{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004813405,0.0001623931,0.0002059889,0.0003478197,0.0003173624,0.00009894692,0.0003042371,0.0001243404,0.000003782877],"category_scores_gemma":[0.002561527,0.0001660966,0.00007797978,0.0003618675,0.00002899441,0.0001368932,0.00001896421,0.0002301412,0.000003160766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002092215,"about_ca_system_score_gemma":0.00002864066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008199107,"about_ca_topic_score_gemma":9.818601e-7,"domain_scores_codex":[0.9989687,0.000123654,0.0001699963,0.0003569888,0.00009146654,0.0002891776],"domain_scores_gemma":[0.99368,0.005823122,0.00003756971,0.0003486311,0.00003763375,0.00007304002],"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":[0.00002917692,0.00004951024,0.0005130207,0.0001694539,0.00009126016,0.00001130847,0.001127455,0.3252201,0.002896944,0.006522725,0.0004763269,0.6628927],"study_design_scores_gemma":[0.0003513366,0.0002408626,0.0004835498,0.00003724261,0.00002469464,0.00001541059,0.000008718038,0.9807503,0.007069388,0.009779502,0.0009468533,0.0002920987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003663086,0.00006648527,0.9819157,0.0002667268,0.0006297991,0.0001212765,0.000003245392,0.01333275,9.469452e-7],"genre_scores_gemma":[0.1374447,0.00001598521,0.8621575,0.0000859865,0.00006850307,0.0001455968,0.00001225138,0.00002500771,0.00004446302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6626006,"threshold_uncertainty_score":0.6773221,"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."}}