{"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/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 (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":1,"rows_per_page":100,"shown":62,"of":62,"of_with_code":31,"tagged_in_all":62,"counts":{"archive_papers_tagged":62,"with_a_code_link":31,"where_syntology_ran_a_sample":8,"not_listed_spam_title":0,"listed":62,"listed_where_code_ran":8,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/gpt-4-technical-report-1","slug":"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/swe-bench-can-language-models-resolve-real","slug":"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":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/swe-bench-can-language-models-resolve-real#ran","syntology_url":"https://syntology.ai/paper/2310.06770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06770"}},"official":null}},{"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/neural-transfer-learning-for-repairing","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/swe-dev-evaluating-and-training-autonomous#ran","syntology_url":"https://syntology.ai/paper/2505.16975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16975"}},"official":{"repos":["dorothyduuu/swe-dev"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/repository-level-code-search-with-neural","slug":"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","slug":"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","slug":"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":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cornstack-high-quality-contrastive-data-for#ran","syntology_url":"https://syntology.ai/paper/2412.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01007"}},"official":{"repos":["gangiswag/cornstack"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/metrex-a-benchmark-for-verilog-code-metric","slug":"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":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/metrex-a-benchmark-for-verilog-code-metric#ran","syntology_url":"https://syntology.ai/paper/2411.03471","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03471"}},"official":{"repos":["scale-lab/MetRex"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"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/leveraging-large-language-models-for-15","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fixeval-execution-based-evaluation-of-program#ran","syntology_url":"https://syntology.ai/paper/2206.07796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07796"}},"official":{"repos":["mahimanzum/fixeval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/s-dabt-schedule-and-dependency-aware-bug","slug":"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","slug":"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","slug":"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","slug":"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/a-simple-approach-for-handling-out-of","slug":"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/neural-code-completion-with-anonymized","slug":"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/empirical-study-of-transformers-for-source","slug":"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},{"url":"/paper/learning-the-relation-between-code-features","slug":"learning-the-relation-between-code-features","title":"Learning the Relation between Code Features and Code Transforms with Structured Prediction","date":"2019-07-22","arxiv_id":"1907.09282","repositories_listed":1,"syntology":null},{"url":null,"slug":"the-foundation-cracks-a-comprehensive-study","title":"The Foundation Cracks: A Comprehensive Study on Bugs and Testing Practices in LLM Libraries","date":"2025-06-14","arxiv_id":"2506.12320","repositories_listed":0,"syntology":null},{"url":null,"slug":"longcodebench-evaluating-coding-llms-at-1m","title":"LongCodeBench: Evaluating Coding LLMs at 1M Context Windows","date":"2025-05-12","arxiv_id":"2505.07897","repositories_listed":0,"syntology":null},{"url":"/paper/ape-bench-i-towards-file-level-automated","slug":"ape-bench-i-towards-file-level-automated","title":"APE-Bench I: Towards File-level Automated Proof Engineering of Formal Math Libraries","date":"2025-04-27","arxiv_id":"2504.19110","repositories_listed":0,"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/ape-bench-i-towards-file-level-automated#ran","syntology_url":"https://syntology.ai/paper/2504.19110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.19110"}},"official":null}},{"url":null,"slug":"veridebug-a-unified-llm-for-verilog-debugging","title":"VeriDebug: A Unified LLM for Verilog Debugging via Contrastive Embedding and Guided Correction","date":"2025-04-27","arxiv_id":"2504.19099","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-simulation-guided-llm-based-code","title":"On Simulation-Guided LLM-based Code Generation for Safe Autonomous Driving Software","date":"2025-04-02","arxiv_id":"2504.02141","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-ai-models-in-software","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Enhancement Protocol","date":"2025-03-07","arxiv_id":"2503.05860","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-evaluation-of-llms-in-predicting","title":"Empirical evaluation of LLMs in predicting fixes of Configuration bugs in Smart Home System","date":"2025-02-16","arxiv_id":"2502.10953","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-on-llm-based-agents-for","title":"An Empirical Study on LLM-based Agents for Automated Bug Fixing","date":"2024-11-15","arxiv_id":"2411.10213","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":"pdc-dm-sft-a-road-for-llm-sql-bug-fix","title":"PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing","date":"2024-11-11","arxiv_id":"2411.06767","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterising-open-source-co-opetition-in","title":"Characterising Open Source Co-opetition in Company-hosted Open Source Software Projects: The Cases of PyTorch, TensorFlow, and Transformers","date":"2024-10-23","arxiv_id":"2410.18241","repositories_listed":0,"syntology":null},{"url":null,"slug":"debug-smarter-not-harder-ai-agents-for-error","title":"Debug Smarter, Not Harder: AI Agents for Error Resolution in Computational Notebooks","date":"2024-10-18","arxiv_id":"2410.14393","repositories_listed":0,"syntology":null},{"url":null,"slug":"marscode-agent-ai-native-automated-bug-fixing","title":"MarsCode Agent: AI-native Automated Bug Fixing","date":"2024-09-02","arxiv_id":"2409.00899","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-comparison-tuning-for-code-large","title":"Code Comparison Tuning for Code Large Language Models","date":"2024-03-28","arxiv_id":"2403.19121","repositories_listed":0,"syntology":null},{"url":null,"slug":"untangling-knots-leveraging-llm-for-error","title":"Untangling Knots: Leveraging LLM for Error Resolution in Computational Notebooks","date":"2024-03-26","arxiv_id":"2405.01559","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":"copilot-evaluation-harness-evaluating-llm","title":"Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming","date":"2024-02-22","arxiv_id":"2402.14261","repositories_listed":0,"syntology":null},{"url":null,"slug":"securefalcon-the-next-cyber-reasoning-system","title":"SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?","date":"2023-07-13","arxiv_id":"2307.06616","repositories_listed":0,"syntology":null},{"url":"/paper/model-card-and-evaluations-for-claude-models","slug":"model-card-and-evaluations-for-claude-models","title":"Model Card and Evaluations for Claude Models","date":"2023-07-11","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rapgen-an-approach-for-fixing-code","title":"RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot","date":"2023-06-29","arxiv_id":"2306.17077","repositories_listed":0,"syntology":null},{"url":null,"slug":"grace-generation-using-associated-code-edits","title":"GrACE: Generation using Associated Code Edits","date":"2023-05-23","arxiv_id":"2305.14129","repositories_listed":0,"syntology":null},{"url":null,"slug":"detect-localize-repair-a-unified-framework","title":"Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5","date":"2022-11-27","arxiv_id":"2211.14875","repositories_listed":0,"syntology":null},{"url":null,"slug":"bug-fix-time-optimization-using-matrix","title":"Bug Fix Time Optimization Using Matrix Factorization and Iterative Gale-Shaply Algorithms","date":"2022-07-14","arxiv_id":"2207.07149","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-causal-inference-for-explainable","title":"Leveraging Causal Inference for Explainable Automatic Program Repair","date":"2022-05-26","arxiv_id":"2205.13342","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-automatic-repair-of-source-code","title":"Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods","date":"2022-02-07","arxiv_id":"2202.03055","repositories_listed":0,"syntology":null},{"url":null,"slug":"fix-filter-fix-intuitively-connect-any-models","title":"Fix-Filter-Fix: Intuitively Connect Any Models for Effective Bug Fixing","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"graphix-a-pre-trained-graph-edit-model-for","title":"GRAPHIX: A Pre-trained Graph Edit Model for Automated Program Repair","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tea-program-repair-using-neural-network-based","title":"Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix","date":"2021-07-17","arxiv_id":"2107.08262","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhmm-on-the-use-of-ensemble-hmms-and-stack","title":"EnHMM: On the Use of Ensemble HMMs and Stack Traces to Predict the Reassignment of Bug Report Fields","date":"2021-03-15","arxiv_id":"2103.08083","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-learning-meaningful-code-changes-via","title":"On Learning Meaningful Code Changes via Neural Machine Translation","date":"2019-01-25","arxiv_id":"1901.09102","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-investigation-into-learning-bug","title":"An Empirical Investigation into Learning Bug-Fixing Patches in the Wild via Neural Machine Translation","date":"2018-09-07","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":9,"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":8,"papers_where_code_ran_first_page":"/task/bug-fixing/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":"ran","page":1,"of":1,"url":"/task/bug-fixing/papers/ran/1","json":"/task/bug-fixing/papers/ran/1.json","rows":8}],"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":"95512b3c4addd56d77ba9a76421205c53724e09483e5141aecec668a300e9d32","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}