将化学文献中的发现拆成可检索的声明，实现跨论文精准查找与验证。
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
- 把论文拆成带来源和原文引用的原子化声明，支持精确检索。
- 在基准测试中，使用AskChem的GPT-5.5可100%定位文献来源，优于其他系统。
- 适合需要跨文献整合证据的科研人员和AI代理使用。
化学文献综述常需从多篇论文中整合特定发现，但现有检索系统仅返回文档列表。科学家和AI代理需手动定位信息、验证出处并拼合答案。我们提出AskChem，一种以声明为中心的跨论文化学文献检索基础设施。将每篇论文转化为携带来源的原子化、类型化声明，每个声明均关联源DOI和原文引文或明确证据定位。基于共享声明库，AskChem提供互补结构：稳定化的分面分类体系用于层级检索与浏览，证据图谱通过关系连接声明，以及探索式动态分类体系将论文按科学原理归类。目前，AskChem已索引14.7万篇论文中的240万条声明，并提供网页界面及REST、SDK、MCP接口供AI代理使用。在AskChem-Bench测试中，将GPT-5.5读者接入AskChem后，100%的文献来源可被解析，未启用检索时为88.3%，且引用密度居五种系统之首。AskChem已上线：https://askchem.org。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。