{"url":"/task/auto-debugging","name":"Auto Debugging","slug":"auto-debugging","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3,"papers_with_code":2,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/auto-debugging-on-big-bench-lite","slug":"auto-debugging-on-big-bench-lite","dataset":"Big-bench Lite","dataset_url":"/dataset/big-bench","rows_in_archive":3,"metrics":["Exact string match"],"first_row_in_archive_order":{"model":"PaLM 62B (few-shot, k=5)","paper_title":"PaLM: Scaling Language Modeling with Pathways","paper_url":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_date":"2022-04-05","arxiv_id":"2204.02311","code_links":[{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"lucidrains/PaLM-pytorch","url":"https://github.com/lucidrains/PaLM-pytorch"},{"title":"google/paxml","url":"https://github.com/google/paxml"},{"title":"foundation-model-stack/fms-fsdp","url":"https://github.com/foundation-model-stack/fms-fsdp"},{"title":"lucidrains/PaLM-jax","url":"https://github.com/lucidrains/PaLM-jax"},{"title":"chrisociepa/allamo","url":"https://github.com/chrisociepa/allamo"},{"title":"conceptofmind/PaLM-flax","url":"https://github.com/conceptofmind/PaLM-flax"}],"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":3,"items":[{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/from-code-to-correctness-closing-the-last","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","date":"2024-10-02","arxiv_id":"2410.01215","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}