{"url":"/dataset/glotsparse","name":"GlotSparse","full_name":null,"description_markdown":"Collection of news websites in low-resource languages.","description_withheld":null,"homepage":"https://huggingface.co/datasets/cis-lmu/GlotSparse","introduced_date":"2023-10-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/glotlid-language-identification-for-low","title":"GlotLID: Language Identification for Low-Resource Languages","first_author":"Amir Hossein Kargaran","url":null},"license":{"name":"CC0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"}],"languages":[{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["GlotSparse"],"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."}