The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches
收藏相关数据集
Data: HasBugs - Handpicked Haskell Bugs
# HasBugs - Haskell Bugs for you and me We try to provide a fresh dataset in the fashion of [Defects4J](https://github.com/rjust/defects4j) to evaluate tasks such as fault localization, program rep
NIAID Data Ecosystem110
Anonymized data for paper "Automatic Bug Fixing in the Era of Large Language Models: Interactive Simulation of Programmer Behavior" submitted to ICSE 2024
The project includes the BFP benchmark used in the submitted ICSE 2024 paper titled "Automatic Bug Fixing in the Era of Large Language Models: Interactive Simulation of Programmer Behavior"
Zenodo2023-08-01 更新30
PyHealer: Agentic Self-Repair for Python Program Execution
PyHealer is an LLM-backed, agentic execution error repair pipeline for Python projects. It automatically analyzes execution failures, infers dependencies and Python versions, builds isolated Docker en
Zenodo2026-06-07 更新20
CodeMind Dataset
Large Language Models (LLMs) have been widely used to automate programming tasks. Their capabilities have been evaluated by assessing the quality of generated code through tests or proofs. T
IEEE50
On Learning Meaningful Code Changes via Neural Machine Translation
Paper: On Learning Meaningful Code Changes via Neural Machine Translation Authors: Michele Tufano, Jevgenija Pantiuchina, Cody Watson, Gabriele Bavota, and Denys Poshyvanyk ICSE 2019 - 41st ACM/IEEE I
Zenodo2022-12-26 更新30
