Year: 2026
Type: conference-paper
Abstract: The paper extends the Data Movement Distance (DMD) -a metric defined to measure the locality in computer memory -to text by defining a normalized version called nDMD.A key feature of nDMD is a new term designed to better characterize low-frequency tokens.By evaluating nDMD on English subset of the M4 dataset and GenAI detection shared task, the paper shows three key findings.First, nDMD is systematically higher in humanwritten text than in machine-generated text.Second, nDMD-based features not only outperform frequency baselines but also improve overall performance when combined.Finally, the proposed DMD normalization is more effective in distinguishing human and machine text than alternative normalization approaches.
Authors: Yiyang Wang, Chen Ding, Hangfeng He
Institution: University of Rochester
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140117773