{"url":"/dataset/scihtc","name":"SciHTC","full_name":null,"description_markdown":"**SciHTC** is a dataset for hierarchical multi-label text classification (HMLTC) of scientific papers which contains 186,160 papers and 1,233 categories from the ACM CCS tree.\r\n\r\nSource: [Hierarchical Multi-Label Classification of Scientific Documents](https://arxiv.org/pdf/2211.02810v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.02810v1.pdf](https://arxiv.org/pdf/2211.02810v1.pdf)","description_withheld":null,"homepage":"https://github.com/msadat3/SciHTC","introduced_date":"2022-11-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/hierarchical-multi-label-classification-of-1","title":"Hierarchical Multi-Label Classification of Scientific Documents","first_author":"Mobashir Sadat","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Multi-Label Text Classification","url":"/task/multi-label-text-classification","datasets_with_task":"/datasets/task/multi-label-text-classification"},{"name":"Hierarchical Multi-label Classification","url":"/task/hierarchical-multi-label-classification","datasets_with_task":"/datasets/task/hierarchical-multi-label-classification"}],"languages":[],"variants":["SciHTC"],"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."}