{"url":"/dataset/mold","name":"MOLD","full_name":"Marathi Offensive Language Dataset","description_markdown":"**MOLD** is a Marathi dataset for offensive language identification","description_withheld":null,"homepage":"https://github.com/tharindudr/MOLD","introduced_date":"2021-09-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/cross-lingual-offensive-language","title":"Cross-lingual Offensive Language Identification for Low Resource Languages: The Case of Marathi","first_author":"Saurabh Gaikwad","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Marathi","url":"/datasets/language/marathi"}],"variants":["MOLD"],"data_loaders":[],"num_papers_in_archive":6,"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."}