Papers with Code 아카이브

Program Repair

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 6
평가표: 4
보존된 평가 기록: 8

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/michiyasunaga/DrRepair

공식 코드

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

https://github.com/michiyasunaga/bifi

공식 코드

Break-It-Fix-It: Unsupervised Learning for Program Repair

https://github.com/nnrepair/nnrepair

공식 코드

NNrepair: Constraint-based Repair of Neural Network Classifiers

https://github.com/ntunlp/xCodeEval

공식 코드

xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval

https://github.com/nus-apr/auto-code-rover

공식 코드

AutoCodeRover: Autonomous Program Improvement

https://github.com/pmorvalho/c-pack-ipas

공식 코드

C-Pack of IPAs: A C90 Program Benchmark of Introductory Programming Assignments

https://github.com/pmorvalho/cfaults

공식 코드

CFaults: Model-Based Diagnosis for Fault Localization in C Programs with Multiple Test Cases

https://github.com/pmorvalho/ecai23-gnns-for-mapping-variables-between-programs

공식 코드

Graph Neural Networks For Mapping Variables Between Programs -- Extended Version

https://github.com/pmorvalho/invaastcluster

공식 코드

InvAASTCluster: On Applying Invariant-Based Program Clustering to Introductory Programming Assignments

https://github.com/seed-vt/tracefl

공식 코드

TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance

https://github.com/serjtroshin/probings4code

공식 코드

Probing Pretrained Models of Source Code

https://github.com/shaido987/alarm-rca

공식 코드

An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks

https://github.com/sola-st/RepairAgent

공식 코드

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair

https://github.com/soroushhashemifar/np-sbfl

공식 코드

Path Analysis for Effective Fault Localization in Deep Neural Networks

https://github.com/sparkssss/aequevox

공식 코드

AequeVox: Automated Fairness Testing of Speech Recognition Systems

https://github.com/squareslab/llmao

공식 코드

Large Language Models for Test-Free Fault Localization

https://github.com/stg-tud/code-llm-critical-evaluation

공식 코드

A Critical Study of What Code-LLMs (Do Not) Learn

https://github.com/thanhlecongg/Invalidator

공식 코드

Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning

https://github.com/thanhlecongg/naturaltransformationforbenchmarkingnpr

공식 코드

Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing

https://github.com/theyoucheng/deepcover

공식 코드

Explaining Image Classifiers using Statistical Fault Localization

https://github.com/tntwow/repair

공식 코드

RePair: Automated Program Repair with Process-based Feedback

https://github.com/tomsawyerhu/gpt-o1-on-quixbugs

공식 코드

Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs

https://github.com/trust4ai/astral

공식 코드

o3-mini vs DeepSeek-R1: Which One is Safer?

https://github.com/uh-serg/ci-memorization

공식 코드

Memorization and Generalization in Neural Code Intelligence Models

https://github.com/warisgill/tracefl

공식 코드

TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance

https://github.com/wasiahmad/PLBART

공식 코드

Unified Pre-training for Program Understanding and Generation

https://github.com/xyzboom/devlore

공식 코드

Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repair

https://github.com/yingweima2022/swe-reasoner

공식 코드

Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute

https://github.com/you68681/lpw

공식 코드

Planning-Driven Programming: A Large Language Model Programming Workflow

https://github.com/zhenlongDai/AdaPatcher

공식 코드

Less is More: Adaptive Program Repair with Bug Localization and Preference Learning

https://github.com/zhonghaojiang/cosil

공식 코드

CoSIL: Software Issue Localization via LLM-Driven Code Repository Graph Searching

https://worksheets.codalab.org/worksheets/0x01838644724a433c932bef4cb5c42fbd

공식 코드

Graph-based, Self-Supervised Program Repair from Diagnostic Feedback

https://zenodo.org/record/10500594

공식 코드

A Novel Approach for Automatic Program Repair using Round-Trip Translation with Large Language Models

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.