{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001099543,0.0001495442,0.0001871535,0.0002874578,0.0002242562,0.00006950423,0.0005308977,0.0001118843,7.19981e-7],"category_scores_gemma":[0.002217167,0.0001240836,0.00005067222,0.000512468,0.00004469928,0.00006664352,0.00002141593,0.0003368476,0.000001212345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004124269,"about_ca_system_score_gemma":0.00006553103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004439291,"about_ca_topic_score_gemma":0.000009082593,"domain_scores_codex":[0.9989079,0.000209602,0.0002071655,0.0003183192,0.00007953326,0.000277537],"domain_scores_gemma":[0.9920557,0.007169219,0.00002814077,0.0006680635,0.00003354188,0.00004536297],"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":[0.00002425565,0.00005702304,0.001834815,0.00005600943,0.00004029771,0.00001836065,0.0002410055,0.0444205,0.0003742957,0.006706925,0.0003516169,0.9458749],"study_design_scores_gemma":[0.003139637,0.0007291164,0.02266729,0.001039095,0.0001149153,0.0001708871,0.00005847477,0.7438399,0.04745443,0.1440485,0.03478801,0.001949709],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003669785,0.0005996084,0.9909579,0.0009103751,0.0005601411,0.0000940335,0.000001046057,0.003200466,0.000006631612],"genre_scores_gemma":[0.1288861,0.00005267529,0.8705463,0.0003648936,0.00001120959,0.00008036626,4.006548e-7,0.000009635844,0.00004843138],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9439252,"threshold_uncertainty_score":0.5059982,"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."}}