Derived metrics for the game of Go -- intrinsic network strength assessment and cheat-detection

TL;DR

This paper introduces new metrics derived from AI-based Go analysis tools to assess intrinsic network strength and detect cheating, enhancing understanding and integrity in modern Go play.

Contribution

It proposes novel metrics based on AI score estimates and search contributions for better game analysis and cheat detection in Go.

Findings

Intrinsic network strength measurement developed

Move effect analysis for performance evaluation

Effective cheat detection method implemented

Abstract

The widespread availability of superhuman AI engines is changing how we play the ancient game of Go. The open-source software packages developed after the AlphaGo series shifted focus from producing strong playing entities to providing tools for analyzing games. Here we describe two ways of how the innovations of the second generation engines (e.g.~score estimates, variable komi) can be used for defining new metrics that help deepen our understanding of the game. First, we study how much information the search component contributes in addition to the raw neural network policy output. This gives an intrinsic strength measurement for the neural network. Second, we define the effect of a move by the difference in score estimates. This gives a fine-grained, move-by-move performance evaluation of a player. We use this in combating the new challenge of detecting online cheating.