Reproduce “Pneuma: A Large-Scale Real-World Time Series Benchmark for Commercial Aircraft Predictive Maintenance” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiafeng Lin, Yutian Zhang, Huan Zhang, Yuxuan Wang, Jinyan Feng, Yuhui Liu, Zhongyi Pei, Jianmin Wang
Pneuma provides a public benchmark for bleed-air fault detection in mainline aircraft, linking Quick Access Recorder telemetry with airline maintenance records across four aircraft types and nine fault subsets. It defines forecasting, classification, and anomaly-detection tasks. The best supervised classifier scores 60.22, while the best normal-only anomaly detector scores 23.11, using mean Precision@R10 across subsets; these are benchmark results, not deployment evidence.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.