{"total":32,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"id":"2107.08760","title":"CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Software","created":"2021-07-19","cited_by_count":91,"area":null},{"id":"2105.12787","title":"Self-Supervised Bug Detection and Repair","created":"2021-05-26","cited_by_count":59,"area":null},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49,"area":null},{"id":"2303.11455","title":"Large Language Models and Simple, Stupid Bugs","created":"2023-03-20","cited_by_count":45,"area":null},{"id":"2306.17193","title":"Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection","created":"2023-06-28","cited_by_count":30,"area":null},{"id":"2306.03438","title":"Large Language Models of Code Fail at Completing Code with Potential Bugs","created":"2023-06-06","cited_by_count":29,"area":null},{"id":"2108.06645","title":"On Multi-Modal Learning of Editing Source Code","created":"2021-08-15","cited_by_count":25,"area":null},{"id":"2106.03353","title":"Understanding Neural Code Intelligence Through Program Simplification","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2106.08704","title":"Memorization and Generalization in Neural Code Intelligence Models","created":"2021-06-16","cited_by_count":19,"area":null},{"id":"2204.10049","title":"On Distribution Shift in Learning-based Bug Detectors","created":"2022-04-21","cited_by_count":15,"area":null},{"id":"2203.03771","title":"Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2304.01102","title":"RunBugRun -- An Executable Dataset for Automated Program Repair","created":"2023-04-03","cited_by_count":11,"area":null},{"id":"2211.14875","title":"Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5","created":"2022-11-27","cited_by_count":10,"area":null},{"id":"2110.04353","title":"Learning to Describe Solutions for Bug Reports Based on Developer Discussions","created":"2021-10-08","cited_by_count":5,"area":null},{"id":"2311.00931","title":"Learning Defect Prediction from Unrealistic Data","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2312.04986","title":"Out of Context: How important is Local Context in Neural Program Repair?","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2509.04078","title":"RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models","created":"2025-09-04","cited_by_count":5,"area":null},{"id":"2207.00301","title":"Can we learn from developer mistakes? Learning to localize and repair real bugs from real bug fixes","created":"2022-07-01","cited_by_count":4,"area":null},{"id":"2302.03924","title":"CCRep: Learning Code Change Representations via Pre-Trained Code Model and Query Back","created":"2023-02-08","cited_by_count":3,"area":null},{"id":"2502.13966","title":"Where's the Bug? Attention Probing for Scalable Fault Localization","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2212.09132","title":"JEMMA: An Extensible Java Dataset for ML4Code Applications","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2106.06110","title":"Assessing the Effectiveness of Syntactic Structure to Learn Code Edit Representations","created":"2021-06-11","cited_by_count":1,"area":null},{"id":"2308.08943","title":"Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2312.10448","title":"Exploring Large Language Models in Resolving Environment-Related Crash Bugs: Localizing and Repairing","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2409.05177","title":"Insights from Benchmarking Frontier Language Models on Web App Code Generation","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2107.06657","title":"DeepMutants: Training neural bug detectors with contextual mutations","created":"2021-07-14","cited_by_count":0,"area":null},{"id":"2207.10739","title":"BigIssue: A Realistic Bug Localization Benchmark","created":"2022-07-21","cited_by_count":0,"area":null},{"id":"2307.13014","title":"Graph Neural Networks For Mapping Variables Between Programs -- Extended Version","created":"2023-07-24","cited_by_count":0,"area":null},{"id":"2312.12492","title":"CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code","created":"2023-12-20","cited_by_count":0,"area":null}],"next_cursor":null}