{"url":"/dataset/scirex","name":"SciREX","full_name":"SciREX","description_markdown":"SCIREX is a document level IE dataset that encompasses multiple IE tasks, including salient entity identification and document level N-ary relation identification from scientific articles. The dataset is annotated by integrating automatic and human annotations, leveraging existing scientific knowledge resources.\r\n\r\nSource: [SCIREX: A Challenge Dataset for Document-Level Information Extraction](https://arxiv.org/pdf/2005.00512v1.pdf)","description_withheld":null,"homepage":"https://github.com/allenai/SciREX","introduced_date":"2020-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/scirex-a-challenge-dataset-for-document-level","title":"SciREX: A Challenge Dataset for Document-Level Information Extraction","first_author":"Sarthak Jain","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Event Extraction","url":"/task/event-extraction","datasets_with_task":"/datasets/task/event-extraction"},{"name":"Binary Relation Extraction","url":"/task/binary-relation-extraction","datasets_with_task":"/datasets/task/binary-relation-extraction"},{"name":"Structured Prediction","url":"/task/structured-prediction","datasets_with_task":"/datasets/task/structured-prediction"},{"name":"4-ary Relation Extraction","url":"/task/4-ary-relation-extraction","datasets_with_task":"/datasets/task/4-ary-relation-extraction"}],"languages":[],"variants":["SciREX"],"data_loaders":[{"repo":"https://github.com/allenai/SciREX","url":"https://github.com/allenai/SciREX","frameworks":[]}],"num_papers_in_archive":33,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/4-ary-relation-extraction-on-scirex","task":"4-ary Relation Extraction","dataset_variant":"SciREX","rows":1,"metrics":["Avg. F1"],"first_row_in_archive_order":{"model":"TempGen","paper":"/paper/document-level-entity-based-extraction-as","metrics":{"Avg. F1":"3.55"},"code_links":[{"title":"PlusLabNLP/TempGen","url":"https://github.com/PlusLabNLP/TempGen"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/binary-relation-extraction-on-scirex","task":"Binary Relation Extraction","dataset_variant":"SciREX","rows":1,"metrics":["Avg. F1"],"first_row_in_archive_order":{"model":"TempGen","paper":"/paper/document-level-entity-based-extraction-as","metrics":{"Avg. F1":"14.47"},"code_links":[{"title":"PlusLabNLP/TempGen","url":"https://github.com/PlusLabNLP/TempGen"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/document-level-entity-based-extraction-as","title":"Document-level Entity-based Extraction as Template Generation","date":"2021-09-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"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":1,"samples_harvested":10,"samples_ran":0,"samples_unverified":10,"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."}