Paper 2607.28618
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
- Published
- Jul 2026
- Research lab
- Independent
- Citations
- 0
- GitHub
- Not linked
01 In brief
Summary
AskChem is a claim-centered infrastructure for cross-paper chemistry search, shifting the retrieval unit from documents to provenance-carrying claims.
Each claim is an atomic, typed assertion extracted from a paper, grounded by a source DOI and a verbatim quote or evidence locator.
The system indexes 2.4M claims from 147K papers (1925–2026) and exposes three complementary structures: a stabilized faceted taxonomy for hierarchical retrieval, an evidence graph linking claims via typed relations (e.g., supports, contradicts), and an exploratory living taxonomy organizing papers under scientific principles.
Access is provided via web UI, REST API, SDK, and MCP.
On AskChem-Bench (30 cross-paper questions), grounding a GPT-5.5 reader in AskChem yields 100% resolvable DOIs (vs.
88.3% without retrieval) and the highest citation density (18.1 verified DOIs per answer).
The evidence graph shows 97.9% edge-type precision in an expert audit.
AskChem is live at https://askchem.org, with MIT-licensed code and a CC-BY index snapshot.
Limitations include partial corpus coverage and potential LLM extraction errors, mitigated by provenance and community flagging.
The system aims to reduce citation fabrication and support verifiable AI-assisted chemistry workflows, not replace reading primary sources.
02 From the paper
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.