{"url":"/dataset/gis","name":"GIS","full_name":"Github Issue Similarity","description_markdown":"This dataset can be used for semantic textual similarity tasks.  It consists of duplicate and non-duplicate Github issues. It has 18565, 1547, and 1548 samples for train, validation, and test set, respectively.","description_withheld":null,"homepage":"https://huggingface.co/datasets/WhereIsAI/github-issue-similarity","introduced_date":"2023-09-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/angle-optimized-text-embeddings","title":"AnglE-optimized Text Embeddings","first_author":"Xianming Li","url":null},"license":{"name":"CC BY-SA","url":null},"modalities":[],"tasks":[{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","datasets_with_task":"/datasets/task/semantic-textual-similarity"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GIS"],"data_loaders":[],"num_papers_in_archive":2,"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."}