{"id":"W4402527174","doi":"10.1145/3678722.3685529","title":"The Havoc Paradox in Generator-Based Fuzzing (Registered Report)","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fuzz testing; Generator (circuit theory); Computer science; Computer security; Programming language; Physics; Power (physics); Software","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":[0.0009141166,0.0001008772,0.00008760861,0.0000942916,0.0001190712,0.0005954515,0.0005776185,0.00004121941,0.000002334504],"category_scores_gemma":[0.0003501041,0.00006482642,0.00004960964,0.000461996,0.00003670434,0.0001418156,0.0001167991,0.0001417384,0.00001987992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004918791,"about_ca_system_score_gemma":0.0001414002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001439651,"about_ca_topic_score_gemma":0.00004456084,"domain_scores_codex":[0.9988934,0.00005402206,0.0002614996,0.0003684224,0.0001930684,0.0002296079],"domain_scores_gemma":[0.9984674,0.0005957322,0.00003966723,0.0008250085,0.00003093787,0.0000412302],"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":[0.000007225471,0.00007705111,0.01366695,0.00008744965,0.00002438091,0.005701806,0.0005859627,0.0002658986,0.0006560555,0.1268308,0.3654848,0.4866116],"study_design_scores_gemma":[0.0001361337,0.00006125036,0.001614129,0.0002647598,0.000004013862,0.000351982,0.000005180706,0.8431059,0.00398215,0.09493551,0.05518154,0.000357459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004855185,0.001342059,0.9676754,0.004711729,0.0006378748,0.000132352,2.942091e-7,0.01704064,0.003604492],"genre_scores_gemma":[0.7968248,0.000007045437,0.2017356,0.0005090981,0.00006739801,0.00004131119,0.000001032081,0.00001180277,0.000801954],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.84284,"threshold_uncertainty_score":0.5741953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03655997503584939,"score_gpt":0.2985628603687788,"score_spread":0.2620028853329294,"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."}}