{"url":"/dataset/pmc-oa","name":"PMC-OA","full_name":"PubmedCentral OpenAcess","description_markdown":"**PMC-OA** is a large-scale dataset that contains 1.65M image-text pairs. The figures and captions from PubMed Central, 2,478,267 available papers are covered and 12,211,907 figure-caption pairs are extracted. \r\n\r\nSource:[PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://arxiv.org/pdf/2303.07240v1.pdf)","description_withheld":null,"homepage":"https://huggingface.co/datasets/axiong/pmc-oa","introduced_date":"2023-03-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/pmc-clip-contrastive-language-image-pre","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","first_author":"Weixiong Lin","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["PMC-OA"],"data_loaders":[],"num_papers_in_archive":31,"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."}