Newest papers

What Do RTL Repair Benchmarks Actually Measure?

Yeyin Eva Zhu, Rishabh Ranawat · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28595 · cited by 0 works (OpenAlex) · open-access PDF

German

RTL Repair Benchmarks sollten messen, ob ein Modell gebrochene RTL-Verhaltensmutationen nach einer Spezifikation beheben kann. Zu diesem Zweck konstruieren und hash-binden wir RTLRepairDataset, 5,784 (gebrochen, festgelegte) Trainingsparen; RTLRepairBench, 459 Halt-out-Fälle mit 374 benchaktischen und 85 Verhaltensmutationen; und eine Bewertungsanlage, die Simulation und formale Äquivalenz unterstützt. Wir verwenden dann diese Infrastruktur, um zwei Messverwirrungen zu identifizieren. Erstens geben Simulation und formale Aggregation entgegengesetzte Anzeichen für den offensichtlichen Effekt der Bereitstellung einer Spezifikation in einer ausgewerteten Kohorte; semet-aware rescoring Attribute fast alle der Simulation

Machine translation (Meta M2M100); the English original follows.

Abstract

RTL repair benchmarks should measure whether a model can fix broken RTL given a specification. To this end, we construct and hash-bind RTLRepairDataset, 5,784 (broken, fixed) training pairs; RTLRepairBench, 459 held-out cases with 374 syntactic and 85 behavioral mutations; and an evaluation harness supporting simulation and formal equivalence. We then use this infrastructure to identify two measurement confounds. First, simulation and formal scoring give opposite signs for the apparent effect of providing a specification in one evaluated cohort; reset-aware rescoring attributes almost all of the simulation-formal disagreement to reset and first-cycle comparison semantics. Second, on 274 mined model failures, the specification-only minus specification-conditioned recovery point estimate ranges from -8.5 to +18.3 percentage points across six models. Thus, a conventional repair score need not isolate whether the model used the faulty RTL. We translate these findings into evaluation controls: report initialization, reset, first-cycle, and unknown-value semantics; disclose oracle coverage and undecided cases; and include a specification-only baseline. Together, the resources and audit provide both a benchmark for behavioral repair and a protocol for diagnosing what contributes to its measured score. We release the benchmark, the training set, construction code, sanitized aggregate evidence, and reproduction materials at https://github.com/Evaaaz/RTLRepairBench.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Benchmark (surveying), Reset (finance), Oracle, Construct (python library), Measure (data warehouse)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange