Reproduce “"PRISM" Is Not All You Need: Cross-Topic Name Collisions and Scientific Paper Retrieval” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jingjie Ning, Xueqi Li, Yibo Kong
The authors study how to identify the intended paper when distinct papers share a title label. They measure name collisions across 144,523 records and find cross-topic collision grew 4.33-fold from 2020–2022 to 2026, versus 1.12-fold within topics. Three abstract-derived clues raise BM25 Top-1 from 30.8% to 70.6% among namesakes, but ambiguity remains.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.