{"access":"open","annotations":"MeSH indexing, article metadata, figure captions; no oncology-specific labels beyond MeSH.","article":null,"cancer_slugs":["pan-cancer"],"details":"","doi":null,"formats":["text","JSON","PNG"],"hf":null,"huggingface":null,"kind":"corpus","license":"PubMed metadata public domain; PMC OA articles under CC licences per article","modalities":["literature"],"models":[{"name":"BiomedCLIP","note":"","role":"pretraining","slug":"biomedclip"},{"name":"BiomedBERT (PubMedBERT)","note":"","role":"pretraining","slug":"biomedbert"},{"name":"CONCH","note":"figure\u2013caption pairs from the PMC open-access subset","role":"pretraining","slug":"conch"},{"name":"CONCH","note":"","role":"training","slug":"conch"},{"name":"BiomedCLIP","note":"","role":"training","slug":"biomedclip"}],"name":"PubMed / PMC Open Access Subset","page":"/ai-oncology/datasets/pubmed-pmc-oa","provider":"US National Library of Medicine","size":{"items":36000000,"notes_en":"abstracts for all of PubMed; full text and figures for the open-access subset","notes_pl":"abstrakty ca\u0142ego PubMed; pe\u0142ne teksty i ryciny dla podzbioru open-access","unit":"citations (PubMed); millions of full texts in PMC OA"},"slug":"pubmed-pmc-oa","sources":[{"label":"PMC Open Access Subset","url":"https://pmc.ncbi.nlm.nih.gov/tools/openftlist/"}],"summary":"The literature corpus behind BiomedBERT, BiomedCLIP and CONCH's caption data; the entry point for any oncology NLP or vision-language pretraining.","tasks":["information-extraction","question-answering","image-text-retrieval"],"url":"https://pmc.ncbi.nlm.nih.gov/tools/openftlist/","verified_at":"2026-09-05T22:25:59.060602"}