{"id":"W4387735187","doi":"10.1145/3628159","title":"Generation-based Differential Fuzzing for Deep Learning Libraries","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Fuzz testing; Computer science; Context (archaeology); Task (project management); Machine learning; Artificial intelligence; Deep learning; Benchmark (surveying); Software engineering; Software; Programming language","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":[0.00228105,0.001330648,0.0008500577,0.001523887,0.000621232,0.001001271,0.002987944,0.001482949,0.002239019],"category_scores_gemma":[0.01137237,0.0006433474,0.001473339,0.0006277882,0.001869508,0.002814895,0.001957968,0.001946809,0.0003441439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002247744,"about_ca_system_score_gemma":0.002416784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005240703,"about_ca_topic_score_gemma":0.00760902,"domain_scores_codex":[0.9977336,0.0005484808,0.0001882298,0.0005739673,0.0006290601,0.000326608],"domain_scores_gemma":[0.9938128,0.003779516,0.0005130239,0.0009491626,0.00078264,0.0001629168],"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":[0.0005557142,0.0004470185,0.02044728,0.0004871466,0.00015043,0.0009470911,0.0004232125,0.5034314,0.03103651,0.01902429,0.004043676,0.4190061],"study_design_scores_gemma":[0.00003584103,0.0001036261,0.0006717679,0.00002772432,0.00003169253,0.0001152516,0.0000287752,0.9716476,0.01359406,0.01287064,0.0008554857,0.00001743638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2513656,0.00085195,0.7299873,0.000796113,0.0000990101,0.0003395923,0.0004245159,0.01276476,0.003371082],"genre_scores_gemma":[0.840384,0.0001283573,0.1563373,0.0004944555,0.00001989162,0.0002080529,0.000596958,0.0003387093,0.001492106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005240703,"threshold_uncertainty_score":0.01630867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1405989980981405,"score_gpt":0.3234042528417899,"score_spread":0.1828052547436493,"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."}}