AI Paper Atlas

Research map / Large language models / Agents, code and math

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code

Lingfei Zeng, Fengdi Che, Xuhan Huang, Fei Ye, Xu Xu, Binhang Yuan, Jie Fu

ICLR 2026 · Large language models › Agents, code and math · approach: Code generation benchmarks · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Dafny-verifier equivalence score instead of NL-based Clover check on DafnySynthesisevaluation metric · DafnySynthesisvalidation: 10% -> 10% plus 9 more flaggedImproved
evaluate on TagComp instead of CloverBenchclaude-4-sonnet · end-to-end verifiable code gen pass@4success rate: 75.81% -> 0Hurt
supply two examples in specification-generation prompt (ablation)Claude-4-sonnet spec generation · LeetCode autoformalizationsyntax error rateImproved
use multi-stage code generation with a lighter polishing modelDafny code generation · LeetCodeverifiable rateImproved
use RL-trained baseline for spec generationSFT model · validation setequivalence scoreNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy