Papers with Code · CC BY-SA 4.0

Program Repair

Program Synthesis › Program Repair 8 평가 기록 4 datasets

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

논문

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

2106.06600 2021-06-11 이 페이지의 평가 3건

Accuracy (%): 90.5

Deep Reinforcement Learning for Programming Language Correction

1801.10467 2018-01-31 이 페이지의 평가 1건

Average Success Rate: 26.6

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

2410.01215 2024-10-02 이 페이지의 평가 1건

Pass@1: 97.6

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

2005.10636 2020-05-20 이 페이지의 평가 1건

Average Success Rate: 68.2

SampleFix: Learning to Generate Functionally Diverse Fixes

1906.10502 2019-06-24 이 페이지의 평가 1건

Average Success Rate: 45.3

TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer

2021-07-18 이 페이지의 평가 1건

Exact Match: 49,3Error Removal: 67,8