The recent publications in the field highlight a significant shift towards enhancing the accuracy and efficiency of causal discovery and influence maximization techniques, alongside innovative approaches to authorship disambiguation and sampling methods. A notable trend is the development of hybrid and reinforcement learning-based methods that aim to overcome the limitations of traditional approaches by integrating multiple strategies for improved robustness and scalability. Additionally, there's a growing emphasis on addressing real-world complexities such as dependent data structures and dynamic network behaviors, which are crucial for accurate causal inference and effective influence spread in temporal networks. The field is also witnessing advancements in quantifying the impact of retracted research and in developing scalable frameworks for multiplex influence maximization, indicating a broader interest in understanding and mitigating the spread of misinformation and harm in academic and social networks.nn### Noteworthy Papersn- Evaluating authorship disambiguation quality through anomaly analysis on researchers' career transition: Introduces a novel framework for assessing authorship disambiguation quality, revealing significant gender disparities in disambiguation accuracy.n- DIPS: Optimal Dynamic Index for Poisson $pi$ps Sampling: Presents a dynamic index for Poisson $pi$ps sampling, achieving optimal query and update times, significantly advancing data sampling efficiency.n- Hybrid Local Causal Discovery: Proposes HLCD, a hybrid algorithm that outperforms existing methods in local causal discovery by combining constraint-based and score-based approaches.n- Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization: Enhances causal discovery through a novel RL method and a refined graph attention encoder, improving optimization robustness and efficiency.n- Causal Discovery on Dependent Binary Data: Develops a decorrelation-based approach for causal graph learning on dependent binary data, improving accuracy in structure learning.n- Treatment Effect Estimation for Graph-Structured Targets: Introduces GraphTEE, a framework for estimating treatment effects on graph-structured targets, effectively mitigating observational bias.n- Influence Maximization in Temporal Networks with Persistent and Reactive Behaviors: Proposes cpSI-R, a model that captures active-inactive transitions in temporal networks, enhancing influence maximization strategies.n- Quantifying the Dynamics of Harm Caused by Retracted Research: Offers a citation-based framework to quantify the harm of retracted papers, shedding light on the mechanisms of harm propagation.n- Controlled Causal Hallucinations Can Estimate Phantom Nodes in Multiexpert Mixtures of Fuzzy Cognitive Maps: Presents a method for estimating phantom nodes in large-scale causal models, advancing the approximation of dynamical systems.n- REM: A Scalable Reinforced Multi-Expert Framework for Multiplex Influence Maximization: Introduces REM, a framework that surpasses state-of-the-art methods in influence spread, scalability, and inference time for multiplex networks.