{"url":"/task/bug-fixing","name":"Bug fixing","slug":"bug-fixing","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":62,"papers_with_code":31,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/swe-bench","name":"SWE-bench-lite","full_name":"","num_papers_in_archive":18}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":31,"tagged_in_all":62,"items":[{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/swe-bench-can-language-models-resolve-real","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","date":"2023-10-10","arxiv_id":"2310.06770","repositories_listed":8,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/autocoderover-autonomous-program-improvement","title":"AutoCodeRover: Autonomous Program Improvement","date":"2024-04-08","arxiv_id":"2404.05427","repositories_listed":5,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/neural-transfer-learning-for-repairing","title":"Neural Transfer Learning for Repairing Security Vulnerabilities in C Code","date":"2021-04-16","arxiv_id":"2104.08308","repositories_listed":3,"syntology":null},{"url":"/paper/swe-agent-agent-computer-interfaces-enable","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","date":"2024-05-06","arxiv_id":"2405.15793","repositories_listed":2,"syntology":null},{"url":"/paper/corecodebench-a-configurable-multi-scenario","title":"CoreCodeBench: A Configurable Multi-Scenario Repository-Level Benchmark","date":"2025-07-04","arxiv_id":"2507.05281","repositories_listed":1,"syntology":null},{"url":"/paper/swe-dev-evaluating-and-training-autonomous","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","date":"2025-05-22","arxiv_id":"2505.16975","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/less-is-more-adaptive-program-repair-with-bug","title":"Less is More: Adaptive Program Repair with Bug Localization and Preference Learning","date":"2025-03-09","arxiv_id":"2503.06510","repositories_listed":1,"syntology":null},{"url":"/paper/repository-level-code-search-with-neural","title":"Repository-level Code Search with Neural Retrieval Methods","date":"2025-02-10","arxiv_id":"2502.07067","repositories_listed":1,"syntology":null},{"url":"/paper/green-code-optimizing-energy-efficiency-in","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","date":"2025-01-19","arxiv_id":"2501.11006","repositories_listed":1,"syntology":null},{"url":"/paper/cornstack-high-quality-contrastive-data-for","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","date":"2024-12-01","arxiv_id":"2412.01007","repositories_listed":1,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/metrex-a-benchmark-for-verilog-code-metric","title":"MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs","date":"2024-11-05","arxiv_id":"2411.03471","repositories_listed":1,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":13}},{"url":"/paper/from-code-to-correctness-closing-the-last","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","date":"2024-10-02","arxiv_id":"2410.01215","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/leveraging-large-language-models-for-15","title":"Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests","date":"2024-08-21","arxiv_id":"2408.11710","repositories_listed":1,"syntology":null},{"url":"/paper/patched-rtc-evaluating-llms-for-diverse","title":"Patched RTC: evaluating LLMs for diverse software development tasks","date":"2024-07-23","arxiv_id":"2407.16557","repositories_listed":1,"syntology":null},{"url":"/paper/coder-issue-resolving-with-multi-agent-and","title":"CodeR: Issue Resolving with Multi-Agent and Task Graphs","date":"2024-06-03","arxiv_id":"2406.01304","repositories_listed":1,"syntology":null},{"url":"/paper/unraveling-code-clone-dynamics-in-deep","title":"Unraveling Code Clone Dynamics in Deep Learning Frameworks","date":"2024-04-25","arxiv_id":"2404.17046","repositories_listed":1,"syntology":null},{"url":"/paper/bug-characterization-in-machine-learning","title":"Bug Characterization in Machine Learning-based Systems","date":"2023-07-26","arxiv_id":"2307.14512","repositories_listed":1,"syntology":null},{"url":"/paper/automating-code-related-tasks-through","title":"Automating Code-Related Tasks Through Transformers: The Impact of Pre-training","date":"2023-02-08","arxiv_id":"2302.04048","repositories_listed":1,"syntology":null},{"url":"/paper/using-developer-discussions-to-guide-fixing","title":"Using Developer Discussions to Guide Fixing Bugs in Software","date":"2022-11-11","arxiv_id":"2211.06335","repositories_listed":1,"syntology":null},{"url":"/paper/adptriage-approximate-dynamic-programming-for","title":"ADPTriage: Approximate Dynamic Programming for Bug Triage","date":"2022-11-02","arxiv_id":"2211.00872","repositories_listed":1,"syntology":null},{"url":"/paper/coditt5-pretraining-for-source-code-and","title":"CoditT5: Pretraining for Source Code and Natural Language Editing","date":"2022-08-10","arxiv_id":"2208.05446","repositories_listed":1,"syntology":null},{"url":"/paper/fixeval-execution-based-evaluation-of-program","title":"FixEval: Execution-based Evaluation of Program Fixes for Programming Problems","date":"2022-06-15","arxiv_id":"2206.07796","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/s-dabt-schedule-and-dependency-aware-bug","title":"S-DABT: Schedule and Dependency-Aware Bug Triage in Open-Source Bug Tracking Systems","date":"2022-04-12","arxiv_id":"2204.05972","repositories_listed":1,"syntology":null},{"url":"/paper/ropgen-towards-robust-code-authorship","title":"RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation","date":"2022-02-12","arxiv_id":"2202.06043","repositories_listed":1,"syntology":null},{"url":"/paper/dabt-a-dependency-aware-bug-triaging-method","title":"DABT: A Dependency-aware Bug Triaging Method","date":"2021-04-26","arxiv_id":"2104.12744","repositories_listed":1,"syntology":null},{"url":"/paper/d2a-a-dataset-built-for-ai-based","title":"D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis","date":"2021-02-16","arxiv_id":"2102.07995","repositories_listed":1,"syntology":null},{"url":"/paper/neural-code-completion-with-anonymized","title":"On the Embeddings of Variables in Recurrent Neural Networks for Source Code","date":"2020-10-23","arxiv_id":"2010.12693","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-approach-for-handling-out-of","title":"A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code","date":"2020-10-23","arxiv_id":"2010.12663","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-study-of-transformers-for-source","title":"Empirical Study of Transformers for Source Code","date":"2020-10-15","arxiv_id":"2010.07987","repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}