{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001196946,0.0002423512,0.0003576875,0.0005427864,0.0001375785,0.0000852885,0.000594044,0.0001588323,0.00000523212],"category_scores_gemma":[0.001060373,0.0002280647,0.00008090747,0.0005916672,0.00004892909,0.0002597327,0.0000403682,0.0005522504,0.000002645371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003346498,"about_ca_system_score_gemma":0.00005109538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001220322,"about_ca_topic_score_gemma":0.000006466406,"domain_scores_codex":[0.9982539,0.000360489,0.0002828536,0.0006057197,0.0001903932,0.0003066075],"domain_scores_gemma":[0.9944891,0.004465791,0.00003769496,0.0008215825,0.00005383567,0.0001320173],"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":[0.00004372829,0.0005913611,0.003878756,0.0003255652,0.0003270332,0.0001233784,0.01231661,0.03363759,0.001143441,0.0008200784,0.0005329619,0.9462595],"study_design_scores_gemma":[0.008248434,0.03847359,0.06312873,0.004005428,0.002110163,0.005115591,0.004831299,0.6613119,0.04683159,0.09532479,0.06015806,0.01046044],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1027033,0.0003655904,0.8880937,0.000292086,0.0005817522,0.0001487301,0.000003757911,0.007808845,0.000002329155],"genre_scores_gemma":[0.4357216,0.00001402322,0.5641223,0.00004323976,0.00002701036,0.00003465624,6.871394e-7,0.00002063745,0.0000158878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9357991,"threshold_uncertainty_score":0.9300209,"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."}}