{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007373025,0.0001108733,0.000139365,0.0001609446,0.0002600652,0.00003689207,0.0003758417,0.00008422513,0.000001511616],"category_scores_gemma":[0.0004364254,0.0000937772,0.00004772858,0.0004789313,0.00004310868,0.00006783022,0.00001453431,0.0002471501,0.000001858562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003599487,"about_ca_system_score_gemma":0.00008333899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002677031,"about_ca_topic_score_gemma":0.00001315503,"domain_scores_codex":[0.9990843,0.0001119571,0.0002238337,0.0003048811,0.00007113532,0.0002039138],"domain_scores_gemma":[0.9970869,0.002153463,0.0000297123,0.0006497352,0.00003588844,0.00004430578],"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":[0.00002664581,0.0002171869,0.00122072,0.00006020526,0.0001076176,0.0000797916,0.00028906,0.3534743,0.001740415,0.0832514,0.0004160286,0.5591167],"study_design_scores_gemma":[0.002452699,0.0002934229,0.05801647,0.0002119255,0.00009652975,0.0005360948,0.0001431824,0.6139586,0.01684946,0.03912811,0.2670745,0.001238972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004070389,0.0005121166,0.9920315,0.002575122,0.000485923,0.0001083788,0.000002255679,0.0002012738,0.00001302912],"genre_scores_gemma":[0.04340915,0.00009353484,0.9557883,0.0002156022,0.00002147871,0.0001722625,0.000001876227,0.000006977837,0.0002908536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5578777,"threshold_uncertainty_score":0.3824123,"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."}}