166 citations · 587 across the 57 of their papers we have counts for
63 papers
An AI Approach to Verified Production Cryptographic Libraries
Chuyue Sun, Su Fong, Zhiyi Kuang +5
Cryptographic code is critical infrastructure that must be correct, yet formally verifying production libraries remains difficult. Existing language-model proof systems solve isola…
Viverra: Text-to-Code with Guarantees
Haoze Wu, Rocky Klopfenstein, Keith Farkas +1
A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its correctness, the generated code…
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
Ido Pinto, Yizhak Yisrael Elboher, Haoze Wu +2
The synthesis of inductive loop invariants remains a critical bottleneck in automated program verification. While Large Language Models (LLMs) show promise in mitigating this issue…
SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints
Andrew Tremante, Yang He, Rocky Klopfenstein +3
We present SpotIt+, an open-source tool for evaluating Text-to-SQL systems via bounded equivalence verification. Given a generated SQL query and the ground truth, SpotIt+ actively…
SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification
Rocky Klopfenstein, Yang He, Andrew Tremante +3
Community-driven Text-to-SQL evaluation platforms play a pivotal role in tracking the state of the art of Text-to-SQL performance. The reliability of the evaluation process is crit…
Cubing for Tuning
Haoze Wu, Clark Barrett, Nina Narodytska
We are exploring the problem of building an automated reasoning procedure that adaptively tunes the high-level solving strategy for a given problem. There are two main distinctive…