Project Proposal: Learning Variable Mappings to Repair Programs
In this talk I propose to learn how to map the set of variables between different small imperative programs based on both programs' abstract syntax trees (ASTs) using graph neural …
Anonymized Abstract Syntax Trees and Invariant-Based Program Clustering
In this talk I propose a novel approach for program clustering that uses dynamically generated program invariants to cluster semantically equivalent programming assignments.
SQUARES: A SQL Synthesizer Using Query Reverse Engineering
In this talk I present SQUARES, an open-source tool that generates SQL and R queries from specifications. The specifications are expressed with input-output tables and some …
Encodings for Enumeration-Based Program Synthesis
In this talk I will present a new compact line-based encoding is proposed that allows a faster enumeration of the program space.