arXivSondos Mahmoud Bsharat, Jiacheng Liu, Xiaohan Zhao, Tianjun Yao, Xinyi Shang, Yi Tang, Jiacheng Cui, Ahmed Elhagry, Salwa K. Al Khatib, Hao Li, Salman Khan, Zhiqiang ShenThu, Jun 4, 2026, 10:58 AM PDT
score 17.2
Benchmark reveals how AI-edited documents become detectable
Original: Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection
Source: arxiv.org ↗
Writing ELI5 summary…