PulseAugur
实时 23:57:37
English(EN) AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis

AskChem系统将化学文献检索从论文转变为声明 · 跟踪3个来源

研究人员开发了AskChem,这是一种新颖的基础设施,旨在通过将检索从整篇论文转移到带有来源信息的单个声明,来改进化学文献合成。该系统索引了来自147,000篇论文的240万个声明,提供了一个分面分类法和一个证据图,以增强搜索和合成。当与GPT-5.5等AI代理集成时,与传统搜索方法相比,AskChem显著提高了可解析DOI率和引用密度。 AI

影响 通过实现更精确和可验证的信息检索,增强了科学研究的AI代理能力。

排序理由 该集群描述了一篇关于科学文献合成新颖基础设施的最新研究论文。

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

AskChem系统将化学文献检索从论文转变为声明 · 跟踪3个来源

报道来源 [3]

  1. arXiv cs.CL TIER_1 English(EN) · Bing Yan, Gregory Wolfe, Stefano Martiniani, Kyunghyun Cho ·

    AskChem:面向化学文献合成的以声明为中心的架构

    arXiv:2607.28618v1 Announce Type: new 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…

  2. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Kyunghyun Cho ·

    AskChem:以声明为中心的化学文献合成基础设施

    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 pr…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    AskChem:面向化学文献合成的以声明为中心的架构

    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 pr…