{"id":"W4401635890","doi":"10.1145/3688838","title":"History-Driven Fuzzing for Deep Learning Libraries","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Fuzz testing; Computer science; Heuristic; Artificial intelligence; Set (abstract data type); Machine learning; Natural language processing; Programming language; 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":[0.0005353583,0.0001744863,0.00022486,0.0002886657,0.000163709,0.00008142636,0.0003729527,0.00013483,0.00001749153],"category_scores_gemma":[0.001526396,0.0001806173,0.00009516114,0.000187713,0.0000401505,0.0003908576,0.00002949086,0.0005657572,0.000005226678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008673824,"about_ca_system_score_gemma":0.00004901662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006819412,"about_ca_topic_score_gemma":9.186228e-7,"domain_scores_codex":[0.9988785,0.0001588607,0.0001689299,0.0004287953,0.0000861159,0.0002788192],"domain_scores_gemma":[0.9945977,0.004979262,0.00002648955,0.0002951187,0.00002532508,0.00007607701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001314493,0.000008183489,0.0000288086,0.0001630151,0.00008147241,0.00001373008,0.002471307,0.5958008,0.0003971323,0.02356124,0.00003345202,0.3774277],"study_design_scores_gemma":[0.0002716735,0.0002096303,0.0001322865,0.00009534123,0.00005781715,0.0000869044,0.00006611987,0.8775653,0.0005021601,0.002747022,0.1179093,0.0003563819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004905063,0.002176964,0.993121,0.0003072455,0.002297083,0.0001039089,0.000001247152,0.001489794,0.00001221737],"genre_scores_gemma":[0.03438346,0.00007055617,0.9649102,0.00006768798,0.0001084102,0.00005924436,0.000002304459,0.0000369857,0.000361141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3770714,"threshold_uncertainty_score":0.7365359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06773932218144975,"score_gpt":0.2985530311061435,"score_spread":0.2308137089246937,"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."}}