SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers

ArXi:2605.29059v1 Announce Type: cross Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studies use narrow datasets, inconsistent metrics, and limited semantic consistency checks. This gap is increasingly important as large language models (LLMs) begin to generate source-like Solidity that may compile and appear plausible, even when its semantics diverge from the original contract. We