---
title: "AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.28618v1"
permalink: "https://feed.astralor.com/items/itm_f2552ca7b9a24c7fc6fcac05"
published: "2026-07-30T17:59:11.000Z"
score: 78
channel: "ai"
tags: ["AI Agent","AskChem","Chemistry Literature Search","Claim-Level Retrieval","Evidence Graph"]
---

# AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

## AI commentary

> What stands out most is moving from paper-level citation to claim-level evidence, and opening an MCP interface for AI agents, effectively building an auditable evidence pipeline between chemistry literature and agents. For anyone working on RAG or scientific QA, the AskChem-Bench DOI resolvability metric is worth borrowing directly, especially the 100% vs 88.3% gap showing retrieval granularity heavily impacts answer trustworthiness. If you are building knowledge bases in chemistry, materials, or life sciences, this architecture can be adapted quickly.

## At a glance

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 provenance, and assemble cross-paper answers manually. AskChem changes the unit of retrieval from the paper to provenance-carrying claims: each paper is converted into atomic, typed claims grounded by a source DOI and a verbatim quote or explicit evidence locator. AskChem exposes complementary structures including a stabilized faceted taxonomy, an evidence graph, and an exploratory living taxonomy. It currently indexes 2.4M claims from 147K papers and provides web, 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.

## Key points

- AskChem shifts the retrieval unit from papers to atomic claims with provenance, each grounded by a DOI and a verbatim quote or evidence locator.
- It offers three complementary structures: a stabilized faceted taxonomy, an evidence graph, and an exploratory living taxonomy.
- The system indexes 2.4M claims from 147K papers and provides Web, REST, SDK, and MCP interfaces for AI agents.
- On AskChem-Bench, grounding a GPT-5.5 reader in AskChem lifts resolvable DOIs from 88.3% to 100%.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_f2552ca7b9a24c7fc6fcac05