AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
2026-07-30 • Computation and Language
Computation and LanguageArtificial IntelligenceInformation RetrievalMachine Learning
AI summaryⓘ
The authors developed AskChem, a new search system for chemistry research that focuses on finding specific scientific claims instead of entire papers. They break down papers into small, typed claims linked to their sources, making it easier to search, verify, and connect information across different studies. AskChem organizes claims into taxonomies and graphs that help users and AI explore chemistry knowledge more effectively. It currently covers millions of claims from thousands of papers and improves how AI tools can ground their answers in reliable sources.
chemistry literaturescientific claimsclaim provenancefaceted taxonomyevidence graphDOIcross-paper searchAI agentsknowledge synthesis
Authors
Bing Yan, Gregory Wolfe, Stefano Martiniani, Kyunghyun Cho
Abstract
Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists. As a result, scientists and AI agents need to locate relevant information, verify their provenance, and assemble cross-paper answers manually. We present AskChem, a claim-centered infrastructure for cross-paper chemistry search. AskChem changes the unit of retrieval from the paper to the provenance-carrying claim: each paper is converted into atomic, typed claims, each grounded by a source DOI and a verbatim quote or an explicit evidence locator. Over this shared claim store, AskChem exposes complementary structures for search and synthesis: a stabilized faceted taxonomy for hierarchical retrieval and browsing, an evidence graph linking claims through relations, and an exploratory living taxonomy that situates indexed papers under scientific principles. AskChem currently indexes 2.4M claims from 147K papers and provides a web interface, as well as REST, SDK, and MCP access for AI agents. On AskChem-Bench, grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs, compared with 88.3% without retrieval, and the highest citation density among five tested systems. AskChem is live at https://askchem.org.