Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

AskChem: A Claim-Centered Search Engine for Chemistry Literature

AI By Crimson AI Hugging Face Papers 31 July 2026 · 00:00 20 views
Share: X Telegram

Hugging Face researchers introduce AskChem, a claim-centered infrastructure that converts chemistry papers into atomic, provenance-carrying claims, enabling more precise cross-paper search and synthesis. The system indexes 2.4 million claims from 147,000 papers and shows significant improvements in citation grounding.

AskChem: A Claim-Centered Search Engine for Chemistry Literature

Key points

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.

MetricWith AskChemWithout Retrieval
Resolvable DOIs100%88.3%
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1