{"id":"W4414153585","doi":"10.1145/3767167","title":"The Havoc Paradox in Generator-Based Fuzzing—RCR Report","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Artifact (error); Scripting language; Exploit; Affect (linguistics)","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":[0.0129881,0.0006652682,0.0007177486,0.001617184,0.001051289,0.003371084,0.001903411,0.001537282,0.007140625],"category_scores_gemma":[0.06136585,0.0005465377,0.0006819622,0.001057497,0.00211809,0.004478761,0.001850485,0.00308384,0.001324555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001557609,"about_ca_system_score_gemma":0.002062046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002395442,"about_ca_topic_score_gemma":0.001704968,"domain_scores_codex":[0.9866027,0.003879874,0.0007648928,0.001202615,0.007121109,0.0004288488],"domain_scores_gemma":[0.9410555,0.03571466,0.001952209,0.01407494,0.00662064,0.0005820506],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008827287,0.0008168563,0.003935068,0.0007631406,0.000151809,0.0008914797,0.001945444,0.04385675,0.03729241,0.5345412,0.07382233,0.3011008],"study_design_scores_gemma":[0.0002803568,0.001195467,0.003020214,0.0004032912,0.0001664922,0.001703991,0.0004801723,0.3743838,0.2436597,0.257823,0.1165621,0.0003214055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09683044,0.001577508,0.8334335,0.009699812,0.00207708,0.0004010484,0.001003293,0.01171856,0.04325882],"genre_scores_gemma":[0.5992621,0.001237272,0.3783661,0.001882848,0.0006092952,0.0004056007,0.001571725,0.002737642,0.01392743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0129881,"threshold_uncertainty_score":0.06868851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04416990580043428,"score_gpt":0.3086626128790792,"score_spread":0.2644927070786449,"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."}}