{"url":"/dataset/pubmedcite","name":"PubMedCite","full_name":null,"description_markdown":"**PubMedCite** is a domain-specific dataset with about 192K biomedical scientific papers and a large citation graph preserving 917K citation relationships between them. It is characterized by preserving the salient contents extracted from full texts of references, and the weighted correlation between the salient.\r\n\r\nSource:[CitationSum: Citation-aware Graph Contrastive Learning for Scientific Paper Summarization](https://arxiv.org/pdf/2301.11223v1.pdfhttps://arxiv.org/pdf/2301.11223v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2301.11223v1.pdf](https://arxiv.org/pdf/2301.11223v1.pdf)","description_withheld":null,"homepage":"https://anonymous.4open.science/r/CitationSum-AE41/README.md","introduced_date":"2023-01-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/citationsum-citation-aware-graph-contrastive","title":"CitationSum: Citation-aware Graph Contrastive Learning for Scientific Paper Summarization","first_author":"Zheheng Luo","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Biomedical","url":"/datasets/modality/biomedical"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PubMedCite"],"data_loaders":[],"num_papers_in_archive":3,"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."}