Log In Sign Up

Toward Neural-Network-Guided Program Synthesis and Verification

by   Naoki Kobayashi, et al.

We propose a novel framework of program and invariant synthesis called neural network-guided synthesis. We first show that, by suitably designing and training neural networks, we can extract logical formulas over integers from the weights and biases of the trained neural networks. Based on the idea, we have implemented a tool to synthesize formulas from positive/negative examples and implication constraints, and obtained promising experimental results. We also discuss two applications of our synthesis method. One is the use of our tool for qualifier discovery in the framework of ICE-learning-based CHC solving, which can in turn be applied to program verification and inductive invariant synthesis. Another application is to a new program development framework called oracle-based programming, which is a neural-network-guided variation of Solar-Lezama's program synthesis by sketching.


page 11

page 23

page 24

page 25

page 26

page 27


Synthesis in Uclid5

We describe an integration of program synthesis into Uclid5, a formal mo...

Relational Program Synthesis

This paper proposes relational program synthesis, a new problem that con...

Data-driven Numerical Invariant Synthesis with Automatic Generation of Attributes

We propose a data-driven algorithm for numerical invariant synthesis and...

An Inductive Synthesis Framework for Verifiable Reinforcement Learning

Despite the tremendous advances that have been made in the last decade o...

Validity-Guided Synthesis of Reactive Systems from Assume-Guarantee Contracts

Automated synthesis of reactive systems from spe- cifications has been a...

UCLID5: Multi-Modal Formal Modeling, Verification, and Synthesis

UCLID5 is a tool for the multi-modal formal modeling, verification, and ...

Invariant Synthesis for Incomplete Verification Engines

We propose a framework for synthesizing inductive invariants for incompl...

Code Repositories