{"url":"/dataset/scico","name":"SciCo","full_name":"Scientific Concept Induction Corpus","description_markdown":"**SciCo** is an expert-annotated dataset for hierarchical CDCR (cross-document coreference resolution) for concepts in scientific papers, with the goal of jointly inferring coreference clusters and hierarchy between them.","description_withheld":null,"homepage":"https://scico.apps.allenai.org/","introduced_date":"2021-04-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/scico-hierarchical-cross-document-coreference","title":"SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts","first_author":"Arie Cattan","url":null},"license":{"name":"Apache License 2.0","url":"https://www.apache.org/licenses/LICENSE-2.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Cross Document Coreference Resolution","url":"/task/cross-document-coreference-resolution","datasets_with_task":"/datasets/task/cross-document-coreference-resolution"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SciCo"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/scico","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"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."}