{"url":"/dataset/x-claim","name":"X-CLAIM","full_name":null,"description_markdown":"A multilingual dataset for the task of multilingual claim span identification. \r\n\r\nX-CLAIM consists of 7K real-world claims, and social media posts containing them, collected from various social media platforms (e.g., Instagram) in English, Hindi, Punjabi, Tamil, Telugu and Bengali.","description_withheld":null,"homepage":"https://github.com/mbzuai-nlp/x-claim","introduced_date":"2023-10-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/lost-in-translation-found-in-spans","title":"Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media","first_author":"Shubham Mittal","url":null},"license":null,"modalities":[],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Punjabi","url":"/datasets/language/punjabi"}],"variants":["X-CLAIM"],"data_loaders":[],"num_papers_in_archive":3,"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."}