{"url":"/dataset/auxai","name":"AuxAI","full_name":null,"description_markdown":"**AuxAI** is a distantly supervised dataset for acronym identification.\n\nSource: [https://github.com/PrimerAI/sdu-data](https://github.com/PrimerAI/sdu-data)","description_withheld":null,"homepage":"https://github.com/PrimerAI/sdu-data","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/primer-ai-s-systems-for-acronym","title":"Primer AI's Systems for Acronym Identification and Disambiguation","first_author":"Nicholas Egan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentence Embeddings","url":"/task/sentence-embeddings","datasets_with_task":"/datasets/task/sentence-embeddings"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["AuxAI"],"data_loaders":[{"repo":"https://github.com/PrimerAI/sdu-data","url":"https://github.com/PrimerAI/sdu-data","frameworks":[]}],"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."}