{"url":"/task/code-repair","name":"Code Repair","slug":"code-repair","description_markdown":null,"categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":39,"papers_with_code":14,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":9,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/code-repair-on-codexglue-bugs2fix","slug":"code-repair-on-codexglue-bugs2fix","dataset":"CodeXGLUE - Bugs2Fix","dataset_url":"/dataset/codexglue","rows_in_archive":2,"metrics":["Accuracy (medium)","Accuracy (small)","BLEU (medium)","BLEU (small)","CodeBLEU (medium)","CodeBLEU (small)"],"first_row_in_archive_order":{"model":"NSEdit","paper_title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","paper_url":"/paper/fix-bugs-with-transformer-through-a-neural-1","paper_date":"2022-04-13","arxiv_id":"2204.06643","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205},{"url":"/dataset/criticbench","name":"CriticBench","full_name":"","num_papers_in_archive":10},{"url":"/dataset/pytorrent","name":"PyTorrent","full_name":"PyTorrent","num_papers_in_archive":5},{"url":"/dataset/disl","name":"DISL","full_name":"Fueling Research with A Large Dataset of Solidity Smart Contracts","num_papers_in_archive":2},{"url":"/dataset/fixeval","name":"FixEval","full_name":"FixEval","num_papers_in_archive":1},{"url":"/dataset/migration-bench-java-full","name":"migration-bench-java-full","full_name":"","num_papers_in_archive":1},{"url":"/dataset/migration-bench-java-selected","name":"migration-bench-java-selected","full_name":"","num_papers_in_archive":1},{"url":"/dataset/migration-bench-java-utg","name":"migration-bench-java-utg","full_name":"","num_papers_in_archive":1},{"url":"/dataset/performance-improving-code-edits-pie","name":"Performance Improving Code Edits (PIE)","full_name":"Performance Improving Code Edits","num_papers_in_archive":1}],"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":14,"of":14,"tagged_in_all":39,"items":[{"url":"/paper/codexglue-a-machine-learning-benchmark","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","date":"2021-02-09","arxiv_id":"2102.04664","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/octopack-instruction-tuning-code-large","title":"OctoPack: Instruction Tuning Code Large Language Models","date":"2023-08-14","arxiv_id":"2308.07124","repositories_listed":3,"syntology":{"n":13,"n_ran":9,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/learning-performance-improving-code-edits","title":"Learning Performance-Improving Code Edits","date":"2023-02-15","arxiv_id":"2302.07867","repositories_listed":2,"syntology":{"n":19,"n_ran":7,"n_unverified":12,"n_pointer_only":19}},{"url":"/paper/agent-kb-leveraging-cross-domain-experience","title":"Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving","date":"2025-07-08","arxiv_id":"2507.06229","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/why-stop-at-one-error-benchmarking-llms-as","title":"Why Stop at One Error? Benchmarking LLMs as Data Science Code Debuggers for Multi-Hop and Multi-Bug Errors","date":"2025-03-28","arxiv_id":"2503.22388","repositories_listed":1,"syntology":null},{"url":"/paper/fortran2cpp-automating-fortran-to-c-migration","title":"Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration","date":"2024-12-27","arxiv_id":"2412.19770","repositories_listed":1,"syntology":null},{"url":"/paper/2409-12993","title":"CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair","date":"2024-09-19","arxiv_id":"2409.12993","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-the-code-debugging-ability-of-llms","title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","date":"2024-08-09","arxiv_id":"2408.05006","repositories_listed":1,"syntology":null},{"url":"/paper/code-agents-are-state-of-the-art-software","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","date":"2024-06-18","arxiv_id":"2406.12952","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/autocoder-enhancing-code-large-language-model","title":"AutoCoder: Enhancing Code Large Language Model with \\textsc{AIEV-Instruct}","date":"2024-05-23","arxiv_id":"2405.14906","repositories_listed":1,"syntology":null},{"url":"/paper/intervenor-prompt-the-coding-ability-of-large","title":"INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair","date":"2023-11-16","arxiv_id":"2311.09868","repositories_listed":1,"syntology":null},{"url":"/paper/guiding-language-models-of-code-with-global","title":"Guiding Language Models of Code with Global Context using Monitors","date":"2023-06-19","arxiv_id":"2306.10763","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/break-it-fix-it-unsupervised-learning-for","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","date":"2021-06-11","arxiv_id":"2106.06600","repositories_listed":1,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/macer-a-modular-framework-for-accelerated","title":"MACER: A Modular Framework for Accelerated Compilation Error Repair","date":"2020-05-28","arxiv_id":"2005.14015","repositories_listed":1,"syntology":null}],"syntology_records":7,"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"}}