{"url":"/dataset/bentham","name":"Bentham","full_name":"Bentham project","description_markdown":"Bentham manuscripts refers to a large set of documents that were written by the renowned English philosopher and reformer Jeremy Bentham (1748-1832). Volunteers of the Transcribe Bentham initiative transcribed this collection. Currently, >6 000 documents or > 25 000 pages have been transcribed using this public web platform.\r\nFor our experiments, we used the BenthamR0 dataset a part of the Bentham manuscripts.","description_withheld":null,"homepage":"http://www.transcriptorium.eu/~tsdata/BenthamR0/","introduced_date":"2014-04-07","introduced_date_note":null,"introduced_by":null,"license":{"name":"custom","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Handwritten Text Recognition","url":"/task/handwritten-text-recognition","datasets_with_task":"/datasets/task/handwritten-text-recognition"},{"name":"Handwriting Recognition","url":"/task/handwriting-recognition","datasets_with_task":"/datasets/task/handwriting-recognition"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Bentham"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/handwritten-text-recognition-on-bentham","task":"Handwritten Text Recognition","dataset_variant":"Bentham","rows":1,"metrics":["CER"],"first_row_in_archive_order":{"model":"StackMix+Blots","paper":"/paper/stackmix-and-blot-augmentations-for","metrics":{"CER":"1.73"},"code_links":[{"title":"sberbank-ai/StackMix-OCR","url":"https://github.com/sberbank-ai/StackMix-OCR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/stackmix-and-blot-augmentations-for","title":"StackMix and Blot Augmentations for Handwritten Text Recognition","date":"2021-08-26","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."}