{"url":"/dataset/askubuntu","name":"AskUbuntu","full_name":null,"description_markdown":"AskUbuntu question dataset is a preprocessed collection of questions taken from the AskUbuntu.com 2014 corpus dump. It also comes with 400*20 manual annotations, marking pairs of questions as \"similar\" or \"non-similar\".","description_withheld":null,"homepage":"https://github.com/taolei87/askubuntu","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Re-Ranking","url":"/task/re-ranking","datasets_with_task":"/datasets/task/re-ranking"}],"languages":[],"variants":["AskUbuntu"],"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":"2026-09-25T09:33:49+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."}