{"url":"/dataset/oagt","name":"OAGT","full_name":"Paper Topic Dataset","description_markdown":"OAGL is a paper topic dataset consisting of 6942930 records which comprise various scientific publication attributes like abstracts, titles, keywords, publication years, venues, etc. The last two fields of each record are the topic id from a taxonomy of 27 topics created from the entire collection and the 20 most significant topic words. Each dataset record (sample) is stored as a JSON line in the text file.","description_withheld":null,"homepage":"https://zenodo.org/record/6560535","introduced_date":"2022-05-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/topic-segmentation-of-research-article","title":"Topic Segmentation of Research Article Collections","first_author":"Erion Çano","url":null},"license":{"name":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Topic Models","url":"/task/topic-models","datasets_with_task":"/datasets/task/topic-models"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OAGT"],"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."}