{"url":"/dataset/scirepeval","name":"SciRepEval","full_name":null,"description_markdown":"**SciRepEval** is a comprehensive benchmark for training and evaluating scientific document representations. It includes 25 challenging and realistic tasks, 11 of which are new, across four formats: classification, regression, ranking and search.\r\n\r\nSource: [SciRepEval: A Multi-Format Benchmark for Scientific Document Representations](https://arxiv.org/pdf/2211.13308v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.13308v1.pdf](https://arxiv.org/pdf/2211.13308v1.pdf)","description_withheld":null,"homepage":"https://github.com/allenai/scirepeval","introduced_date":"2022-11-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/scirepeval-a-multi-format-benchmark-for","title":"SciRepEval: A Multi-Format Benchmark for Scientific Document Representations","first_author":"Amanpreet Singh","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/allenai/scirepeval/blob/main/LICENSE.md"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"regression","url":"/task/regression-1","datasets_with_task":"/datasets/task/regression-1"},{"name":"Ad-Hoc Information Retrieval","url":"/task/ad-hoc-information-retrieval","datasets_with_task":"/datasets/task/ad-hoc-information-retrieval"}],"languages":[],"variants":["SciRepEval"],"data_loaders":[{"repo":"https://github.com/allenai/scirepeval","url":"https://github.com/allenai/scirepeval","frameworks":["pytorch"]}],"num_papers_in_archive":9,"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."}