{"total":33,"rows":[{"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":"2103.12535","title":"NNrepair: Constraint-based Repair of Neural Network Classifiers","created":"2021-03-23","cited_by_count":26,"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":"2108.04214","title":"Neural Network Repair with Reachability Analysis","created":"2021-08-09","cited_by_count":19,"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":"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":"2105.08095","title":"Automatic Fault Detection for Deep Learning Programs Using Graph Transformations","created":"2021-05-17","cited_by_count":9,"area":null},{"id":"2112.03395","title":"Manas: Mining Software Repositories to Assist AutoML","created":"2021-12-06","cited_by_count":5,"area":null},{"id":"2301.11912","title":"OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks","created":"2023-01-27","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":"2103.00124","title":"NEUROSPF: A tool for the Symbolic Analysis of Neural Networks","created":"2021-02-27","cited_by_count":4,"area":null},{"id":"2310.06800","title":"Test & Evaluation Best Practices for Machine Learning-Enabled Systems","created":"2023-10-10","cited_by_count":4,"area":null},{"id":"2306.07995","title":"Semantic-Based Neural Network Repair","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2312.15101","title":"FetaFix: Automatic Fault Localization and Repair of Deep Learning Model Conversions","created":"2023-12-22","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":"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":"2202.03055","title":"Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods","created":"2022-02-07","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":"2203.13612","title":"Repairing Group-Level Errors for DNNs Using Weighted Regularization","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2304.02813","title":"Causal Repair of Learning-enabled Cyber-physical Systems","created":"2023-04-06","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":"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":"2509.15815","title":"GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworks","created":"2025-09-19","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}],"next_cursor":null}