Search Results for author:
Found 6 papers, 1 papers with code
Cobblestone: Iterative Automation for Formal Verification
We introduce Cobblestone, a new proof-synthesis approach that improves on the state of the art by taking advantage of partial progress in proof synthesis attempts.
QEDCartographer: Automating Formal Verification Using Reward-Free Reinforcement Learning
To address this problem, we create QEDCartographer, an automated proof-synthesis tool that combines supervised and reinforcement learning to more effectively explore the proof space.
Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion
The framework includes a representation that captures the general \textit{syntax} of structural recursion, coupled with two different frameworks for understanding their \textit{semantics} -- one that is more natural from a programming languages perspective and one that helps bridge that perspective with a mechanistic understanding of the underlying transformer architecture.
Can Transformers Learn to Solve Problems Recursively?
Neural networks have in recent years shown promise for helping software engineers write programs and even formally verify them.
Baldur: Whole-Proof Generation and Repair with Large Language Models
Recent work has developed methods to automate formal verification using proof assistants, such as Coq and Isabelle/HOL, e. g., by training a model to predict one proof step at a time, and using that model to search through the space of possible proofs.
Proof Repair across Type Equivalences
We describe a new approach to automatically repairing broken proofs in the Coq proof assistant in response to changes in types.
Programming Languages
