{"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/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 (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":39,"of":39,"of_with_code":14,"tagged_in_all":39,"counts":{"archive_papers_tagged":39,"with_a_code_link":14,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":39,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":5,"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/codexglue-a-machine-learning-benchmark","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/codexglue-a-machine-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2102.04664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.04664"}},"official":{"repos":["microsoft/CodeXGLUE"],"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":["official"]}}},{"url":"/paper/octopack-instruction-tuning-code-large","slug":"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_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"9 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; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/octopack-instruction-tuning-code-large#ran","syntology_url":"https://syntology.ai/paper/2308.07124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07124"}},"official":{"repos":["bigcode-project/bigcode-evaluation-harness","bigcode-project/octopack"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-performance-improving-code-edits","slug":"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":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":11,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":19,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/learning-performance-improving-code-edits#ran","syntology_url":"https://syntology.ai/paper/2302.07867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07867"}},"official":{"repos":["madaan/pie-perf"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-kb-leveraging-cross-domain-experience","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agent-kb-leveraging-cross-domain-experience#ran","syntology_url":"https://syntology.ai/paper/2507.06229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06229"}},"official":{"repos":["oppo-personalai/agent-kb"],"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":["official"]}}},{"url":"/paper/why-stop-at-one-error-benchmarking-llms-as","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/code-agents-are-state-of-the-art-software#ran","syntology_url":"https://syntology.ai/paper/2406.12952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12952"}},"official":{"repos":["logic-star-ai/swt-bench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autocoder-enhancing-code-large-language-model","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guiding-language-models-of-code-with-global#ran","syntology_url":"https://syntology.ai/paper/2306.10763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.10763"}},"official":{"repos":["microsoft/monitors4codegen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/macer-a-modular-framework-for-accelerated","slug":"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},{"url":null,"slug":"codejudgebench-benchmarking-llm-as-a-judge","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","date":"2025-07-14","arxiv_id":"2507.10535","repositories_listed":0,"syntology":null},{"url":null,"slug":"breakpoint-scalable-evaluation-of-system","title":"Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents","date":"2025-05-30","arxiv_id":"2506.00172","repositories_listed":0,"syntology":null},{"url":null,"slug":"crashfixer-a-crash-resolution-agent-for-the","title":"CrashFixer: A crash resolution agent for the Linux kernel","date":"2025-04-29","arxiv_id":"2504.20412","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-accurately-do-large-language-models","title":"How Accurately Do Large Language Models Understand Code?","date":"2025-04-06","arxiv_id":"2504.04372","repositories_listed":0,"syntology":null},{"url":null,"slug":"rocketppa-ultra-fast-llm-based-ppa-estimator","title":"RocketPPA: Code-Level Power, Performance, and Area Prediction via LLM and Mixture of Experts","date":"2025-03-27","arxiv_id":"2503.21971","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01098","title":"SolBench: A Dataset and Benchmark for Evaluating Functional Correctness in Solidity Code Completion and Repair","date":"2025-03-03","arxiv_id":"2503.01098","repositories_listed":0,"syntology":null},{"url":null,"slug":"aupair-golden-example-pairs-for-code-repair","title":"AuPair: Golden Example Pairs for Code Repair","date":"2025-02-12","arxiv_id":"2502.18487","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-aided-efficient-hardware-design","title":"LLM-Aided Efficient Hardware Design Automation","date":"2024-10-24","arxiv_id":"2410.18582","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-source-code-security-with-llms","title":"Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs","date":"2024-09-01","arxiv_id":"2409.00571","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-your-ai-generated-code-really-secure","title":"Is Your AI-Generated Code Really Safe? Evaluating Large Language Models on Secure Code Generation with CodeSecEval","date":"2024-07-02","arxiv_id":"2407.02395","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilrr-transferring-code-repair-for-low","title":"Investigating the Transferability of Code Repair for Low-Resource Programming Languages","date":"2024-06-21","arxiv_id":"2406.14867","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-repair-with-llms-gives-an-exploration","title":"Code Repair with LLMs gives an Exploration-Exploitation Tradeoff","date":"2024-05-26","arxiv_id":"2405.17503","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":"code-security-vulnerability-repair-using","title":"Code Security Vulnerability Repair Using Reinforcement Learning with Large Language Models","date":"2024-01-13","arxiv_id":"2401.07031","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-automated-code-vulnerability-repair","title":"Enhanced Automated Code Vulnerability Repair using Large Language Models","date":"2024-01-08","arxiv_id":"2401.03741","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-models-for-secure","title":"Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigation","date":"2023-10-25","arxiv_id":"2310.16263","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-box-prediction-of-flaky-test-fix","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","date":"2023-06-21","arxiv_id":"2307.00012","repositories_listed":0,"syntology":null},{"url":null,"slug":"poison-attack-and-defense-on-deep-source-code","title":"Poison Attack and Defense on Deep Source Code Processing Models","date":"2022-10-31","arxiv_id":"2210.17029","repositories_listed":0,"syntology":null},{"url":"/paper/fix-bugs-with-transformer-through-a-neural-1","slug":"fix-bugs-with-transformer-through-a-neural-1","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2022-04-13","arxiv_id":"2204.06643","repositories_listed":0,"syntology":null},{"url":null,"slug":"break-it-message-it-fix-it-learning-to-repair","title":"Break it - Message it - Fix it : Learning to Repair Python Programs using Error Messages without Labelled Data","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fix-bugs-with-transformer-through-a-neural","title":"Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-learning-to-repair-code-and-generate","title":"Jointly Learning to Repair Code and Generate Commit Message","date":"2021-09-25","arxiv_id":"2109.12296","repositories_listed":0,"syntology":null},{"url":null,"slug":"inferring-javascript-types-using-graph-neural","title":"Inferring Javascript types using Graph Neural Networks","date":"2019-05-16","arxiv_id":"1905.06707","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-repair-software-vulnerabilities","title":"Learning to Repair Software Vulnerabilities with Generative Adversarial Networks","date":"2018-05-18","arxiv_id":"1805.07475","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-code-repair-using-neuro-symbolic","title":"Semantic Code Repair using Neuro-Symbolic Transformation Networks","date":"2017-10-30","arxiv_id":"1710.11054","repositories_listed":0,"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"},"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":7,"papers_where_code_ran_first_page":"/task/code-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":"ran","page":1,"of":1,"url":"/task/code-repair/papers/ran/1","json":"/task/code-repair/papers/ran/1.json","rows":7}],"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":"3facd156df68a962e946fdbf14009008b29990b2fb39bd92b12d8bcdd4e313d5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}