Program Repair
23 papers with code • 3 benchmarks • 6 datasets
Benchmarks
These leaderboards are used to track progress in Program Repair
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
DeepFix
TFix's Code Patches Data
Subtasks
Most implemented papers
Neural Program Repair by Jointly Learning to Localize and Repair
mdrafiqulrabin/SIVAND
•
We show that it is beneficial to train a model that jointly and directly localizes and repairs variable-misuse bugs.
Learning and Evaluating Contextual Embedding of Source Code
google-research/google-research
•
We fine-tune CuBERT on our benchmark tasks, and compare the resulting models to different variants of Word2Vec token embeddings, BiLSTM and Transformer models, as well as published state-of-the-art models, showing that CuBERT outperforms them all, even with shorter training, and with fewer labeled examples.
Graph-based, Self-Supervised Program Repair from Diagnostic Feedback
michiyasunaga/DrRepair
•
•
ICML 2020
Second, we present a self-supervised learning paradigm for program repair that leverages unlabeled programs available online to create a large amount of extra program repair examples, which we use to pre-train our models.
C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments
Due to the vast number of students enrolled in Massive Open Online Courses (MOOCs), there has been an increasing number of automated program repair techniques focused on introductory programming assignments (IPAs).
DeepFix: Fixing Common C Language Errors by Deep Learning
iiscseal/deepfix
•
The problem of automatically fixing programming errors is a very active research topic in software engineering.
Dynamic Neural Program Embedding for Program Repair
keowang/dynamic-program-embedding
•
Evaluation results show that our new semantic program embedding significantly outperforms the syntactic program embeddings based on token sequences and abstract syntax trees.
Deep Reinforcement Learning for Programming Language Correction
terne/dtuproject
•
•
Novice programmers often struggle with the formal syntax of programming languages.
SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair
This paper presents a novel end-to-end approach to program repair based on sequence-to-sequence learning.
Human-In-The-Loop Automatic Program Repair
Our key challenge is to maximize the oracle's accuracy in predicting which tests are bug-exposing given a small budget of queries.
Arachne: Search Based Repair of Deep Neural Networks
coinse/arachne
•
•
The rapid and widespread adoption of Deep Neural Networks (DNNs) has called for ways to test their behaviour, and many testing approaches have successfully revealed misbehaviour of DNNs.
