2026-03-09
Jose Garcia-Alonso, Majid Haghparast, Tommi Mikkonen, Juan Manuel Murillo Rodríguez, Vlad Stirbu
Quantum software engineering has gained a lot of attention recently. Multiple traditional software engineering events have introduced a quantum software track, or a co-located quantum related workshop or other side event, indicating that quantum software is becoming a popular research topic, with more and more software engineering researchers contributing to its evolution. In this paper, we address software engineering research that aims at solving problems that emerge when quantum programs are used on industry domains. The paper is based on the keynote at the IEEE Symposium on Quantum Software: Quantum Software Engineering 2025, which took place in Helsinki, Finland, Summer of 2025. In particular, we address the state of research in quantum software engineering, its novel aspects as well as its connections to other branches of software engineering. Furthermore, in the light of this research, we also assess the maturity of quantum software engineering in the light of industry expectations.
2026-03-09
Zhao Na, Mao Yanying
Web service traffic forecasting is vital for dynamic resource scaling, load balancing, and anomaly detection, but remains challenging due to frequent large-scale fluctuations caused by heterogeneous user behaviors. Traditional time-series models and recent deep neural networks have made progress by capturing temporal patterns, yet they largely overlook latent causal relationships between services that can significantly influence traffic dynamics. In this paper, we propose a novel causal cross-embedded spatio-temporal LSTM (CEST-LSTM) architecture that integrates spatio-temporal modelling with a causal inference mechanism to improve web traffic prediction. The model consists of a spatio-temporal LSTM branch for capturing temporal dependencies across services and a causal branch that leverages convergent cross mapping-based cross-embedding to uncover and incorporate latent inter-service causal influences. A cross-embedding fusion mechanism seamlessly combines these causal features with spatio-temporal representations. On real-world datasets (e.g., Microsoft Azure and Alibaba Cloud), CEST-LSTM achieves a variance-explained prediction accuracy of approximately 93%, surpassing state-of-the-art baselines such as temporal graph convolutional networks (T-GCN) and spatio-temporal attention GCNs (STA-GCN). Comparative experiments and ablation studies confirm that the causal branch consistently improves forecasting accuracy – for example, removing the causal module reduces accuracy by several percentage points. These results demonstrate that integrating latent causal relationship modelling into spatio-temporal neural networks yields substantial improvements in web traffic prediction, offering a promising direction for robust and interpretable forecasting in complex web systems.