9 citations · 22 across the 9 of their papers we have counts for
10 papers
Bogus Bugs, Duplicates, and Revealing Comments: Data Quality Issues in NPR
Julian Aron Prenner, Romain Robbes
The performance of a machine learning system is not only determined by the model but also, to a substantial degree, by the data it is trained on. With the increasing use of machine…
Simple Fault Localization using Execution Traces
Julian Aron Prenner, Romain Robbes
Traditional spectrum-based fault localization (SBFL) exploits differences in a program's coverage spectrum when run on passing and failing test cases. However, such runs can provid…
ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions
Julian Aron Prenner, Romain Robbes
Modern Large Language Models (LLMs) have shown astounding capabilities of code understanding and synthesis. In order to assess such capabilities, several benchmarks have been devis…
Extracting Fix Ingredients using Language Models
Julian Aron Prenner, Romain Robbes
Deep learning and language models are increasingly dominating automated program repair research. While previous generate-and-validate approaches were able to find and use fix ingre…
Out of Context: How important is Local Context in Neural Program Repair?
Julian Aron Prenner, Romain Robbes
Deep learning source code models have been applied very successfully to the problem of automated program repair. One of the standing issues is the small input window of current mod…
RunBugRun -- An Executable Dataset for Automated Program Repair
Julian Aron Prenner, Romain Robbes
Recently, we can notice a transition to data-driven techniques in Automated Program Repair (APR), in particular towards deep neural networks. This entails training on hundreds of t…
Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation
Anjan Karmakar, Julian Aron Prenner, Marco D'Ambros +1
The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hid…
Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs
Julian Aron Prenner, Romain Robbes
OpenAI's Codex, a GPT-3 like model trained on a large code corpus, has made headlines in and outside of academia. Given a short user-provided description, it is capable of synthesi…
Making the most of small Software Engineering datasets with modern machine learning
Julian Aron Prenner, Romain Robbes
This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due t…
Mining Software Repositories with a Collaborative Heuristic Repository
Hlib Babii, Julian Aron Prenner, Laurin Stricker +3
Many software engineering studies or tasks rely on categorizing software engineering artifacts. In practice, this is done either by defining simple but often imprecise heuristics,…