{"id":"W4411087888","doi":"10.1145/3742894","title":"The Havoc Paradox in Generator-Based Fuzzing","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Computer science; Generator (circuit theory); Programming language; Software; Power (physics)","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":[0.006480064,0.000707156,0.0007472973,0.00142835,0.0006045751,0.001343752,0.001695748,0.001208624,0.000853636],"category_scores_gemma":[0.03470755,0.0005937871,0.0006559186,0.0006592985,0.00312882,0.00331406,0.001933226,0.001783731,0.0001789902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009357057,"about_ca_system_score_gemma":0.001423779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001623111,"about_ca_topic_score_gemma":0.002427691,"domain_scores_codex":[0.9933089,0.002571205,0.0003749251,0.0009610461,0.002416922,0.0003669973],"domain_scores_gemma":[0.9726977,0.01883802,0.001789896,0.004945518,0.001401301,0.0003276205],"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":[0.001584177,0.0005181816,0.03721983,0.0008403749,0.0003578705,0.001658769,0.002287661,0.3509492,0.1226322,0.09930183,0.002845074,0.3798048],"study_design_scores_gemma":[0.0001247528,0.0007624498,0.004214784,0.0001076178,0.0001420005,0.001185741,0.0002049688,0.8167184,0.1007687,0.07171281,0.003960565,0.00009711801],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4351816,0.0007122447,0.5546521,0.0007131132,0.00004982834,0.0001234593,0.0000872194,0.005007104,0.003473404],"genre_scores_gemma":[0.9102899,0.0001182045,0.08817828,0.0002804601,0.00001216183,0.0000552452,0.00009142952,0.0003617545,0.0006125966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006480064,"threshold_uncertainty_score":0.03427029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0603762164017855,"score_gpt":0.3174931715724063,"score_spread":0.2571169551706208,"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."}}