{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/program-repair","name":"Program Repair","slug":"program-repair","description_markdown":"Task of teaching ML models to modify an existing program to fix a bug in a given code.","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":132,"papers_with_code":52,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":6,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/program-repair-on-deepfix","slug":"program-repair-on-deepfix","dataset":"DeepFix","dataset_url":"/dataset/deepfix","rows_in_archive":4,"metrics":["Average Success Rate"],"first_row_in_archive_order":{"model":"DrRepair + BIFI","paper_title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","paper_url":"/paper/break-it-fix-it-unsupervised-learning-for","paper_date":"2021-06-11","arxiv_id":"2106.06600","code_links":[{"title":"michiyasunaga/bifi","url":"https://github.com/michiyasunaga/bifi"}],"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/break-it-fix-it-unsupervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.06600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06600"}},"official":{"repos":["michiyasunaga/bifi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/program-repair-on-github-python","slug":"program-repair-on-github-python","dataset":"GitHub-Python","dataset_url":"/dataset/github-python","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"Transformer + BIFI","paper_title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","paper_url":"/paper/break-it-fix-it-unsupervised-learning-for","paper_date":"2021-06-11","arxiv_id":"2106.06600","code_links":[{"title":"michiyasunaga/bifi","url":"https://github.com/michiyasunaga/bifi"}],"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/break-it-fix-it-unsupervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.06600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06600"}},"official":{"repos":["michiyasunaga/bifi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/program-repair-on-humanevalpack","slug":"program-repair-on-humanevalpack","dataset":"HumanEvalPack","dataset_url":"/dataset/humanevalpack","rows_in_archive":1,"metrics":["Pass@1"],"first_row_in_archive_order":{"model":"MGDebugger (DeepSeek-Coder-V2-Lite)","paper_title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","paper_url":"/paper/from-code-to-correctness-closing-the-last","paper_date":"2024-10-02","arxiv_id":"2410.01215","code_links":[{"title":"YerbaPage/MGDebugger","url":"https://github.com/YerbaPage/MGDebugger"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/from-code-to-correctness-closing-the-last#ran","syntology_url":"https://syntology.ai/paper/2410.01215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01215"}},"official":{"repos":["YerbaPage/MGDebugger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/program-repair-on-tfix-s-code-patches-data","slug":"program-repair-on-tfix-s-code-patches-data","dataset":"TFix's Code Patches Data","dataset_url":"/dataset/tfix-s-code-patch-data","rows_in_archive":1,"metrics":["Error Removal","Exact Match"],"first_row_in_archive_order":{"model":"TFix","paper_title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","paper_url":"/paper/tfix-learning-to-fix-coding-errors-with-a","paper_date":"2021-07-18","arxiv_id":null,"code_links":[{"title":"eth-sri/TFix","url":"https://github.com/eth-sri/TFix"}],"syntology":null}}],"datasets":[{"url":"/dataset/deepfix","name":"DeepFix","full_name":"","num_papers_in_archive":38},{"url":"/dataset/humanevalpack","name":"HumanEvalPack","full_name":"HumanEvalPack","num_papers_in_archive":26},{"url":"/dataset/manysstubs4j","name":"ManySStuBs4J","full_name":"","num_papers_in_archive":22},{"url":"/dataset/xcodeeval","name":"xCodeEval","full_name":"xCodeEval","num_papers_in_archive":15},{"url":"/dataset/defects4j","name":"Defects4J","full_name":"Defects4J","num_papers_in_archive":9},{"url":"/dataset/codrep","name":"CodRep","full_name":"","num_papers_in_archive":7},{"url":"/dataset/github-python","name":"GitHub-Python","full_name":"","num_papers_in_archive":5},{"url":"/dataset/eth-py150-open","name":"ETH Py150 Open","full_name":"","num_papers_in_archive":3},{"url":"/dataset/tfix-s-code-patch-data","name":"TFix's Code Patches Data","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/exception-type","name":"Exception type"},{"url":"/task/fault-localization","name":"Fault localization"},{"url":"/task/function-docstring-mismatch","name":"Function-docstring mismatch"},{"url":"/task/swapped-operands","name":"Swapped operands"},{"url":"/task/variable-misuse","name":"Variable misuse"},{"url":"/task/wrong-binary-operator","name":"Wrong binary operator"}],"parent_tasks":[{"url":"/task/program-synthesis","name":"Program Synthesis"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":132,"of_with_code":52,"tagged_in_all":132,"counts":{"archive_papers_tagged":132,"with_a_code_link":52,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":132,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/autocoderover-autonomous-program-improvement","slug":"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":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autocoderover-autonomous-program-improvement#ran","syntology_url":"https://syntology.ai/paper/2404.05427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05427"}},"official":{"repos":["nus-apr/auto-code-rover"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/agentless-demystifying-llm-based-software","slug":"agentless-demystifying-llm-based-software","title":"Agentless: Demystifying LLM-based Software Engineering Agents","date":"2024-07-01","arxiv_id":"2407.01489","repositories_listed":4,"syntology":{"n":24,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/agentless-demystifying-llm-based-software#ran","syntology_url":"https://syntology.ai/paper/2407.01489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01489"}},"official":{"repos":["OpenAutoCoder/Agentless"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/xcodeeval-a-large-scale-multilingual","slug":"xcodeeval-a-large-scale-multilingual","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","date":"2023-03-06","arxiv_id":"2303.03004","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xcodeeval-a-large-scale-multilingual#ran","syntology_url":"https://syntology.ai/paper/2303.03004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03004"}},"official":{"repos":["ntunlp/xCodeEval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["named_in_paper","official"]}}},{"url":"/paper/c-pack-of-ipas-a-c90-program-benchmark-of","slug":"c-pack-of-ipas-a-c90-program-benchmark-of","title":"C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments","date":"2022-06-17","arxiv_id":"2206.08768","repositories_listed":3,"syntology":null},{"url":"/paper/repairbench-leaderboard-of-frontier-models","slug":"repairbench-leaderboard-of-frontier-models","title":"RepairBench: Leaderboard of Frontier Models for Program Repair","date":"2024-09-27","arxiv_id":"2409.18952","repositories_listed":2,"syntology":null},{"url":"/paper/hyperagent-generalist-software-engineering","slug":"hyperagent-generalist-software-engineering","title":"HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale","date":"2024-09-09","arxiv_id":"2409.16299","repositories_listed":2,"syntology":null},{"url":"/paper/teaching-large-language-models-to-self-debug","slug":"teaching-large-language-models-to-self-debug","title":"Teaching Large Language Models to Self-Debug","date":"2023-04-11","arxiv_id":"2304.05128","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/teaching-large-language-models-to-self-debug#ran","syntology_url":"https://syntology.ai/paper/2304.05128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05128"}},"official":null}},{"url":"/paper/exploring-plausible-patches-using-source-code","slug":"exploring-plausible-patches-using-source-code","title":"Exploring Plausible Patches Using Source Code Embeddings in JavaScript","date":"2021-03-31","arxiv_id":"2103.16846","repositories_listed":2,"syntology":null},{"url":"/paper/unified-pre-training-for-program","slug":"unified-pre-training-for-program","title":"Unified Pre-training for Program Understanding and Generation","date":"2021-03-10","arxiv_id":"2103.06333","repositories_listed":2,"syntology":null},{"url":"/paper/graph-based-self-supervised-program-repair","slug":"graph-based-self-supervised-program-repair","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","date":"2020-05-20","arxiv_id":"2005.10636","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/graph-based-self-supervised-program-repair#ran","syntology_url":"https://syntology.ai/paper/2005.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10636"}},"official":{"repos":["michiyasunaga/DrRepair","worksheets.codalab.org/worksheets/0x01838644724a433c932bef4cb5c42fbd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pre-trained-contextual-embedding-of-source-1","slug":"pre-trained-contextual-embedding-of-source-1","title":"Learning and Evaluating Contextual Embedding of Source Code","date":"2019-12-21","arxiv_id":"2001.00059","repositories_listed":2,"syntology":null},{"url":"/paper/neural-program-repair-by-jointly-learning-to-1","slug":"neural-program-repair-by-jointly-learning-to-1","title":"Neural Program Repair by Jointly Learning to Localize and Repair","date":"2019-04-03","arxiv_id":"1904.01720","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/neural-program-repair-by-jointly-learning-to-1#ran","syntology_url":"https://syntology.ai/paper/1904.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01720"}},"official":null}},{"url":"/paper/sequencer-sequence-to-sequence-learning-for","slug":"sequencer-sequence-to-sequence-learning-for","title":"SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair","date":"2018-12-24","arxiv_id":"1901.01808","repositories_listed":2,"syntology":null},{"url":"/paper/cosil-software-issue-localization-via-llm","slug":"cosil-software-issue-localization-via-llm","title":"CoSIL: Software Issue Localization via LLM-Driven Code Repository Graph Searching","date":"2025-03-28","arxiv_id":"2503.22424","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-adaptive-program-repair-with-bug","slug":"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/o3-mini-vs-deepseek-r1-which-one-is-safer","slug":"o3-mini-vs-deepseek-r1-which-one-is-safer","title":"o3-mini vs DeepSeek-R1: Which One is Safer?","date":"2025-01-30","arxiv_id":"2501.18438","repositories_listed":1,"syntology":null},{"url":"/paper/integrating-various-software-artifacts-for","slug":"integrating-various-software-artifacts-for","title":"Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair","date":"2024-12-05","arxiv_id":"2412.03905","repositories_listed":1,"syntology":null},{"url":"/paper/planning-driven-programming-a-large-language","slug":"planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","arxiv_id":"2411.14503","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/planning-driven-programming-a-large-language#ran","syntology_url":"https://syntology.ai/paper/2411.14503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14503"}},"official":{"repos":["you68681/lpw"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-code-to-correctness-closing-the-last","slug":"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_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/from-code-to-correctness-closing-the-last#ran","syntology_url":"https://syntology.ai/paper/2410.01215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01215"}},"official":{"repos":["YerbaPage/MGDebugger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/can-gpt-o1-kill-all-bugs","slug":"can-gpt-o1-kill-all-bugs","title":"Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs","date":"2024-09-16","arxiv_id":"2409.10033","repositories_listed":1,"syntology":null},{"url":"/paper/repair-automated-program-repair-with-process","slug":"repair-automated-program-repair-with-process","title":"RePair: Automated Program Repair with Process-based Feedback","date":"2024-08-21","arxiv_id":"2408.11296","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/repair-automated-program-repair-with-process#ran","syntology_url":"https://syntology.ai/paper/2408.11296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11296"}},"official":{"repos":["tntwow/repair"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/semcoder-training-code-language-models-with","slug":"semcoder-training-code-language-models-with","title":"SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning","date":"2024-06-03","arxiv_id":"2406.01006","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/semcoder-training-code-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2406.01006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01006"}},"official":{"repos":["arise-lab/semcoder"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-educational-program-repair","slug":"benchmarking-educational-program-repair","title":"Benchmarking Educational Program Repair","date":"2024-05-08","arxiv_id":"2405.05347","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-educational-program-repair#ran","syntology_url":"https://syntology.ai/paper/2405.05347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05347"}},"official":{"repos":["koutchemecharles/gaied_nips23"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-llms-for-fl-free-program-repair","slug":"aligning-llms-for-fl-free-program-repair","title":"Aligning the Objective of LLM-based Program Repair","date":"2024-04-13","arxiv_id":"2404.08877","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/aligning-llms-for-fl-free-program-repair#ran","syntology_url":"https://syntology.ai/paper/2404.08877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08877"}},"official":{"repos":["cuhk-shenzhen-se/d4c"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/repairagent-an-autonomous-llm-based-agent-for","slug":"repairagent-an-autonomous-llm-based-agent-for","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","date":"2024-03-25","arxiv_id":"2403.17134","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/repairagent-an-autonomous-llm-based-agent-for#ran","syntology_url":"https://syntology.ai/paper/2403.17134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17134"}},"official":{"repos":["sola-st/RepairAgent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-program-repair-with-semantic","slug":"evaluating-program-repair-with-semantic","title":"Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing","date":"2024-02-19","arxiv_id":"2402.11892","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-approach-for-automatic-program-repair","slug":"a-novel-approach-for-automatic-program-repair","title":"A Novel Approach for Automatic Program Repair using Round-Trip Translation with Large Language Models","date":"2024-01-15","arxiv_id":"2401.07994","repositories_listed":1,"syntology":null},{"url":"/paper/repairllama-efficient-representations-and","slug":"repairllama-efficient-representations-and","title":"RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair","date":"2023-12-25","arxiv_id":"2312.15698","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/repairllama-efficient-representations-and#ran","syntology_url":"https://syntology.ai/paper/2312.15698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15698"}},"official":{"repos":["assert-kth/repairllama"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/breaking-the-silence-the-threats-of-using","slug":"breaking-the-silence-the-threats-of-using","title":"Breaking the Silence: the Threats of Using LLMs in Software Engineering","date":"2023-12-13","arxiv_id":"2312.08055","repositories_listed":1,"syntology":null},{"url":"/paper/out-of-context-how-important-is-local-context","slug":"out-of-context-how-important-is-local-context","title":"Out of Context: How important is Local Context in Neural Program Repair?","date":"2023-12-08","arxiv_id":"2312.04986","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-genetic-improvement-mutations-using","slug":"enhancing-genetic-improvement-mutations-using","title":"Enhancing Genetic Improvement Mutations Using Large Language Models","date":"2023-10-18","arxiv_id":"2310.19813","repositories_listed":1,"syntology":null},{"url":"/paper/copiloting-the-copilots-fusing-large-language","slug":"copiloting-the-copilots-fusing-large-language","title":"Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair","date":"2023-09-01","arxiv_id":"2309.00608","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/copiloting-the-copilots-fusing-large-language#ran","syntology_url":"https://syntology.ai/paper/2309.00608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00608"}},"official":{"repos":["ise-uiuc/Repilot"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graph-neural-networks-for-mapping-variables","slug":"graph-neural-networks-for-mapping-variables","title":"Graph Neural Networks For Mapping Variables Between Programs -- Extended Version","date":"2023-07-24","arxiv_id":"2307.13014","repositories_listed":1,"syntology":null},{"url":"/paper/how-effective-are-neural-networks-for-fixing","slug":"how-effective-are-neural-networks-for-fixing","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","date":"2023-05-29","arxiv_id":"2305.18607","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-effective-are-neural-networks-for-fixing#ran","syntology_url":"https://syntology.ai/paper/2305.18607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18607"}},"official":{"repos":["lin-tan/llm-vul"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/knod-domain-knowledge-distilled-tree-decoder","slug":"knod-domain-knowledge-distilled-tree-decoder","title":"KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair","date":"2023-02-03","arxiv_id":"2302.01857","repositories_listed":1,"syntology":null},{"url":"/paper/invalidator-automated-patch-correctness","slug":"invalidator-automated-patch-correctness","title":"Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning","date":"2023-01-03","arxiv_id":"2301.01113","repositories_listed":1,"syntology":null},{"url":"/paper/invaastcluster-on-applying-invariant-based","slug":"invaastcluster-on-applying-invariant-based","title":"InvAASTCluster: On Applying Invariant-Based Program Clustering to Introductory Programming Assignments","date":"2022-06-28","arxiv_id":"2206.14175","repositories_listed":1,"syntology":null},{"url":"/paper/tfix-learning-to-fix-coding-errors-with-a","slug":"tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","date":"2021-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-syntax-guided-edit-decoder-for-neural","slug":"a-syntax-guided-edit-decoder-for-neural","title":"A Syntax-Guided Edit Decoder for Neural Program Repair","date":"2021-06-15","arxiv_id":"2106.08253","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-syntax-guided-edit-decoder-for-neural#ran","syntology_url":"https://syntology.ai/paper/2106.08253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08253"}},"official":null}},{"url":"/paper/assessing-the-effectiveness-of-syntactic","slug":"assessing-the-effectiveness-of-syntactic","title":"Assessing the Effectiveness of Syntactic Structure to Learn Code Edit Representations","date":"2021-06-11","arxiv_id":"2106.06110","repositories_listed":1,"syntology":null},{"url":"/paper/break-it-fix-it-unsupervised-learning-for","slug":"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":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/break-it-fix-it-unsupervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.06600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06600"}},"official":{"repos":["michiyasunaga/bifi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cure-code-aware-neural-machine-translation","slug":"cure-code-aware-neural-machine-translation","title":"CURE: Code-Aware Neural Machine Translation for Automatic Program Repair","date":"2021-02-26","arxiv_id":"2103.00073","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-execute-programs-with-instruction","slug":"learning-to-execute-programs-with-instruction","title":"Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks","date":"2020-10-23","arxiv_id":"2010.12621","repositories_listed":1,"syntology":null},{"url":"/paper/patching-as-translation-the-data-and-the","slug":"patching-as-translation-the-data-and-the","title":"Patching as Translation: the Data and the Metaphor","date":"2020-08-24","arxiv_id":"2008.10707","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/patching-as-translation-the-data-and-the#ran","syntology_url":"https://syntology.ai/paper/2008.10707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10707"}},"official":{"repos":["ARiSE-Lab/Patch-as-translation"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/robot-action-selection-learning-via-layered","slug":"robot-action-selection-learning-via-layered","title":"Robot Action Selection Learning via Layered Dimension Informed Program Synthesis","date":"2020-08-10","arxiv_id":"2008.04133","repositories_listed":1,"syntology":null},{"url":"/paper/coconut-combining-context-aware-neural","slug":"coconut-combining-context-aware-neural","title":"CoCoNuT: Combining Context-Aware Neural Translation Models using Ensemble for Program Repair","date":"2020-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/global-relational-models-of-source-code","slug":"global-relational-models-of-source-code","title":"Global Relational Models of Source Code","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/search-based-repair-of-deep-neural-networks","slug":"search-based-repair-of-deep-neural-networks","title":"Arachne: Search Based Repair of Deep Neural Networks","date":"2019-12-28","arxiv_id":"1912.12463","repositories_listed":1,"syntology":null},{"url":"/paper/human-in-the-loop-automatic-program-repair","slug":"human-in-the-loop-automatic-program-repair","title":"Human-In-The-Loop Automatic Program Repair","date":"2019-12-16","arxiv_id":"1912.07758","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-programming","slug":"deep-reinforcement-learning-for-programming","title":"Deep Reinforcement Learning for Programming Language Correction","date":"2018-01-31","arxiv_id":"1801.10467","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-neural-program-embedding-for-program","slug":"dynamic-neural-program-embedding-for-program","title":"Dynamic Neural Program Embedding for Program Repair","date":"2017-11-20","arxiv_id":"1711.07163","repositories_listed":1,"syntology":null},{"url":"/paper/deepfix-fixing-common-c-language-errors-by","slug":"deepfix-fixing-common-c-language-errors-by","title":"DeepFix: Fixing Common C Language Errors by Deep Learning","date":"2017-02-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"core-benchmarking-llms-code-reasoning","title":"CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","date":"2025-07-03","arxiv_id":"2507.05269","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-3-multi-level-tree-based-automatic-program","title":"$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models","date":"2025-06-26","arxiv_id":"2506.21211","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-software-engineering-agents-a","title":"Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories","date":"2025-06-23","arxiv_id":"2506.18824","repositories_listed":0,"syntology":null},{"url":null,"slug":"dissecting-the-swe-bench-leaderboards","title":"Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems","date":"2025-06-20","arxiv_id":"2506.17208","repositories_listed":0,"syntology":null},{"url":null,"slug":"semagent-a-semantics-aware-program-repair","title":"SemAgent: A Semantics Aware Program Repair Agent","date":"2025-06-19","arxiv_id":"2506.16650","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-dataset-evaluation-of-models-for","title":"A Multi-Dataset Evaluation of Models for Automated Vulnerability Repair","date":"2025-06-05","arxiv_id":"2506.04987","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-llm-as-judge-metric-for-bridging-the-gap","title":"An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks","date":"2025-05-27","arxiv_id":"2505.20854","repositories_listed":0,"syntology":null},{"url":null,"slug":"gradient-based-program-repair-fixing-bugs-in","title":"Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces","date":"2025-05-23","arxiv_id":"2505.17703","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-code-surgery-repairing-bugs-and","title":"Synthetic Code Surgery: Repairing Bugs and Vulnerabilities with LLMs and Synthetic Data","date":"2025-05-12","arxiv_id":"2505.07372","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-effectively-leveraging-execution","title":"Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs","date":"2025-05-07","arxiv_id":"2505.04441","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-art-of-repair-optimizing-iterative","title":"The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models","date":"2025-05-05","arxiv_id":"2505.02931","repositories_listed":0,"syntology":null},{"url":null,"slug":"swe-synth-synthesizing-verifiable-bug-fix","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","date":"2025-04-20","arxiv_id":"2504.14757","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-ml-filters-to-help-automated","title":"Using ML filters to help automated vulnerability repairs: when it helps and when it doesn't","date":"2025-04-09","arxiv_id":"2504.07027","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-pruning-automated-fairness-repair","title":"Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing","date":"2025-03-20","arxiv_id":"2503.15815","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-generalizability-of-llms-in","title":"Evaluating the Generalizability of LLMs in Automated Program Repair","date":"2025-03-12","arxiv_id":"2503.09217","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-s-the-bug-attention-probing-for","title":"Where's the Bug? Attention Probing for Scalable Fault Localization","date":"2025-02-19","arxiv_id":"2502.13966","repositories_listed":0,"syntology":null},{"url":null,"slug":"lessleak-bench-a-first-investigation-of-data","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","date":"2025-02-10","arxiv_id":"2502.06215","repositories_listed":0,"syntology":null},{"url":null,"slug":"agentic-bug-reproduction-for-effective","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","date":"2025-02-03","arxiv_id":"2502.01821","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-agent-based-program-repair-at","title":"Evaluating Agent-based Program Repair at Google","date":"2025-01-13","arxiv_id":"2501.07531","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-input-order-bias-on-large","title":"The Impact of Input Order Bias on Large Language Models for Software Fault Localization","date":"2024-12-25","arxiv_id":"2412.18750","repositories_listed":0,"syntology":null},{"url":null,"slug":"counterexample-guided-program-repair-using","title":"Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization","date":"2024-12-19","arxiv_id":"2502.07786","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-of-ai-driven","title":"A Comprehensive Survey of AI-Driven Advancements and Techniques in Automated Program Repair and Code Generation","date":"2024-11-12","arxiv_id":"2411.07586","repositories_listed":0,"syntology":null},{"url":null,"slug":"mdeval-massively-multilingual-code-debugging","title":"MdEval: Massively Multilingual Code Debugging","date":"2024-11-04","arxiv_id":"2411.02310","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-guided-search-for-efficient-program","title":"Semantic-guided Search for Efficient Program Repair with Large Language Models","date":"2024-10-22","arxiv_id":"2410.16655","repositories_listed":0,"syntology":null},{"url":null,"slug":"collu-bench-a-benchmark-for-predicting","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","date":"2024-10-13","arxiv_id":"2410.09997","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-code-text-learning-for-bimodal","title":"In-Context Code-Text Learning for Bimodal Software Engineering","date":"2024-10-08","arxiv_id":"2410.18107","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-potential-of-conversational","title":"Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench","date":"2024-10-06","arxiv_id":"2410.04485","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-llm-based-automated-program-repair","title":"Enhancing Automated Program Repair with Solution Design","date":"2024-08-22","arxiv_id":"2408.12056","repositories_listed":0,"syntology":null},{"url":null,"slug":"mergerepair-an-exploratory-study-on-merging","title":"MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair","date":"2024-08-18","arxiv_id":"2408.09568","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02232","title":"SpecRover: Code Intent Extraction via LLMs","date":"2024-08-05","arxiv_id":"2408.02232","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-c-c-program-repair-for-high-level","title":"Automated C/C++ Program Repair for High-Level Synthesis via Large Language Models","date":"2024-07-04","arxiv_id":"2407.03889","repositories_listed":0,"syntology":null},{"url":null,"slug":"narrepair-non-autoregressive-code-generation","title":"NARRepair: Non-Autoregressive Code Generation Model for Automatic Program Repair","date":"2024-06-24","arxiv_id":"2406.16526","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-program-repair-emerging-trends-pose","title":"Automated Program Repair: Emerging trends pose and expose problems for benchmarks","date":"2024-05-08","arxiv_id":"2405.05455","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-programming-large-language-models","title":"Automatic Programming: Large Language Models and Beyond","date":"2024-05-03","arxiv_id":"2405.02213","repositories_listed":0,"syntology":null},{"url":null,"slug":"next-teaching-large-language-models-to-reason","title":"NExT: Teaching Large Language Models to Reason about Code Execution","date":"2024-04-23","arxiv_id":"2404.14662","repositories_listed":0,"syntology":null},{"url":null,"slug":"peer-aided-repairer-empowering-large-language","title":"Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments","date":"2024-04-02","arxiv_id":"2404.01754","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-the-capabilities-of","title":"To Err is Machine: Vulnerability Detection Challenges LLM Reasoning","date":"2024-03-25","arxiv_id":"2403.17218","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-vulnerability-repair-in-javascript","title":"A Study of Vulnerability Repair in JavaScript Programs with Large Language Models","date":"2024-03-19","arxiv_id":"2403.13193","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepcode-ai-fix-fixing-security","title":"DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models","date":"2024-02-19","arxiv_id":"2402.13291","repositories_listed":0,"syntology":null},{"url":null,"slug":"nova-generative-language-models-for-binaries","title":"Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning","date":"2023-11-22","arxiv_id":"2311.13721","repositories_listed":0,"syntology":null},{"url":null,"slug":"condefects-a-new-dataset-to-address-the-data","title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair","date":"2023-10-25","arxiv_id":"2310.16253","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-bug-generation-in-the-era-of-large","title":"Automated Bug Generation in the era of Large Language Models","date":"2023-10-03","arxiv_id":"2310.02407","repositories_listed":0,"syntology":null},{"url":null,"slug":"program-repair-with-minimal-edits-using","title":"Program Repair with Minimal Edits Using CodeT5","date":"2023-09-26","arxiv_id":"2309.14760","repositories_listed":0,"syntology":null},{"url":null,"slug":"frustrated-with-code-quality-issues-llms-can","title":"Frustrated with Code Quality Issues? LLMs can Help!","date":"2023-09-22","arxiv_id":"2309.12938","repositories_listed":0,"syntology":null},{"url":null,"slug":"2309-06057","title":"RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair","date":"2023-09-12","arxiv_id":"2309.06057","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-exploratory-literature-study-on-sharing","title":"An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code","date":"2023-07-05","arxiv_id":"2307.02443","repositories_listed":0,"syntology":null},{"url":null,"slug":"majority-rule-better-patching-via-self","title":"Better patching using LLM prompting, via Self-Consistency","date":"2023-05-31","arxiv_id":"2306.00108","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-chatgpt-the-ultimate-programming-assistant","title":"Is ChatGPT the Ultimate Programming Assistant -- How far is it?","date":"2023-04-24","arxiv_id":"2304.11938","repositories_listed":0,"syntology":null}],"syntology_records":19,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/task/program-repair/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/program-repair/papers/2","json":"/task/program-repair/papers/2.json","rows":32},{"order":"ran","page":1,"of":1,"url":"/task/program-repair/papers/ran/1","json":"/task/program-repair/papers/ran/1.json","rows":18}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"ef6761dcf090a690c75589cf29951d283e59e7da0395e9f5cc8df27834522f55","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}