{"url":"/dataset/chcatext","name":"ChCatExt","full_name":"Chinese Catalog Extraction Dataset","description_markdown":"ChCatExt is composed of BidAnn (bid announcement), FinAnn (financial announcement) and CreRat (credit rating report).\r\nIt is designed for re-construct catalog trees from documents.","description_withheld":null,"homepage":"https://github.com/Spico197/CatalogExtraction","introduced_date":"2023-04-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/ced-catalog-extraction-from-documents","title":"CED: Catalog Extraction from Documents","first_author":"Tong Zhu","url":null},"license":null,"modalities":[],"tasks":[{"name":"Catalog Extraction","url":"/task/catalog-extraction","datasets_with_task":"/datasets/task/catalog-extraction"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["ChCatExt"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/catalog-extraction-on-chcatext","task":"Catalog Extraction","dataset_variant":"ChCatExt","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"TRACER","paper":"/paper/ced-catalog-extraction-from-documents","metrics":{"F1":"82.39"},"code_links":[{"title":"spico197/catalogextraction","url":"https://github.com/spico197/catalogextraction"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ced-catalog-extraction-from-documents","title":"CED: Catalog Extraction from Documents","date":"2023-04-28","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}