Abstract
Text readability is vital for effective communication and learning, especially for those with lower information literacy. This research aims to assess Llama 3's ability to grade readability and compare its alignment with established metrics. For that purpose, we create a new dataset of article lead sections from English and Simple English Wikipedia, covering nine categories. The model is prompted to rate the readability of the texts on a grade-level scale, and an in-depth analysis of the results is conducted. While Llama 3 correlates strongly with most metrics, it may underestimate text grade levels.

Abstract
Handheld controllers are standard in immersive virtual reality (iVR), but the rise of natural hand-based interactions exposes the limitations of hand gestures, especially for point-and-click tasks with graphical user interfaces (GUI). This shows the need to explore alternative hands-free selection methods. Unlike most studies focusing on the selection task itself, this work evaluates the impact of such methods on multiple dimensions when selections occur alongside another primary task. The tested methods were: head gaze + dwell, leaning, and voice; eye gaze + dwell, leaning, blinking, and voice; and voice-only. Controllers served as the baseline. Methods were further analyzed by pointing and confirming mechanisms. Four dimensions were analyzed: (1) iVR experience, (2) user satisfaction, (3) usability, and (4) efficiency and effectiveness. With 72 participants, results show hands-free methods provide comparable experiences to controllers, suggesting selection methods have a lower impact on the user experience when users focus on a primary task.

Abstract
We present Keigo, a concurrency-and workload-aware storage middleware that enhances the performance of log-structured merge key-value stores (LSM KVS) when they are deployed on a hierarchy of storage devices. The key observation behind Keigo is that there is no one-size-fits-all placement of data across the storage hierarchy that optimizes for all workloads. Hence, to leverage the benefits of combining different storage devices, Keigo places files across different devices based on their parallelism, I/O bandwidth, and capacity. We introduce three techniques-concurrency-aware data placement, persistent read-only caching, and context-based I/O differentiation. Keigo is portable across different LSMs, is adaptable to dynamic workloads, and does not require extensive profiling. Our system enables established production KVS such as RocksDB, LevelDB, and Speedb to benefit from heterogeneous storage setups. We evaluate Keigo using synthetic and realistic workloads, showing that it improves the throughput of production-grade LSMs up to 4x for write-and 18x for read-heavy workloads when compared to general-purpose storage systems and specialized LSM KVS.

Abstract
Artificial Intelligence (AI), in particular Generative Artificial Intelligence (GenAI), is a quickly developing field capable of revolutionizing educational digital escape rooms. Traditionally reliant on static content, these immersive environments have faced limitations in adaptability, replayability, and personalization. However, recent advancements in AI and GenAI enable dynamic puzzle generation, adaptive storytelling, and AI-driven non-player characters (NPCs) with agentic AI, allowing for highly responsive and personalized experiences. This paper reviews the state-of-the-art in integrating AI (with the focus on GenAI) into educational digital escape rooms, integrating interdisciplinary insights from cognitive science, game design, and machine learning, and showing how AI can improve engagement, scalability, and content diversity, but also indicates challenges related to ethical AI use, bias in algorithmic decision-making, and the need for robust evaluation frameworks to assess player satisfaction and learning outcomes. © 2025 Elsevier B.V., All rights reserved.

Abstract
SPHINCS+ is a post-quantum signature scheme that, at the time of writing, is being standardized as SLH-DSA. It is the most conservative option for post-quantum signatures, but the original tight proofs of security were flawed- as reported by Kudinov, Kiktenko and Fedorov in 2020. In this work, we formally prove a tight security bound for SPHINCS+ using the EasyCrypt proof assistant, establishing greater confidence in the general security of the scheme and that of the parameter sets considered for standardization. To this end, we reconstruct the tight security proof presented by Hulsing and Kudinov (in 2022) in a modular way. A small but important part of this effort involves a complex argument relating four different games at once, of a form not yet formalized in EasyCrypt (to the best of our knowledge). We describe our approach to overcoming this major challenge, and develop a general formal verification technique aimed at this type of reasoning. Enhancing the set of reusable EasyCrypt artifacts previously produced in the formal verification of stateful hash-based cryptographic constructions, we (1) improve and extend the existing libraries for hash functions and (2) develop new libraries for fundamental concepts related to hash-based cryptographic constructions, including Merkle trees. These enhancements, along with the formal verification technique we develop, further ease future formal verification endeavors in EasyCrypt, especially those concerning hash-based cryptographic constructions.

Abstract
Objectives: The shape is commonly used to describe the objects. State-of-the-art algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from the growing popularity of ShapeNet (51,300 models) and Princeton ModelNet (127,915 models). However, a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D models of surgical instruments is missing. Methods: We present MedShapeNet to translate data-driven vision algorithms to medical applications and to adapt state-of-the-art vision algorithms to medical problems. As a unique feature, we directly model the majority of shapes on the imaging data of real patients. We present use cases in classifying brain tumors, skull reconstructions, multi-class anatomy completion, education, and 3D printing. Results: By now, MedShapeNet includes 23 datasets with more than 100,000 shapes that are paired with annotations (ground truth). Our data is freely accessible via a web interface and a Python application programming interface and can be used for discriminative, reconstructive, and variational benchmarks as well as various applications in virtual, augmented, or mixed reality, and 3D printing. Conclusions: MedShapeNet contains medical shapes from anatomy and surgical instruments and will continue to collect data for benchmarks and applications. The project page is: https://medshapenet.ikim.nrw/.