{"total":75,"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":"2110.10234","title":"Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Process","created":"2021-10-19","cited_by_count":56,"area":null},{"id":"2112.11255","title":"Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems","created":"2021-12-21","cited_by_count":37,"area":null},{"id":"2107.06997","title":"DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search","created":"2021-07-05","cited_by_count":29,"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":"2103.09783","title":"Characterizing Technical Debt and Antipatterns in AI-Based Systems: A Systematic Mapping Study","created":"2021-03-17","cited_by_count":21,"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":"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":"2212.11368","title":"When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study","created":"2022-12-21","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":"2305.12751","title":"Testing of Deep Reinforcement Learning Agents with Surrogate Models","created":"2023-05-22","cited_by_count":13,"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":"2404.18573","title":"Predicting Safety Misbehaviours in Autonomous Driving Systems using Uncertainty Quantification","created":"2024-04-29","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":"2201.05077","title":"Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering","created":"2022-01-13","cited_by_count":8,"area":null},{"id":"2203.13746","title":"Code Smells for Machine Learning Applications","created":"2022-03-25","cited_by_count":8,"area":null},{"id":"2207.10495","title":"Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testing","created":"2022-07-21","cited_by_count":8,"area":null},{"id":"2208.08982","title":"Quality issues in Machine Learning Software Systems","created":"2022-08-18","cited_by_count":7,"area":null},{"id":"2210.00859","title":"Requirements Engineering for Machine Learning: A Review and Reflection","created":"2022-10-03","cited_by_count":7,"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":"2309.05067","title":"Mutation-based Fault Localization of Deep Neural Networks","created":"2023-09-10","cited_by_count":5,"area":null},{"id":"2301.05651","title":"Mutation Testing of Deep Reinforcement Learning Based on Real Faults","created":"2023-01-13","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":"2508.12285","title":"\"My productivity is boosted, but ...\" Demystifying Users' Perception on AI Coding Assistants","created":"2025-08-17","cited_by_count":4,"area":null},{"id":"2211.00471","title":"Exploring Effects of Computational Parameter Changes to Image Recognition Systems","created":"2022-11-01","cited_by_count":3,"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":"2306.06208","title":"DeltaNN: Assessing the Impact of Computational Environment Parameters on the Performance of Image Recognition Models","created":"2023-06-05","cited_by_count":3,"area":null},{"id":"2306.07995","title":"Semantic-Based Neural Network Repair","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2309.03617","title":"NeuroCodeBench: a plain C neural network benchmark for software verification","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2405.08848","title":"Automated Repair of AI Code with Large Language Models and Formal Verification","created":"2024-05-14","cited_by_count":3,"area":null},{"id":"2408.06258","title":"Targeted Deep Learning System Boundary Testing","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2409.16559","title":"Demystifying Issues, Causes and Solutions in LLM Open-Source Projects","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2502.09460","title":"Metamorphic Testing for Pose Estimation Systems","created":"2025-02-13","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":"2204.00694","title":"Testing Feedforward Neural Networks Training Programs","created":"2022-04-01","cited_by_count":2,"area":null},{"id":"2209.01566","title":"Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables","created":"2022-09-04","cited_by_count":2,"area":null},{"id":"2210.05876","title":"Statistical Modeling of Soft Error Influence on Neural Networks","created":"2022-10-12","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":"2105.01407","title":"A Review on Oracle Issues in Machine Learning","created":"2021-05-04","cited_by_count":1,"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":"2407.05466","title":"Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality","created":"2024-07-07","cited_by_count":1,"area":null},{"id":"2410.24214","title":"ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2502.02910","title":"DANDI: Diffusion as Normative Distribution for Deep Neural Network Input","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2503.08936","title":"Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2504.01248","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2506.15084","title":"An Empirical Study of Bugs in Data Visualization Libraries","created":"2025-06-18","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":"2105.01404","title":"TimeGym: Debugging for Time Series Modeling in Python","created":"2021-05-04","cited_by_count":0,"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":"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":"2306.01697","title":"Exploring Robustness of Image Recognition Models on Hardware Accelerators","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2306.15007","title":"Quality Issues in Machine Learning Software Systems","created":"2023-06-26","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":"2411.02450","title":"Assessing Superposition-Targeted Coverage Criteria for Quantum Neural Networks","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2412.11304","title":"An Empirical Study of Fault Localisation Techniques for Deep Learning","created":"2024-12-15","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":"2602.15552","title":"Latent Regularization in Generative Test Input Generation","created":"2026-02-17","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":"2604.28118","title":"Hierarchical Fault Detection and Diagnosis for Transformer Architectures","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.09957","title":"Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics","created":"2026-06-08","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":"2607.19621","title":"Understanding Developer Pain Points in Federated Learning: Insights from Stack Overflow and GitHub","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.35812","title":"Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.36525","title":"Reliability Testing of Medical Model Performance under Distributed Deployment","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}