{"id":"W4401724691","doi":"10.1145/3688842","title":"My Fuzzers Won’t Build: An Empirical Study of Fuzzing Build Failures","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Fuzz testing; Computer science; Software engineering; Software bug; Context (archaeology); Software; Set (abstract data type); Operating system; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01147908,0.0005325733,0.0004165731,0.003363524,0.001285619,0.001484257,0.001681459,0.001552352,0.001339736],"category_scores_gemma":[0.09841094,0.0005941055,0.0004686402,0.002722858,0.001996972,0.004490789,0.001401526,0.002985418,0.0006603835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001045784,"about_ca_system_score_gemma":0.001102296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008763247,"about_ca_topic_score_gemma":0.01149735,"domain_scores_codex":[0.9938351,0.00242514,0.0006752897,0.0008147748,0.001777856,0.0004718438],"domain_scores_gemma":[0.7600774,0.1809156,0.03152547,0.01081013,0.01350385,0.003167682],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002946439,0.001314647,0.947741,0.000187373,0.0001021775,0.0006523363,0.01664972,0.003122806,0.001051677,0.001428743,0.003032471,0.02442245],"study_design_scores_gemma":[0.00006832298,0.001139097,0.9128461,0.0003054225,0.00009765428,0.001754475,0.02627915,0.04603189,0.0019692,0.003016419,0.006371902,0.0001204079],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975033,0.0001166993,0.001161555,0.0002899244,0.000004360011,0.00004268016,0.0002753023,0.00003778725,0.0005684398],"genre_scores_gemma":[0.9972646,0.0001050486,0.001583035,0.0001233388,0.000008849613,0.00005238776,0.0005905303,0.00002726416,0.0002450115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9885209,"threshold_uncertainty_score":0.06070793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09234755339412065,"score_gpt":0.369741653032348,"score_spread":0.2773940996382273,"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."}}