{"id":"W4385477690","doi":"10.1109/sp46215.2023.10179438","title":"Finding Specification Blind Spots via Fuzz Testing","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spec#; Computer science; Codebase; Fuzz testing; Programming language; Code coverage; Source code; 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":[0.0005108091,0.00009164051,0.00008270345,0.0002256731,0.0001610445,0.0001542162,0.0005474854,0.0000435886,0.000008574365],"category_scores_gemma":[0.0006610408,0.00008538052,0.0000260631,0.001565767,0.00001705538,0.0002351738,0.0002076111,0.00009174339,0.0005148001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000274544,"about_ca_system_score_gemma":0.00002599185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004002784,"about_ca_topic_score_gemma":8.481836e-7,"domain_scores_codex":[0.9990461,0.00002363819,0.0001679479,0.0003165806,0.0001982712,0.0002474537],"domain_scores_gemma":[0.9987187,0.0006075719,0.00006326407,0.0004785813,0.00007615961,0.00005574398],"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":[0.000002832217,0.00004097615,0.03186904,0.00002137825,0.000007520052,0.00005414871,0.0005062548,0.000132493,0.00326261,0.01289245,0.0745478,0.8766625],"study_design_scores_gemma":[0.000286809,0.0000841913,0.1210765,0.00009927282,0.000004574349,0.00007991922,0.000009951178,0.6426162,0.007313949,0.2258614,0.002071741,0.0004955554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0219968,0.00001032941,0.9210798,0.0006241119,0.0002423069,0.0001103573,2.969656e-7,0.04499236,0.01094365],"genre_scores_gemma":[0.5696615,0.000001378497,0.4295734,0.0001037602,0.00007678218,0.00001127165,0.000002290409,0.000008316072,0.0005612873],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8761669,"threshold_uncertainty_score":0.6616886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1334906773802719,"score_gpt":0.3164290038649961,"score_spread":0.1829383264847242,"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."}}