{"url":"/dataset/cqadupstack","name":"CQADupStack","full_name":null,"description_markdown":"CQADupStack is a benchmark dataset for community question-answering research. It contains threads from twelve StackExchange subforums, annotated with duplicate question information. Pre-defined training and test splits are provided, both for retrieval and classification experiments, to ensure maximum comparability between different studies using the set. Furthermore, it comes with a script to manipulate the data in various ways.","description_withheld":null,"homepage":"https://github.com/D1Doris/CQADupStack","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"}],"languages":[],"variants":["CQADupStack"],"data_loaders":[{"repo":"https://github.com/D1Doris/CQADupStack","url":"https://github.com/D1Doris/CQADupStack","frameworks":[]}],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/information-retrieval-on-cqadupstack","task":"Information Retrieval","dataset_variant":"CQADupStack","rows":2,"metrics":["mAP@100"],"first_row_in_archive_order":{"model":"SGPT-BE-5.8B","paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","metrics":{"mAP@100":"0.160"},"code_links":[{"title":"muennighoff/sgpt","url":"https://github.com/muennighoff/sgpt"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sgpt-gpt-sentence-embeddings-for-semantic","title":"SGPT: GPT Sentence Embeddings for Semantic Search","date":"2022-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"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."}