[Submitted on 31 Jan 2026 (v1), last revised 22 Jul 2026 (this version, v5)]

View PDF HTML (experimental)

Abstract:Zero-knowledge circuits enable privacy-preserving and scalable systems but are difficult to implement correctly due to the tight coupling between witness computation and circuit constraints. We present zkCraft, a practical framework that combines deterministic, R1CS-aware localization with proof-bearing search to detect semantic inconsistencies. zkCraft encodes candidate constraint edits into a single Row-Vortex polynomial and replaces repeated solver queries with a Violation IOP that certifies the existence of edits together with a succinct proof. Deterministic LLM-driven mutation templates bias exploration toward edge cases while preserving auditable algebraic verification. Evaluation on real Circom code shows that proof-bearing localization detects diverse under- and over-constrained faults with low false positives and reduces costly solver interaction. Our approach bridges formal verification and automated debugging, offering a scalable path for robust ZK circuit development.

Submission history

From: Rong Fu [view email]
[v1] Sat, 31 Jan 2026 11:31:00 UTC (18,093 KB)
[v2] Sat, 14 Feb 2026 03:06:53 UTC (18,092 KB)
[v3] Tue, 3 Mar 2026 03:16:43 UTC (18,093 KB)
[v4] Wed, 22 Apr 2026 08:06:41 UTC (2,272 KB)
[v5] Wed, 22 Jul 2026 02:26:21 UTC (2,272 KB)