Chemistry researchers often struggle to synthesize findings scattered across numerous publications. Traditional literature search systems return ranked document lists, forcing scientists and AI agents to manually locate relevant information, verify provenance, and assemble cross-paper answers. A new system called AskChem aims to change this by shifting the unit of retrieval from the paper to the claim.
AskChem converts each paper into atomic, typed claims, each grounded by a source DOI and a verbatim quote or explicit evidence locator. This shared claim store supports multiple complementary structures: a stabilized faceted taxonomy for hierarchical retrieval, an evidence graph linking claims through relations, and an exploratory living taxonomy that situates papers under scientific principles.
Currently, AskChem indexes 2.4 million claims from 147,000 papers and provides a web interface, as well as REST, SDK, and MCP access for AI agents. On the AskChem-Bench benchmark, grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs, compared to 88.3% without retrieval, and achieves the highest citation density among five tested systems.
The system is live at askchem.org, with open datasets and code available on Hugging Face and GitHub.