Dataset of Yul Contracts to Support Solidity Compiler Research

TL;DR

The YulCode dataset offers a large, real-world collection of Yul smart contract instances, enabling advanced research in smart contract analysis, verification, and optimization at the low-level code layer.

Contribution

It introduces the first publicly available, extensive dataset of Yul contracts derived from Ethereum mainnet deployments, supporting low-level smart contract research.

Findings

Provides 348,840 Yul contract instances from real-world deployments

Fills a critical gap in smart contract datasets for low-level analysis

Enables new research avenues in formal verification and optimization

Abstract

The YulCode dataset presents a comprehensive collection of 348,840 Yul-based smart contract instances, comprising approximately 135,013 unique contracts. These contracts were generated through the compilation of Solidity source files that have been deployed on the Ethereum mainnet, making the dataset directly representative of real-world decentralized applications. YulCode provides a rich foundation for a variety of research and development tasks, including but not limited to machine learning applications, formal verification, optimization analysis, and software engineering tool evaluation in the context of low-level smart contract code. To the best of our knowledge at the time of writing, YulCode is the first and only publicly available dataset that focuses specifically on Yul, an intermediate language designed for the Ethereum Virtual Machine (EVM). As such, it fills a critical gap in the current ecosystem of smart contract datasets and opens new avenues for research and tooling aimed at low-level contract analysis and generation.