{"id":"W3196600806","doi":"","title":"Finding Counterexamples of Temporal Logic properties in Software Implementations via Greybox Fuzzing","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Computer science; Model checking; Liveness; Programming language; Counterexample; Temporal logic; Stateful firewall; Software; Property (philosophy); Linear temporal logic; Implementation; Theoretical computer science; Mathematics; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002216011,0.0008035195,0.0006612206,0.001995152,0.000561937,0.001331892,0.001209115,0.001381748,0.001467312],"category_scores_gemma":[0.0236591,0.0006393797,0.001680724,0.0008150191,0.001817295,0.002553466,0.001601589,0.001467565,0.0001853204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001150906,"about_ca_system_score_gemma":0.001342984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003182186,"about_ca_topic_score_gemma":0.00360486,"domain_scores_codex":[0.9964168,0.0006745031,0.0002302961,0.0009181696,0.001481437,0.0002787014],"domain_scores_gemma":[0.9819838,0.0130709,0.001705464,0.002038521,0.0009710954,0.0002301781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001366644,0.0004950504,0.06470498,0.001008262,0.0005844246,0.00464539,0.002479715,0.4132094,0.1884278,0.1250544,0.003470786,0.194553],"study_design_scores_gemma":[0.00008373062,0.000167077,0.003040068,0.0001125037,0.0001356663,0.0005521365,0.0001415668,0.8815585,0.06281774,0.04958696,0.001741539,0.00006250434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.411824,0.000258564,0.5797044,0.0004823616,0.00005874456,0.0001523286,0.0002799636,0.005852252,0.00138731],"genre_scores_gemma":[0.8169208,0.0001158371,0.181365,0.0002302169,0.0000163896,0.0001217255,0.0003537014,0.0003047349,0.0005715319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003182186,"threshold_uncertainty_score":0.01171952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1810027213860887,"score_gpt":0.2374389049298393,"score_spread":0.05643618354375063,"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."}}