215769,0.00005936438,0.9103379,0.0009125501,0.00004486976,0.0002033408,0.000001137561,0.005111005,0.001172131],"genre_scores_gemma":[0.6712798,0.000003952957,0.32848,0.0002004679,0.00001558994,0.00001079316,9.105443e-7,0.000003242013,0.00000520682],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9728417,"threshold_uncertainty_score":0.3190812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05157918219343462,"score_gpt":0.3174457627915477,"score_spread":0.2658665805981131,"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."}}