Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

Source

arXiv

arxiv.org/abs/2607.28618v1

Read the source

Source

Plain-Language Brief

The paper introduces AskChem, a system that aims to simplify chemistry literature synthesis by converting papers into atomic, typed claims. Each claim is linked to its source and can be searched and synthesized using various structures like a stabilized faceted taxonomy, an evidence graph, and an exploratory living taxonomy. AskChem currently indexes 2.4 million claims from 147,000 papers and provides a web interface for users as well as access for AI agents.

What the Document Says

  • The paper presents AskChem, an infrastructure for cross-paper chemistry search that changes the unit of retrieval from papers to claims.
  • Each claim is grounded by a source DOI and can be a verbatim quote or an explicit evidence locator.
  • AskChem provides complementary structures for search and synthesis: a stabilized faceted taxonomy, an evidence graph, and an exploratory living taxonomy.
  • The system currently indexes 2.4 million claims from 147,000 papers.
  • A web interface, as well as REST, SDK, and MCP access, are available for users.
  • On AskChem-Bench, the grounding of a GPT-5.5 reader in AskChem results in 100% resolvable DOIs compared to 88.3% without retrieval.

Key Concepts Mentioned

  • AskChem
  • claim-centered infrastructure
  • literature synthesis
  • chemistry
  • faceted taxonomy
  • evidence graph
  • exploratory living taxonomy
  • GPT-5.5

Claims Made by the Document

  • AskChem changes the unit of retrieval from papers to claims.
  • Each claim is grounded by a source DOI and can be a verbatim quote or an explicit evidence locator.
  • AskChem provides complementary structures for search and synthesis.
  • AskChem currently indexes 2.4 million claims from 147,000 papers.
  • A web interface, as well as REST, SDK, and MCP access, are available for users.
  • On AskChem-Bench, the grounding of a GPT-5.5 reader in AskChem results in 100% resolvable DOIs compared to 88.3% without retrieval.

Evidence Used

  • The paper describes the functioning and features of AskChem.
  • Results from AskChem-Bench are presented in the paper.

Methods / Approach

  • Converting papers into atomic, typed claims.
  • Providing a stabilized faceted taxonomy, an evidence graph, and an exploratory living taxonomy.

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The paper does not mention any limitations of AskChem as described by the authors.

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • How effective is AskChem in various domains outside of chemistry?
  • What are the potential challenges and solutions for scaling AskChem to larger datasets?

Raw Abstract / Excerpt

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.