{"url":"/dataset/newsclippings","name":"NewsCLIPpings","full_name":null,"description_markdown":"**NewsCLIPpings** is a dataset for detecting mismatched images and captions. Different to previous misinformation datasets, in NewsCLIPpings both the images and captions are unmanipulated, but some of them are mismatched.","description_withheld":null,"homepage":"https://github.com/g-luo/news_clippings","introduced_date":"2021-04-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/newsclippings-automatic-generation-of-out-of","title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","first_author":"Grace Luo","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["NewsCLIPpings"],"data_loaders":[{"repo":"https://github.com/g-luo/news_clippings","url":"https://github.com/g-luo/news_clippings","frameworks":["pytorch"]}],"num_papers_in_archive":16,"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."}