{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003472331,0.0002654427,0.000385729,0.0004263476,0.0001248955,0.0001328797,0.001217871,0.0001718376,0.00001372062],"category_scores_gemma":[0.000196239,0.0002956007,0.0001449684,0.000662984,0.0001004109,0.0003792358,0.001855609,0.0003970239,0.00000275474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002152463,"about_ca_system_score_gemma":0.000306631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002033902,"about_ca_topic_score_gemma":0.0004919227,"domain_scores_codex":[0.9982626,0.0001539376,0.0003466846,0.000802541,0.0001158646,0.0003183317],"domain_scores_gemma":[0.9983048,0.0002180987,0.0003474441,0.0008442097,0.0002206692,0.00006477535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002936294,0.0004356328,0.9182431,0.001167209,0.0001644394,0.0009416061,0.004477393,0.05031763,0.0003628601,0.01795596,0.0005796984,0.00532509],"study_design_scores_gemma":[0.001726705,0.0003765273,0.05921515,0.006108101,0.0001858777,0.00008036657,0.001129278,0.5273611,0.004261152,0.3966167,0.0001275767,0.002811514],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3659771,0.0001353923,0.6320407,0.00002809894,0.0001474464,0.0001881693,0.000009074168,0.00141934,0.00005461468],"genre_scores_gemma":[0.9290522,0.00003668571,0.07076201,0.00004016179,0.00001762738,0.000003293969,0.00002581017,0.00001499358,0.00004727535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.859028,"threshold_uncertainty_score":0.9999496,"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."}}