{"url":"/dataset/arxmliv-08-2018","name":"arXMLiv:08.2018","full_name":null,"description_markdown":"This is a second public release of the arXMLiv dataset generated by the KWARC research group. It contains 1,232,186 HTML5 scientific documents from the arXiv.org preprint archive, converted from their respective TeX sources. A 13% increase in available articles over the 08.2017 release.\r\n\r\nThe dataset is segmented in 3 different subsets, each corresponding to a severity level of the LaTeXML software responsible for the HTML5 conversion.\r\n\r\nderivative word embeddings and a token model are available separately [here](https://sigmathling.kwarc.info/resources/arxmliv-embeddings-082018/)","description_withheld":null,"homepage":"https://sigmathling.kwarc.info/resources/arxmliv-dataset-082018/","introduced_date":"2018-08-31","introduced_date_note":null,"introduced_by":null,"license":{"name":"SIGMathLing members, research-only","url":"https://sigmathling.kwarc.info/nda/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["arXMLiv:08.2018"],"data_loaders":[],"num_papers_in_archive":1,"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."}