Blockprint Accuracy Study

TL;DR

This study improves the accuracy of Blockprint, a tool for assessing Ethereum client diversity, by evaluating classifiers like KNN and MLP, and proposes methods to mitigate mode-related accuracy declines.

Contribution

It introduces an optimized MLP classifier trained on combined datasets to enhance Blockprint's accuracy in diverse client configurations.

Findings

MLP outperforms KNN in accuracy with less training data

Clients subscribed to all subnets affect attestation inclusion differently

Combined datasets improve model robustness and accuracy

Abstract

Blockprint, a tool for assessing client diversity on the Ethereum beacon chain, is essential for analyzing decentralization. This paper details experiments conducted at MigaLabs to enhance Blockprint's accuracy, evaluating various configurations for the K-Nearest Neighbors (KNN) classifier and exploring the Multi-Layer Perceptron (MLP) classifier as a proposed alternative. Findings suggest that the MLP classifier generally achieves superior accuracy with a smaller training dataset. The study revealed that clients running in different modes, especially those subscribed to all subnets, impact attestation inclusion differently, leading to proposed methods for mitigating the decline in model accuracy. Consequently, the recommendation is to employ an MLP model trained with a combined dataset of slots from both default and subscribed-to-all-subnets client configurations.