We introduce a self-play framework for semantic equivalence in Haskell, utilizing formal verification to guide adversarial training between a generator and an evaluator. The framework leverages Liquid Haskell proofs for validating equivalence and execution-based counterexamples for inequivalence, organized via a difficulty-aware curriculum. To facilitate this, we release \textbf{OpInstruct-HSx}, a synthetic dataset of $\approx$28k validated Haskell programs. Empirical experiments show that our evaluator transfers effectively to downstream tasks, achieving up to 13.3pp accuracy gain on EquiBench and consistent gains on PySecDB. Ablation studies on the SEQ-SINQ regimes indicate that while inequivalence supervision provides data volume, equivalence proofs are uniquely responsible for the model's reasoning capabilities. The entire training pipeline and dataset are publicly released on GitHub and Hugging Face respectively.

翻译：我们提出了一种基于Haskell的语义等价自对弈框架，利用形式化验证引导生成器与评估器之间的对抗训练。该框架通过Liquid Haskell证明验证等价性，并利用执行反例验证不等价性，借助难度感知课程机制进行组织。为支撑该框架，我们发布了\textbf{OpInstruct-HSx}——包含约2.8万个已验证Haskell程序的合成数据集。实验表明，评估器能有效迁移至下游任务，在EquiBench上实现高达13.3个百分点的准确率提升，并在PySecDB上持续获得改善。针对SEQ-SINQ机制的消融研究显示，虽然不等价监督提供了数据规模支撑，但等价性证明才是模型推理能力的根本来源。完整训练流程与数据集已分别发布于GitHub和Hugging Face平台。