{"url":"/dataset/edgar-corpus","name":"EDGAR-CORPUS","full_name":null,"description_markdown":"EDGAR-CORPUS is a novel corpus comprising annual reports from all the publicly traded companies in the US spanning a period of more than 25 years. All the reports are downloaded, split into their corresponding items (sections), and provided in a clean, easy-to-use JSON format. \r\n\r\nImage source: [https://arxiv.org/pdf/2109.14394v1.pdf](https://arxiv.org/pdf/2109.14394v1.pdf)","description_withheld":null,"homepage":"https://zenodo.org/record/5528490#.YVV1V0bMJ6o","introduced_date":"2021-09-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/edgar-corpus-billions-of-tokens-make-the","title":"EDGAR-CORPUS: Billions of Tokens Make The World Go Round","first_author":"Lefteris Loukas","url":null},"license":{"name":"Attribution 4.0 International","url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["EDGAR-CORPUS"],"data_loaders":[],"num_papers_in_archive":2,"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."}