{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009166521,0.001154049,0.001212296,0.002836752,0.0008980912,0.002289861,0.002574583,0.001760002,0.001854916],"category_scores_gemma":[0.05793146,0.001097157,0.001602406,0.001069483,0.004303513,0.006095317,0.004214143,0.002594765,0.0005032998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001438037,"about_ca_system_score_gemma":0.002526299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002622748,"about_ca_topic_score_gemma":0.002684664,"domain_scores_codex":[0.9888089,0.004286494,0.0005193446,0.001509346,0.004216258,0.0006595595],"domain_scores_gemma":[0.9341602,0.0468102,0.004302132,0.01065076,0.003496873,0.0005799007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001093903,0.0004222812,0.03628041,0.0009490192,0.0004138068,0.002046397,0.002924416,0.1395347,0.05959134,0.2153675,0.004929677,0.5364466],"study_design_scores_gemma":[0.0001246976,0.0004691952,0.003568717,0.0002942443,0.0001786936,0.001000587,0.0004755329,0.6851108,0.06521316,0.2353756,0.008061664,0.0001269812],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08405233,0.0002926086,0.906788,0.000772314,0.00004044302,0.0001476869,0.0001107848,0.005997547,0.001798261],"genre_scores_gemma":[0.5988767,0.0002386133,0.3979721,0.0004924989,0.00003313897,0.000180364,0.0003084967,0.0007755122,0.001122583],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009166521,"threshold_uncertainty_score":0.04847777,"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."}}