{"url":"/dataset/ncse-v2-0","name":"NCSE v2.0","full_name":"NCSE v2.0: A Dataset of OCR-Processed 19th Century English Newspapers","description_markdown":"The NCSE v2.0 is a digitized collection of six 19th-century English periodicals\r\n\r\nThe ground truth contains 358 cropped images of text blocks from 31 pages of 19th century newspaper data","description_withheld":null,"homepage":"https://rdr.ucl.ac.uk/articles/dataset/NCSE_v2_0_A_Dataset_of_OCR-Processed_19th_Century_English_Newspapers/28381610","introduced_date":"2025-02-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/reading-the-unreadable-creating-a-dataset-of","title":"Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models","first_author":"Jonathan Bourne","url":null},"license":{"name":"CC BY 4.0","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["NCSE v2.0"],"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."}