Research

Paper

TESTING February 27, 2026

LeGend: A Data-Driven Framework for Lemma Generation in Hardware Model Checking

Authors

Mingkai Miao, Guangyu Hu, Wei Zhang, Hongce Zhang

Abstract

Property checking of RTL designs is a central task in formal verification. Among available engines, IC3/PDR is a widely used backbone whose performance critically depends on inductive generalization, the step that generalizes a concrete counterexample-to-induction (CTI) cube into a lemma. Prior work has explored machine learning to guide this step and achieved encouraging results, yet most methods adopt a per-clause graph analysis paradigm: for each clause they repeatedly build and analyze graphs, incurring heavy overhead and creating a scalability bottleneck. We introduce LeGend, which replaces this paradigm with one-time global representation learning. LeGend pre-trains a domain-adapted self-supervised model to produce latch embeddings that capture global circuit properties. These precomputed embeddings allow a lightweight model to predict high-quality lemmas with negligible overhead, effectively decoupling expensive learning from fast inference. Experiments show LeGend accelerates two state-of-the-art IC3/PDR engines across a diverse set of benchmarks, presenting a promising path to scale up formal verification.

Metadata

arXiv ID: 2602.24010
Provider: ARXIV
Primary Category: cs.AR
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.24010v1</id>\n    <title>LeGend: A Data-Driven Framework for Lemma Generation in Hardware Model Checking</title>\n    <updated>2026-02-27T13:34:48Z</updated>\n    <link href='https://arxiv.org/abs/2602.24010v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.24010v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Property checking of RTL designs is a central task in formal verification. Among available engines, IC3/PDR is a widely used backbone whose performance critically depends on inductive generalization, the step that generalizes a concrete counterexample-to-induction (CTI) cube into a lemma. Prior work has explored machine learning to guide this step and achieved encouraging results, yet most methods adopt a per-clause graph analysis paradigm: for each clause they repeatedly build and analyze graphs, incurring heavy overhead and creating a scalability bottleneck. We introduce LeGend, which replaces this paradigm with one-time global representation learning. LeGend pre-trains a domain-adapted self-supervised model to produce latch embeddings that capture global circuit properties. These precomputed embeddings allow a lightweight model to predict high-quality lemmas with negligible overhead, effectively decoupling expensive learning from fast inference. Experiments show LeGend accelerates two state-of-the-art IC3/PDR engines across a diverse set of benchmarks, presenting a promising path to scale up formal verification.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <published>2026-02-27T13:34:48Z</published>\n    <arxiv:primary_category term='cs.AR'/>\n    <author>\n      <name>Mingkai Miao</name>\n    </author>\n    <author>\n      <name>Guangyu Hu</name>\n    </author>\n    <author>\n      <name>Wei Zhang</name>\n    </author>\n    <author>\n      <name>Hongce Zhang</name>\n    </author>\n  </entry>"
}