{"url":"/dataset/medisim","name":"medisim","full_name":null,"description_markdown":"**medisim** is a collection of new large-scale medical term similarity datasets based on SNOMED-CT.\n\nSource: [https://github.com/babylonhealth/medisim](https://github.com/babylonhealth/medisim)","description_withheld":null,"homepage":"https://github.com/babylonhealth/medisim","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/can-embeddings-adequately-represent-medical","title":"Can Embeddings Adequately Represent Medical Terminology? New Large-Scale Medical Term Similarity Datasets Have the Answer!","first_author":"Claudia Schulz","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["medisim"],"data_loaders":[{"repo":"https://github.com/babylonhealth/medisim","url":"https://github.com/babylonhealth/medisim","frameworks":[]}],"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."}