{"url":"/dataset/digital-peter","name":"Digital Peter","full_name":null,"description_markdown":"Digital Peter is a dataset of Peter the Great's manuscripts annotated for segmentation and text recognition. The dataset may be useful for researchers to train handwriting text recognition models as a benchmark for comparing different models. It consists of 9,694 images and text files corresponding to lines in historical documents. The dataset includes Peter’s handwritten materials covering the period from 1709 to 1713. \r\n\r\nThe open machine learning competition Digital Peter was held based on the considered dataset.","description_withheld":null,"homepage":"https://github.com/MarkPotanin/DigitalPeter","introduced_date":"2021-03-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/digital-peter-dataset-competition-and","title":"Digital Peter: Dataset, Competition and Handwriting Recognition Methods","first_author":"Mark Potanin","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Handwritten Text Recognition","url":"/task/handwritten-text-recognition","datasets_with_task":"/datasets/task/handwritten-text-recognition"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["Digital Peter"],"data_loaders":[{"repo":"https://github.com/MarkPotanin/DigitalPeter","url":"https://github.com/MarkPotanin/DigitalPeter","frameworks":[]}],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/handwritten-text-recognition-on-digital-peter","task":"Handwritten Text Recognition","dataset_variant":"Digital Peter","rows":1,"metrics":["CER"],"first_row_in_archive_order":{"model":"StackMix+Blots","paper":"/paper/stackmix-and-blot-augmentations-for","metrics":{"CER":"2.5"},"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."}