SOTAVerified

Program Repair

Task of teaching ML models to modify an existing program to fix a bug in a given code.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–132 of 132 papers

TitleStatusHype
AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations—0
Neural Program Repair: Systems, Challenges and Solutions—0
Enabling Automatic Repair of Source Code Vulnerabilities Using Data-Driven Methods—0
MultiFix: Learning to Repair Multiple Errors by Optimal Alignment Learning—0
GRAPHIX: A Pre-trained Graph Edit Model for Automated Program Repair—0
Mapping the Structure and Evolution of Software Testing Research Over the Past Three Decades—0
Grammar-Based Patches Generation for Automated Program Repair—0
Tea: Program Repair Using Neural Network Based on Program Information Attention Matrix—0
Assessing the Effectiveness of Syntactic Structure to Learn Code Edit RepresentationsCode0
DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons—0
Program Repair with Repeated Learning—0
Generating Bug-Fixes Using Pretrained Transformers—0
Exploring Plausible Patches Using Source Code Embeddings in JavaScriptCode0
Fairness-guided SMT-based Rectification of Decision Trees and Random Forests—0
Obstacles in Fully Automatic Program Repair: A survey—0
Learning to Execute Programs with Instruction Pointer Attention Graph Neural NetworksCode0
Patching as Translation: the Data and the MetaphorCode0
Robot Action Selection Learning via Layered Dimension Informed Program SynthesisCode0
SCELMo: Source Code Embeddings from Language Models—0
Arachne: Search Based Repair of Deep Neural NetworksCode0
Learning and Evaluating Contextual Embedding of Source CodeCode0
Human-In-The-Loop Automatic Program RepairCode0
Learning to Fix Build Errors with Graph2Diff Neural Networks—0
SampleFix: Learning to Generate Functionally Diverse Fixes—0
ENCORE: Ensemble Learning using Convolution Neural Machine Translation for Automatic Program Repair—0
SequenceR: Sequence-to-Sequence Learning for End-to-End Program RepairCode0
Towards Mixed Optimization for Reinforcement Learning with Program Synthesis—0
Deep Reinforcement Learning for Programming Language CorrectionCode0
Dynamic Neural Program Embeddings for Program Repair—0
Dynamic Neural Program Embedding for Program RepairCode0
SmartPaste: Learning to Adapt Source Code—0
DeepFix: Fixing Common C Language Errors by Deep LearningCode0
Show:102550
← PrevPage 3 of 3Next →
All datasetsDeepFixGitHub-PythonHumanEvalPackTFix's Code Patches Data

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DrRepair + BIFIAverage Success Rate71.7—Unverified
2DrRepairAverage Success Rate68.2—Unverified
3SampleFixAverage Success Rate45.3—Unverified
4RLAssistAverage Success Rate26.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Transformer + BIFIAccuracy (%)90.5—Unverified
2TransformerAccuracy (%)62—Unverified
#ModelMetricClaimedVerifiedStatus
1MGDebugger (DeepSeek-Coder-V2-Lite)Pass@197.6—Unverified
#ModelMetricClaimedVerifiedStatus
1TFixError Removal678—Unverified