{"total":23,"rows":[{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"area":null},{"id":"2408.05148","title":"Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications","created":"2024-08-09","cited_by_count":24,"area":null},{"id":"2206.12311","title":"Bugs in Machine Learning-based Systems: A Faultload Benchmark","created":"2022-06-24","cited_by_count":15,"area":null},{"id":"2404.10304","title":"LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2307.14512","title":"Bug Characterization in Machine Learning-based Systems","created":"2023-07-26","cited_by_count":10,"area":null},{"id":"2407.00125","title":"A Survey on Failure Analysis and Fault Injection in AI Systems","created":"2024-06-28","cited_by_count":10,"area":null},{"id":"2401.03069","title":"Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2404.17871","title":"Deep Learning Library Testing: Definition, Methods and Challenges","created":"2024-04-27","cited_by_count":5,"area":null},{"id":"2406.07944","title":"Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2208.01508","title":"COMET: Coverage-guided Model Generation For Deep Learning Library Testing","created":"2022-08-02","cited_by_count":4,"area":null},{"id":"2310.07715","title":"To Build Our Future, We Must Know Our Past: Contextualizing Paradigm Shifts in Natural Language Processing","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2302.06086","title":"Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects","created":"2023-02-13","cited_by_count":3,"area":null},{"id":"2201.09953","title":"Challenges in Migrating Imperative Deep Learning Programs to Graph Execution: An Empirical Study","created":"2022-01-24","cited_by_count":2,"area":null},{"id":"2404.17046","title":"Unraveling Code Clone Dynamics in Deep Learning Frameworks","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2307.13777","title":"An Empirical Study on Bugs Inside PyTorch: A Replication Study","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2505.05777","title":"PyResBugs: A Dataset of Residual Python Bugs for Natural Language-Driven Fault Injection","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2506.09280","title":"TTrace: Lightweight Error Checking and Diagnosis for Distributed Training","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2508.04925","title":"Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2209.09932","title":"Comparative analysis of real bugs in open-source Machine Learning projects -- A Registered Report","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2509.10694","title":"Verifying Computational Graphs in Production-Grade Distributed Machine Learning Frameworks","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2604.08720","title":"Demystifying the Silence of Correctness Bugs in PyTorch Compiler","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2607.21797","title":"Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.22991","title":"Silent Failures Beyond the 32-Bit Index Range: A Differential Characterization of Large-Tensor Matrix Multiplication in PyTorch's MPS Backend","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}