{"url":"/dataset/spiced","name":"Spiced","full_name":null,"description_markdown":"**Spiced** is a paraphrase dataset of scientific findings annotated for degree of information change. Spiced contains 6,000 scientific finding pairs extracted from news stories, social media discussions, and full texts of original papers.\r\n\r\nSource: [Modeling Information Change in Science Communication with Semantically Matched Paraphrases](https://arxiv.org/pdf/2210.13001v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.13001v1.pdf](https://arxiv.org/pdf/2210.13001v1.pdf)","description_withheld":null,"homepage":"http://www.copenlu.com/publication/2022_emnlp_wright/","introduced_date":"2022-10-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/modeling-information-change-in-science","title":"Modeling Information Change in Science Communication with Semantically Matched Paraphrases","first_author":"Dustin Wright","url":null},"license":{"name":"MIT license","url":"https://huggingface.co/datasets?license=license:mit"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Retrieval","url":"/task/retrieval","datasets_with_task":"/datasets/task/retrieval"},{"name":"Fact Checking","url":"/task/fact-checking","datasets_with_task":"/datasets/task/fact-checking"}],"languages":[],"variants":["Spiced"],"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."}