{"url":"/task/catalog-extraction","name":"Catalog Extraction","slug":"catalog-extraction","description_markdown":"Catalog Extraction aims to re-construct catalog-based document trees.","categories":[{"name":"Medical","url":"/area/medical"},{"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":1,"papers_with_code":1,"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":1},"benchmarks":[{"leaderboard":"/sota/catalog-extraction-on-chcatext","slug":"catalog-extraction-on-chcatext","dataset":"ChCatExt","dataset_url":"/dataset/chcatext","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"TRACER","paper_title":"CED: Catalog Extraction from Documents","paper_url":"/paper/ced-catalog-extraction-from-documents","paper_date":"2023-04-28","arxiv_id":"2304.14662","code_links":[{"title":"spico197/catalogextraction","url":"https://github.com/spico197/catalogextraction"}],"syntology":null}}],"datasets":[{"url":"/dataset/chcatext","name":"ChCatExt","full_name":"Chinese Catalog Extraction Dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/information-extraction","name":"Information Extraction"}],"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":1,"of":1,"tagged_in_all":1,"items":[{"url":"/paper/ced-catalog-extraction-from-documents","title":"CED: Catalog Extraction from Documents","date":"2023-04-28","arxiv_id":"2304.14662","repositories_listed":1,"syntology":null}],"syntology_records":0,"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"}}