Location
Havener Center, Miner Lounge / Wiese Atrium, 1:30pm-3:30pm
Start Date
4-1-2026 1:30 PM
End Date
4-1-2026 3:30 PM
Presentation Date
April 1, 2026; 1:30pm-3:30pm
Description
The proliferation of chess engines has compromised the integrity of online play through both manual assistance and automated bots. This research proposes Si, a novel metric designed to quantify unnatural play by integrating move latency, the relative strength of the selected move, and the density of high-quality alternatives available in a given position. By fitting Si values to theoretical probability distributions across specific Elo ratings and time controls, we establish a statistical baseline for human performance. Discrepancies between an individual's Si profile and these established distributions provide a robust framework for identifying artificially inflated play, offering a potential method for cheat detection in digital chess environments.
Biography
Benjamin Sullins is a Senior Computer Science major at Missouri University of Science and Technology, graduating in May 2026. He currently works as an undergraduate researcher for Dr. Gabriel Nicolosi in the Department of Engineering Management and Systems Engineering at Missouri S&T. His work focuses on developing methods of chess cheat detection in online play using data from Lichess to analyze statistical patterns based on engine evaluations. He serves on the executive board as Logistics Officer for Missouri S&T's ACM chapter.
Benjamin Biehl is a Senior studying Computer Science at Missouri University of Science & Technology. His current research focuses on developing methods for chess cheating detection, where he analyzes game-play data and statistical patterns using information sources for the Lichess API. His work explores how engine-like evaluation differences and move timing can be combined to identify anomalous behavior in competitive chess. He is interested in applying data-driven methods and software engineering techniques to real-world problems involving pattern recognition and decision-making systems.
Meeting Name
2026 - Miners Solving for Tomorrow Research Conference
Department(s)
Engineering Management and Systems Engineering
Document Type
Poster
Document Version
Final Version
File Type
event
Language(s)
English
Rights
© 2026 The Authors, All rights reserved
A Speed-Adjusted Centipawn Metric For Chess Cheating Detection
Havener Center, Miner Lounge / Wiese Atrium, 1:30pm-3:30pm
The proliferation of chess engines has compromised the integrity of online play through both manual assistance and automated bots. This research proposes Si, a novel metric designed to quantify unnatural play by integrating move latency, the relative strength of the selected move, and the density of high-quality alternatives available in a given position. By fitting Si values to theoretical probability distributions across specific Elo ratings and time controls, we establish a statistical baseline for human performance. Discrepancies between an individual's Si profile and these established distributions provide a robust framework for identifying artificially inflated play, offering a potential method for cheat detection in digital chess environments.
Comments
Advisor: Gabriel Nicolosi, gabrielnicolosi@mst.edu