PulseAugur
实时 06:10:40
English(EN) Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch

新的学术搜索工具 Crase 限制引用探索以提高召回率

研究人员开发了 Crase,一种新的学术搜索方法,它限制了引用网络的探索。与开放式深度研究代理不同,Crase 首先通过搜索引擎查询初始论文,然后扩展到固定的 1.5 跳引用邻域。它会修剪缺乏证据支持的声明的边,并使用具有时间感知能力的随机游走对剩余论文进行排名,从而使搜索过程透明且有界。在 LitSearch 和其他数据集上的基准测试表明,与专有的深度研究代理相比,Crase 的召回率提高了三倍,成本却降低了三分之一。 AI

影响 这种结构化的学术搜索方法可以提高依赖人工智能工具的研究人员的效率并降低成本。

排序理由 该项目是一篇研究论文,详细介绍了一种新的学术搜索方法。[lever_c_demoted from research: ic=1 ai=0.7]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的学术搜索工具 Crase 限制引用探索以提高召回率

本文如何被排名

Signal score
3 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该项目是一篇研究论文,详细介绍了一种新的学术搜索方法。[lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Animesh Mukherjee ·

    面向基于证据的学术深度搜索的结构化约束智能体图探索

    We present Crase, a bounded and inspectable alternative to deep research agents for scholarly search. Instead of an open-ended search loop, Crase queries a search engine once for seed papers, expands them along their 1.5-hop citation neighborhood, prunes citation edges whose clai…