{"url":"/dataset/curation-corpus","name":"Curation Corpus","full_name":null,"description_markdown":"The Curation Corpus is a collection of 40,000 professionally-written summaries of news articles, with links to the articles themselves. \r\n\r\nSource: [Curation Corpus](https://github.com/CurationCorp/curation-corpus)","description_withheld":null,"homepage":"https://github.com/CurationCorp/curation-corpus","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[],"variants":["Curation Corpus"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/d0rj/curation-corpus","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/CurationCorp/curation-corpus","url":"https://github.com/CurationCorp/curation-corpus","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-curation-corpus","task":"Language Modelling","dataset_variant":"Curation Corpus","rows":1,"metrics":["BPB"],"first_row_in_archive_order":{"model":"Gopher","paper":"/paper/scaling-language-models-methods-analysis-1","metrics":{"BPB":"0.475"},"code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","rows_on_this_dataset":1,"code_links":3,"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."}