PulseAugur
EN
LIVE 06:02:44

New scholarly search tool Crase limits citation exploration for better recall

By PulseAugur Editorial · [1 sources] ·

Researchers have developed Crase, a novel approach to scholarly search that limits the exploration of citation networks. Unlike open-ended deep research agents, Crase begins by querying a search engine for initial papers, then expands to a fixed 1.5-hop citation neighborhood. It prunes edges where claims lack supporting evidence and ranks remaining papers using a recency-aware random walk, making the search process transparent and bounded. Benchmarks on LitSearch and other datasets show Crase achieving up to three times the recall at a third of the cost compared to proprietary deep research agents. AI

IMPACT This structured approach to scholarly search could improve efficiency and reduce costs for researchers relying on AI-powered tools.

RANK_REASON The item is a research paper detailing a new method for scholarly search. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.IR (Information Retrieval) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New scholarly search tool Crase limits citation exploration for better recall

How we ranked this

Signal score
3 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item is a research paper detailing a new method for scholarly search. [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.

Full methodology in our editorial standards.

COVERAGE [1]

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

    Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch

    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…

RELATED ENTITIES

RELATED TOPICS