Neuro-Symbolic Program Corrector for Introductory Programming Assignments

By Sahil Bhatia, Pushmeet Kohli, Rishabh Singh. 2018

96 citations recorded by the source corpus.

Subfields: Information Systems, Software, LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Software

In LLM Agents & Tool Use

Citations in the corpus

SPoC: Search-based Pseudocode to Code (2019, background): “Other work identiﬁes error locations by interpreting compiler error messages [13, 5].”
Neural Program Repair by Jointly Learning to Localize and Repair (2019, methodology): “SynFix uses a Python compiler to identify error locations and then performs a constraint-based search to compute repairs.”
TBar: revisiting template-based automated program repair (2019, methodology): “Other APR pipelines focus on specific search methods for donor code or patch synthesizing strategies, to address the search space problem, such as contract-based [10, 66], symbolic execution based [53], learning based [7, 16, 44, 59, 64, 70], and donor code searching [21, 51] APR tools.”
MISIM: An End-to-End Neural Code Similarity System (2020, background): “Accurate code similarity systems may assist in many programming tasks, such as code recommendation systems to improve programming development productivity, to automated bug detection and mitigation systems to improve programmer debugging productivity [2, 6, 8, 11, 14, 29, 34].”
Teaching Temporal Logics to Neural Networks (2020, background): “Other works focused on recurrent neural networks or graph neural networks for code analysis, e.g. [30,14,5,48,1].”
Neural Attribution for Semantic Bug-Localization in Student Programs (2019, background): “Several recent works proposed deep learning based techniques for automated syntactic error repair in student programs [11, 6, 3, 13].”