{"url":"/dataset/rvl-cdip-mp","name":"RVL-CDIP_MP","full_name":"RVL-CDIP multi-page","description_markdown":"RVL-CDIP_MP is our first contribution to retrieve the original documents of the IIT-CDIP test collection which were used to create RVL-CDIP. Some PDFs or encoded images were corrupt, which explains that we have around 500 fewer instances. By leveraging metadata from OCR-IDL , we matched the original identifiers from IIT-CDIP and retrieved them from IDL using a conversion. \r\n\r\nIt has the same label taxonomy as RVL-CDIP (16) with close to 400K documents in PDF format,   averaging 5 pages per document.","description_withheld":null,"homepage":"https://huggingface.co/datasets/bdpc/rvl_cdip_mp","introduced_date":"2023-08-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/beyond-document-page-classification-design","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","first_author":"Jordy Van Landeghem","url":null},"license":{"name":"apache 2.0","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Document Classification","url":"/task/document-classification","datasets_with_task":"/datasets/task/document-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["RVL-CDIP_MP"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}