{"id":"W4409478867","doi":"10.1145/3729533","title":"Evaluating API-Level Deep Learning Fuzzers: A Comprehensive Benchmarking Study","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Benchmarking; Deep learning; Artificial intelligence; Software engineering; Machine learning; Data science","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":[0.007018362,0.00308005,0.001052936,0.003678215,0.0007700109,0.001448474,0.004386404,0.002234072,0.001452719],"category_scores_gemma":[0.03009481,0.0006796612,0.001443988,0.002498642,0.001856058,0.004100663,0.002435804,0.002331894,0.0008554612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003118305,"about_ca_system_score_gemma":0.002320378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0141455,"about_ca_topic_score_gemma":0.02000809,"domain_scores_codex":[0.9917892,0.002103047,0.0008392225,0.001982224,0.002764398,0.0005219729],"domain_scores_gemma":[0.9831149,0.008782233,0.001248773,0.003335847,0.00297011,0.0005481397],"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":[0.002279923,0.002254241,0.1026521,0.004724312,0.001681474,0.0008365897,0.0005248272,0.362907,0.01952172,0.006069791,0.07874124,0.4178069],"study_design_scores_gemma":[0.0004791942,0.001976453,0.03011208,0.0005193504,0.0003880577,0.0009117238,0.0003359226,0.8946992,0.04193434,0.005906337,0.02257733,0.000160201],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8858414,0.01619782,0.0482523,0.001942447,0.0007000447,0.0005478522,0.01190225,0.02548311,0.009132816],"genre_scores_gemma":[0.8662659,0.002219886,0.08192795,0.001257141,0.0001201448,0.0003378541,0.04424416,0.001033261,0.002593739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0141455,"threshold_uncertainty_score":0.03711706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1624685076286059,"score_gpt":0.392204384378163,"score_spread":0.2297358767495571,"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."}}