{"url":"/dataset/scicite","name":"SciCite","full_name":"SciCite","description_markdown":"**SciCite** is a dataset of citation intents that addresses multiple scientific domains and is more than five times larger than ACL-ARC.\n\nSource: [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://arxiv.org/abs/1904.01608)\nImage Source: [https://arxiv.org/pdf/1904.01608v2.pdf](https://arxiv.org/pdf/1904.01608v2.pdf)","description_withheld":null,"homepage":"https://github.com/allenai/scicite","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/structural-scaffolds-for-citation-intent","title":"Structural Scaffolds for Citation Intent Classification in Scientific Publications","first_author":"Arman Cohan","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentence Classification","url":"/task/sentence-classification","datasets_with_task":"/datasets/task/sentence-classification"},{"name":"Citation Intent Classification","url":"/task/citation-intent-classification","datasets_with_task":"/datasets/task/citation-intent-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ScienceCite","SciCite"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/scicite","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/scicite","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/scillm/SciCite","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/scicite","frameworks":["tf","jax"]},{"repo":"https://github.com/allenai/scicite","url":"https://github.com/allenai/scicite","frameworks":[]}],"num_papers_in_archive":40,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/citation-intent-classification-on-scicite","task":"Citation Intent Classification","dataset_variant":"SciCite","rows":8,"metrics":["Macro-F1"],"first_row_in_archive_order":{"model":"EnsIntWS","paper":"/paper/why-do-you-cite-an-investigation-on-citation","metrics":{"Macro-F1":"89.46"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sentence-classification-on-scicite","task":"Sentence Classification","dataset_variant":"SciCite","rows":5,"metrics":["F1"],"first_row_in_archive_order":{"model":"SciBERT","paper":"/paper/scibert-pretrained-contextualized-embeddings","metrics":{"F1":"84.9"},"code_links":[{"title":"allenai/scibert","url":"https://github.com/allenai/scibert"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"tetsu9923/scireviewgen","url":"https://github.com/tetsu9923/scireviewgen"},{"title":"georgetown-cset/ai-relevant-papers","url":"https://github.com/georgetown-cset/ai-relevant-papers"},{"title":"kuldeep7688/BioMedicalBertNer","url":"https://github.com/kuldeep7688/BioMedicalBertNer"},{"title":"hoangcuongnguyen2001/scibert-for-technique-classification","url":"https://github.com/hoangcuongnguyen2001/scibert-for-technique-classification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/sentence-classification-on-sciencecite","task":"Sentence Classification","dataset_variant":"ScienceCite","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"SciBERT (SciVocab)","paper":"/paper/scibert-pretrained-contextualized-embeddings","metrics":{"F1":"84.99"},"code_links":[{"title":"allenai/scibert","url":"https://github.com/allenai/scibert"},{"title":"charles9n/bert-sklearn","url":"https://github.com/charles9n/bert-sklearn"},{"title":"tetsu9923/scireviewgen","url":"https://github.com/tetsu9923/scireviewgen"},{"title":"georgetown-cset/ai-relevant-papers","url":"https://github.com/georgetown-cset/ai-relevant-papers"},{"title":"kuldeep7688/BioMedicalBertNer","url":"https://github.com/kuldeep7688/BioMedicalBertNer"},{"title":"hoangcuongnguyen2001/scibert-for-technique-classification","url":"https://github.com/hoangcuongnguyen2001/scibert-for-technique-classification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/leveraging-gans-for-citation-intent","title":"Leveraging GANs for citation intent classification and its impact on citation network analysis","date":"2025-05-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/why-do-you-cite-an-investigation-on-citation","title":"Why do you cite? An investigation on citation intents and decision-making classification processes","date":"2024-07-18","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/citeprompt-using-prompts-to-identify-citation","title":"CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers","date":"2023-04-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/impactcite-an-xlnet-based-method-for-citation","title":"ImpactCite: An XLNet-based method for Citation Impact Analysis","date":"2020-05-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/structural-scaffolds-for-citation-intent","title":"Structural Scaffolds for Citation Intent Classification in Scientific Publications","date":"2019-04-02","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/scibert-pretrained-contextualized-embeddings","title":"SciBERT: A Pretrained Language Model for Scientific Text","date":"2019-03-26","rows_on_this_dataset":4,"code_links":6,"syntology":null},{"paper":"/paper/measuring-the-evolution-of-a-scientific-field","title":"Measuring the Evolution of a Scientific Field through Citation Frames","date":"2018-01-01","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":5,"samples_ran":0,"samples_unverified":5,"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."}