{"total":56,"rows":[{"id":"2105.01984","title":"Software Engineering for AI-Based Systems: A Survey","created":"2021-05-05","cited_by_count":69,"area":null},{"id":"2407.06153","title":"What's Wrong with Your Code Generated by Large Language Models? An Extensive Study","created":"2024-07-08","cited_by_count":53,"area":null},{"id":"2106.06054","title":"Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline","created":"2021-06-02","cited_by_count":49,"area":null},{"id":"2112.13314","title":"Silent Bugs in Deep Learning Frameworks: An Empirical Study of Keras and TensorFlow","created":"2021-12-26","cited_by_count":25,"area":null},{"id":"2101.04930","title":"An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications","created":"2021-01-13","cited_by_count":20,"area":null},{"id":"2112.04036","title":"DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs","created":"2021-12-07","cited_by_count":19,"area":null},{"id":"2101.00135","title":"Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach","created":"2021-01-01","cited_by_count":18,"area":null},{"id":"2205.01938","title":"DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs","created":"2022-05-04","cited_by_count":16,"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":"2109.07514","title":"DeepMetis: Augmenting a Deep Learning Test Set to Increase its Mutation Score","created":"2021-09-15","cited_by_count":12,"area":null},{"id":"2112.01771","title":"Understanding Performance Problems in Deep Learning Systems","created":"2021-12-03","cited_by_count":12,"area":null},{"id":"2303.07476","title":"Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer Vision","created":"2023-03-13","cited_by_count":11,"area":null},{"id":"2107.02279","title":"Design Smells in Deep Learning Programs: An Empirical Study","created":"2021-07-05","cited_by_count":10,"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":"2105.08095","title":"Automatic Fault Detection for Deep Learning Programs Using Graph Transformations","created":"2021-05-17","cited_by_count":9,"area":null},{"id":"2203.13746","title":"Code Smells for Machine Learning Applications","created":"2022-03-25","cited_by_count":8,"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":"2105.10197","title":"Yes We Care! -- Certification for Machine Learning Methods through the Care Label Framework","created":"2021-05-21","cited_by_count":5,"area":null},{"id":"2112.03395","title":"Manas: Mining Software Repositories to Assist AutoML","created":"2021-12-06","cited_by_count":5,"area":null},{"id":"2309.05067","title":"Mutation-based Fault Localization of Deep Neural Networks","created":"2023-09-10","cited_by_count":5,"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":"2203.10384","title":"Data Smells: Categories, Causes and Consequences, and Detection of Suspicious Data in AI-based Systems","created":"2022-03-19","cited_by_count":4,"area":null},{"id":"2205.12095","title":"DNNAbacus: Toward Accurate Computational Cost Prediction for Deep Neural Networks","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2301.13476","title":"An investigation of challenges encountered when specifying training data and runtime monitors for safety critical ML applications","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2502.18726","title":"Deep-Bench: Deep Learning Benchmark Dataset for Code Generation","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2601.13655","title":"Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2601.16809","title":"Will It Survive? Deciphering the Fate of AI-Generated Code in Open Source","created":"2026-01-23","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":"2203.12697","title":"What is Software Quality for AI Engineers? Towards a Thinning of the Fog","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2204.00694","title":"Testing Feedforward Neural Networks Training Programs","created":"2022-04-01","cited_by_count":2,"area":null},{"id":"2204.08702","title":"Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review","created":"2022-04-19","cited_by_count":2,"area":null},{"id":"2211.15733","title":"An Empirical Study of Library Usage and Dependency in Deep Learning Frameworks","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2307.14465","title":"What Kinds of Contracts Do ML APIs Need?","created":"2023-07-26","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":"2401.14628","title":"Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment","created":"2024-01-26","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":"2510.21048","title":"xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2601.03988","title":"Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures","created":"2026-01-07","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":"2303.02695","title":"Understanding Bugs in Multi-Language Deep Learning Frameworks","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2303.17708","title":"Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem","created":"2023-03-30","cited_by_count":0,"area":null},{"id":"2304.12857","title":"What Causes Exceptions in Machine Learning Applications? Mining Machine Learning-Related Stack Traces on Stack Overflow","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2308.05014","title":"A Comprehensive Empirical Study of Bugs in Open-Source Federated Learning Frameworks","created":"2023-08-09","cited_by_count":0,"area":null},{"id":"2312.01588","title":"ActiveClean: Generating Line-Level Vulnerability Data via Active Learning","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2401.03653","title":"An Exploratory Study on Automatic Identification of Assumptions in the Development of Deep Learning Frameworks","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2402.16546","title":"Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects","created":"2024-02-26","cited_by_count":0,"area":null},{"id":"2406.08688","title":"On Security Weaknesses and Vulnerabilities in Deep Learning Systems","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2504.03887","title":"Accurate GPU Memory Prediction for Deep Learning Jobs through Dynamic Analysis","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2504.05424","title":"Speculative Automated Refactoring of Imperative Deep Learning Programs to Graph Execution","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2509.03242","title":"TopoMap: A Feature-based Semantic Discriminator of the Topographical Regions in the Test Input Space","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2509.15815","title":"GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworks","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2604.28118","title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.26492","title":"Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.12868","title":"Deep4ge: DNN Training Trajectories for Fault Detection and Diagnosis","created":"2026-07-14","cited_by_count":0,"area":null}],"next_cursor":null}