AI for science
Scientific discovery depends on finding the right evidence, making sense of it, and turning it into new ideas. We’re building AI models and tools that help researchers search and synthesize scientific knowledge, accelerating the path from question to discovery.
Asta
Asta is Ai2’s ecosystem of agents designed to accelerate science while preserving user agency and scientific freedom. Co-designed with domain scientists, Asta’s mission is to inspire new research methodologies toward novel discoveries.
Unlocking discoveries
Ai2 is actively working on technologies to help with scientific research, data analysis, and ultimately assist scientists in making novel discoveries. Check out our recent research and open resources in this important area.
olmOCR
olmOCR is an open-source tool designed for high-throughput conversion of PDFs and other documents into plain text while preserving natural reading order. It supports tables, equations, handwriting, and more.
Semantic Scholar
Find relevant papers. Explore new knowledge. Stay up-to-date. Understand the paper. Our free, AI-driven tools help you search, discover, and consume scientific knowledge in more efficient ways.
Scientific datasets
Ai2 collects and provides open and programmatic access to large corpora of scientific text to encourage researchers and developers to create tools for better understanding and engaging with scientific publications.
S2ORC - A large corpus of structured full text for English-language open access academic papers. It is the largest publicly available collection of machine-readable academic text, comprising over 10M documents.
S2AG - A large collection of over 200M paper titles, abstracts, citations, and other metadata of open access papers from the Semantic Scholar Academic Graph.
