{"url":"/dataset/mist","name":"MiST","full_name":null,"description_markdown":"**MiST** (Modals In Scientific Text) is a dataset containing 3737 modal instances in five scientific domains annotated for their semantic, pragmatic, or rhetorical function.\r\n\r\nSource: [MIST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text](https://arxiv.org/pdf/2212.07156v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.07156v1.pdf](https://arxiv.org/pdf/2212.07156v1.pdf)","description_withheld":null,"homepage":"https://github.com/boschresearch/mist_emnlp_findings2022","introduced_date":"2022-12-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/mist-a-large-scale-annotated-resource-and","title":"MIST: a Large-Scale Annotated Resource and Neural Models for Functions of Modal Verbs in English Scientific Text","first_author":"Sophie Henning","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"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MiST"],"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."}