NeuroFlake integrates discriminative token mining into LLMs to classify flaky tests, raising F1-score to 69.34% on FlakeBench while showing greater robustness to semantic-preserving perturbations than prior methods.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
UltraInstinctVR automates VR system test generation from scenario models and detects more unique failures than prior automated tools across 10 open-source VR applications.
ACT is a proposed framework for automated continuous testing of open-source CPS software using robotic platforms and GitHub integration, demonstrated via a case study on an educational robot.
citing papers explorer
-
NeuroFlake: A Neuro-Symbolic LLM Framework for Flaky Test Classification
NeuroFlake integrates discriminative token mining into LLMs to classify flaky tests, raising F1-score to 69.34% on FlakeBench while showing greater robustness to semantic-preserving perturbations than prior methods.
-
System Test Generation for Virtual Reality Applications using Scenario Models
UltraInstinctVR automates VR system test generation from scenario models and detects more unique failures than prior automated tools across 10 open-source VR applications.
-
ACT: Automated CPS Testing for Open-Source Robotic Platforms
ACT is a proposed framework for automated continuous testing of open-source CPS software using robotic platforms and GitHub integration, demonstrated via a case study on an educational robot.