Transaction Profiling and Address Role Inference in Tokenized U.S. Treasuries

2025-07-19

AI Summary

This work addresses the lack of empirical studies on trading behaviors of tokenized U.S. Treasuries (e.g., BUIDL, BENJI, USDY) across multi-chain environments—including Ethereum and major Layer-2 networks. We propose a curvature-aware address role inference framework that jointly integrates function-level smart contract call parsing (to identify minting, redemption, transfers, and cross-chain operations), liquidity dynamics modeling, and Poincaré hyperbolic space embedding, enhanced by graph neural networks to learn geometric representations of addresses within liquidity graphs. To our knowledge, this is the first application of hyperbolic geometry to real-world asset (RWA) address role identification. Evaluated on an RWA Treasury dataset, our framework significantly outperforms Euclidean embedding baselines, enabling precise discrimination between institutional and retail activity, anomaly detection, and wallet categorization. Cross-chain generalization experiments confirm its robustness and scalability in heterogeneous multi-chain settings.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Security and Privacy: Cryptocurrency and smart contracts
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies

Abstract

Tokenized U.S. Treasuries have emerged as a prominent subclass of real-world assets (RWAs), offering cryptographically enforced, yield-bearing instruments collateralized by sovereign debt and deployed across multiple blockchain networks. While the market has expanded rapidly, empirical analyses of transaction-level behaviour remain limited. This paper conducts a quantitative, function-level dissection of U.S. Treasury-backed RWA tokens including BUIDL, BENJI, and USDY, across multi-chain: mostly Ethereum and Layer-2s. We analyze decoded contract calls to isolate core functional primitives such as issuance, redemption, transfer, and bridge activity, revealing segmentation in behaviour between institutional actors and retail users. To model address-level economic roles, we introduce a curvature-aware representation learning framework using Poincaré embeddings and liquidity-based graph features. Our method outperforms baseline models on our RWA Treasury dataset in role inference and generalizes to downstream tasks such as anomaly detection and wallet classification in broader blockchain transaction networks. These findings provide a structured understanding of functional heterogeneity and participant roles in tokenized Treasury in a transaction-level perspective, contributing new empirical evidence to the study of on-chain financialization.

Problem

• Analyzes transaction behavior in tokenized U.S. Treasuries
• Models address-level economic roles using representation learning
• Improves role inference and anomaly detection in blockchain networks

Innovation

• Function-level dissection of Treasury-backed RWA tokens
• Curvature-aware representation learning with Poincaré embeddings
• Liquidity-based graph features for role inference