{"count":2,"items":[{"access":"open","article":null,"cancer_slugs":["pan-cancer"],"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"],"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","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"},{"access":"open","article":null,"cancer_slugs":["pan-cancer"],"doi":null,"formats":["JSON","CSV"],"hf":null,"huggingface":null,"kind":"registry","license":"public domain","modalities":["clinical-text"],"name":"ClinicalTrials.gov","page":"/ai-oncology/datasets/clinicaltrials-gov","provider":"US National Library of Medicine","size":{"items":500000,"notes_en":"structured eligibility criteria, arms, outcomes and results; full API","notes_pl":"ustrukturyzowane kryteria kwalifikacji, ramiona, punkty ko\u0144cowe i wyniki; pe\u0142ne API","unit":"registered studies"},"slug":"clinicaltrials-gov","summary":"The registry that trial-matching systems such as TrialGPT retrieve from; oncology is its largest therapeutic area.","tasks":["clinical-trial-matching","information-extraction"],"url":"https://clinicaltrials.gov/","verified_at":"2026-09-05T22:25:59.082279"}]}