{"url":"/dataset/aquamuse","name":"aquamuse","full_name":null,"description_markdown":"5,519 query-based summaries, each associated with an average of 6 input documents selected from an index of 355M documents from Common Crawl.\r\n\r\nSource: [AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization](/paper/aquamuse-automatically-generating-datasets)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/aquamuse","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/aquamuse-automatically-generating-datasets","title":"AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization","first_author":"Sayali Kulkarni","url":null},"license":null,"modalities":[],"tasks":[{"name":"Abstractive Text Summarization","url":"/task/abstractive-text-summarization","datasets_with_task":"/datasets/task/abstractive-text-summarization"},{"name":"Document Summarization","url":"/task/document-summarization","datasets_with_task":"/datasets/task/document-summarization"},{"name":"Multi-Document Summarization","url":"/task/multi-document-summarization","datasets_with_task":"/datasets/task/multi-document-summarization"}],"languages":[],"variants":["aquamuse"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/aquamuse","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/aquamuse","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/aquamuse","url":"https://github.com/google-research-datasets/aquamuse","frameworks":["tf"]}],"num_papers_in_archive":11,"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."}