{"url":"/dataset/arxivedits","name":"arXivEdits","full_name":null,"description_markdown":"**arXivEdits** an annotated corpus of 751 full papers from arXiv with gold sentence alignment across their multiple versions of revision, as well as fine-grained span-level edits and their underlying intentions for 1,000 sentence pairs. This dataset is designed for studying the human revision process in the scientific writing domain.\r\n\r\nSource: [arXivEdits: Understanding the Human Revision Process in Scientific Writing](https://arxiv.org/pdf/2210.15067v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.15067v1.pdf](https://arxiv.org/pdf/2210.15067v1.pdf)","description_withheld":null,"homepage":"https://tiny.one/arxivedits","introduced_date":"2022-10-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/arxivedits-understanding-the-human-revision","title":"arXivEdits: Understanding the Human Revision Process in Scientific Writing","first_author":"Chao Jiang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"}],"languages":[],"variants":["arXivEdits"],"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."}