{"url":"/dataset/lot-insts","name":"Lot-insts","full_name":"Long-Tailed instituition names","description_markdown":"LoT-insts contains over 25k classes whose frequencies are naturally long-tail distributed. Its test set from four different subsets: many-, medium-, and few-shot sets, as well as a zero-shot open set. To our best knowledge, this is the first natural language dataset that focuses on this long-tailed and open classification problem.","description_withheld":null,"homepage":"https://lot-insts.github.io/","introduced_date":"2023-02-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/text-classification-in-the-wild-a-large-scale","title":"Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset","first_author":"Jiexing Qi","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Long-tail Learning","url":"/task/long-tail-learning","datasets_with_task":"/datasets/task/long-tail-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Lot-insts"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-classification-on-lot-insts","task":"Text Classification","dataset_variant":"Lot-insts","rows":5,"metrics":["Accuracy","Macro-F1"],"first_row_in_archive_order":{"model":"Character-BERT+RS","paper":"/paper/text-classification-in-the-wild-a-large-scale","metrics":{"Accuracy":"83.73","Macro-F1":"65.9"},"code_links":[{"title":"lumia-group/lot-insts","url":"https://github.com/lumia-group/lot-insts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/long-tail-learning-on-lot-insts","task":"Long-tail Learning","dataset_variant":"Lot-insts","rows":1,"metrics":[" Macro-F1"],"first_row_in_archive_order":{"model":"Character-BERT+RS","paper":"/paper/text-classification-in-the-wild-a-large-scale","metrics":{" Macro-F1":"65.90"},"code_links":[{"title":"lumia-group/lot-insts","url":"https://github.com/lumia-group/lot-insts"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/text-classification-in-the-wild-a-large-scale","title":"Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset","date":"2023-02-19","rows_on_this_dataset":6,"code_links":1,"syntology":null}],"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."}