arXiv subjects

Stefan Wagner

Publications and source records attributed to Stefan Wagner.

At least 19 recordsLinked to original sources

arXiv2026

Apple Vision Pro: The good, the bad, the ugly

Apple Vision Pro (AVP), the headset Apple introduced as its first ``spatial computer,'' built by a single, vertically integrated vendor, entered the market in February 2024 and has since accumulated a fast-growing body of primary research spanning surgery, education, accessibility, design, and human-computer interaction. In this paper, we adopt the tripartite structure of Leone's 1966 film to organize a systematic review of this literature: we cataloged the validated, working applications of AVP (the good), the persistent technical and ergonomic limitations of a still-early-generation headset (the bad), and the ethical concerns and structural harms that follow from deliberate design, marketing, and deployment choices (the ugly). The review is built from a Scopus export of 218 records mentioning AVP, which we narrowed to 104 papers (2024--2026) with a primary focus on AVP, using explicit inclusion/exclusion criteria that we report in full, alongside a PRISMA-informed flow diagram of the screening process. We find the corpus heavily skewed toward validating benefits (medicine and surgery, education, and software tooling account for over half of the included papers) and comparatively thin on documented risks or misuse, a pattern we treat as a finding in its own right rather than a limitation to be explained away. We further show that several recurring issues, namely price, simulated social presence, and the gaze-tracking privacy architecture, resist a clean separation into ``bad'' or ``ugly'' using the published evidence alone, since both readings remain compatible with the same data. We close by identifying where the evidence base most needs to grow: independent risk and ethics research, bystander- and equity-focused study designs, and disclosure that would let researchers distinguish an engineering backlog from a structural choice.

cs.HC↗

arXiv2026

Noncommutative principal bundles and central extensions

Motivated by the classical theory of spin structures, we develop a theory for lifting free C$^*$-dynamical systems, a.k.a. noncommutative principal bundles, along central extensions. This theory extends the bundle-theoretic notion of spin structures and yields a complete existence and classification result for such lifts. Using factor system techniques and Picard formalism, our approach introduces new invariants and obstruction classes, thereby unifying geometric, cohomological, and operator-algebraic perspectives. A range of examples demonstrates the scope of the theory.

math.OA↗

arXiv2026

Reduction of structure groups for noncommutative principal bundles

Let $G$ be a compact group and let $H \subseteq G$ be a closed subgroup. We study reduction of the structure group for noncommutative principal bundles, modelled by free C${}^*$-dynamical systems in the sense of Ellwood. We first describe how induction from $H$ to $G$ behaves on associated correspondences and their tensor structure. Using reconstruction, this leads to a Tannakian characterization of reduction of the structure group in terms of the associated tensor functor. For normal subgroups, we characterize reduction in terms of central equivariant homomorphisms and derive module- and $K$-theoretic obstructions. We conclude with a noncommutative $O(n)$-example which admits no reduction to $SO(n)$.

math.OA↗

arXiv2026

Spectral geometry of saturated Fell bundles

Let $\mathcal B=(B_g)_{g\in G}$ be a saturated Fell bundle over a countable discrete group, equipped with a spectral triple. We give explicit sufficient conditions for lifting this triple to the reduced cross-sectional C\Star-algebra $C_r^*(\mathcal B)$. Using finite projective realizations of the homogeneous Morita equivalence $B_e$-bimodules, we transport the base Dirac operator to the individual fibres and assemble the resulting operators into a fibrewise Dirac operator. We introduce a spectral-regularity condition ensuring bounded commutators and give a sufficient criterion in terms of uniform derivative bounds on smooth factor-system data. Combining the fibrewise operator with a length operator associated with a proper translation-bounded matrix-valued length function yields the lifted spectral triple. When $B_e$ is separable, the lifted triple, with a suitable grading, represents the Kasparov product of the vertical class with the class of the unit-fibre triple. We also establish a summability criterion and sufficient conditions for stability under central cocycle twisting. A range of examples illustrates the scope of the construction, including twisted crossed products, free compact Abelian actions, and Fell bundles with nonfree homogeneous fibres.

math.OA↗

arXiv2026

Towards Reliable Vision-Language Models for Autonomous Driving

Vision-Language models (VLMs) are increasingly being explored in autonomous driving for tasks such as scene understanding, driving reasoning, decision-making, and end-to-end driving. As their role becomes more prominent, ensuring their robustness and reliability is increasingly important. In real-world conditions, visual inputs may be degraded by sensor imperfections and environmental conditions, potentially affecting both model predictions and their associated confidence. Such degradation is especially concerning in autonomous driving, where safety-critical decisions require models to make accurate predictions and recognize when their predictions may be unreliable. In this work, we evaluate five VLMs (Qwen3.5-9B, Gemma4-E4B, LLaVA-OneVision-7B, DriveFusion/DriveFusionQA-4B, and NVIDIA Alpamayo-1.5-10B) across four driving-related QA datasets with different visual input settings, including single-frame, multi-view, multi-frame, and monocular inputs. Our results show that the effects of visual corruption vary across models, datasets, and input settings, with changes in accuracy and confidence reliability and also differing across conditions. We then apply Visual Evidence Augmentation ($\mathrm{V}{\scriptstyle \mathrm{EA}}$), a recent inference-time method to examine whether it can improve model reliability under degraded visual conditions. We find that $\mathrm{V}{\scriptstyle \mathrm{EA}}$ improves performance for some models and datasets, although the gains are not consistent across all settings.

cs.AI↗

arXiv2026

Evaluating Physical Consistency and Plausibility in Generative Scenario Models for Autonomous Driving

Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they often provide limited transparency into learned representations and consistency with real-world vehicle dynamics. This lack of formal assurance limits their use in safety-critical validation and certification workflows. To address this aspect, we introduce a layered evaluation protocol that complements existing methods by assessing models across five layers. The first four layers inspect internal representations and network layers through kinematic alignment, statistical baseline comparison, latent controllability, and activation analysis. The fifth layer evaluates model outputs against vehicle dynamics constraints such as lateral jerk thresholds. We demonstrate the protocol on a Variational Autoencoder (VAE)-based scenario generator. Although standard output-level metrics and visualizations suggest that the generated scenarios are realistic, our protocol provides deeper insight into the extent to which the model's latent space aligns with kinematic features and whether visually plausible trajectories satisfy vehicle-dynamics constraints. We further apply the protocol to additional generative models, demonstrating its applicability beyond the VAE architecture.

cs.AI↗

arXiv2026

Towards Semi-Automatically Comparing Keyword-Based and Semantic Search Accuracy

The increasing importance of Information Retrieval (IR) in managing large datasets has highlighted significant limitations in traditional keyword-based search systems. Context-aware chat-based search methods, such as Retrieval Augmented Generation (RAG), have recently emerged, but their evaluation compared to keyword-based systems often relies on subjective user feedback. A rigorous, quantitative comparison between these paradigms remains lacking. This work introduces a novel, preliminary framework to quantitatively assess IR accuracy of search systems that produce different output formats, such as lists and messages. It focuses on two key aspects: the ranking accuracy for keyword-based systems and the completeness of retrieved information for semantic chat-based systems. Our approach enables semi-automatic comparisons of semantic and keyword-based methods using interchangeable equivalence classes tailored to domain-specific contexts (e.g., companies or problems). We validate the framework through an industrial case study, demonstrating statistically significant improvements in context-aware search over keyword-based methods, supported by analyses including the Mann-Whitney U-Test. With its adaptable design, the proposed framework provides a strong foundation for objectively assessing keyword-based and semantic chat-based search methods.

cs.IR↗

arXiv2026

Tritium for Nanoscale Hydrogen Analysis by Atom Probe Tomography

Accurate nanoscale detection of hydrogen is essential for understanding hydrogen-related phenomena in materials, yet conventional tracing with deuterium is often complicated by residual background hydrogen. This study evaluates tritium as a highly resolvable isotopic marker for nanoscale hydrogen analysis in metals using atom probe tomography. Titanium was selected for its ability to incorporate hydrogen isotopes, providing a suitable platform for tritium detection. Time of flight secondary ion mass spectrometry and electron backscatter diffraction were performed prior to tritium charging to characterize the initial composition and microstructure. Atom probe tomography in laser mode before and after tritium charging, at three post-charging time intervals, enables tracking of tritium incorporation over time. Thermal desorption analysis confirmed the presence of tritium and complemented the secondary ion mass spectrometry measurements, highlighting the role of the surface oxide layer in modulating tritium release. While tritium, deuterium, and protium differ in their diffusion and trapping behavior, the distinct mass signal associated with tritium provides a practical advantage for resolving hydrogen at very low concentrations. This work serves as a fundamental benchmarking study for leveraging tritium and atom probe tomography as a combined tool for understanding hydrogen in materials, relevant for interpreting local processes such as hydrogen embrittlement.

cond-mat.mtrl-sci↗

arXiv2026

Guidelines for Empirical Studies in Software Engineering involving Large Language Models

Large Language Models (LLMs) are widely used in software engineering (SE) research and practice, yet their non-determinism, opaque training data, and rapidly evolving models threaten the reproducibility and replicability of empirical studies. We address this challenge through a collaborative effort of 22 researchers, presenting a taxonomy of seven study types that organizes how LLMs are used in SE research, together with eight guidelines for designing and reporting such studies. Each guideline distinguishes requirements (must) from recommendations (should) and is contextualized by the study types it applies to. Our guidelines recommend that researchers: (1) declare LLM usage and role; (2) report model versions, configurations, and customizations; (3) document the system and prompt design beyond the model; (4) report session traces, i.e., interaction logs and runtime traces; (5) use suitable baselines, benchmarks, and metrics; (6) include an open LLM as a baseline; (7) validate LLM outputs against human judgment; and (8) articulate limitations and mitigations. We complement the guidelines with an applicability matrix mapping guidelines to study types and a reporting checklist for authors and reviewers. We maintain the study types and guidelines online as a living resource for the community to use and shape (llm-guidelines$.$org).

cs.SE↗

arXiv2026

Lifting strongly graded rings via overgroups

Motivated by lifting problems for principal bundles, we study the following algebraic problem. Let $\smash{\widehat{G}}$ be a group with identity element $e$, let $G \leq \smash{\widehat{G}}$, and let $S$ be a strongly $G$-graded unital ring with principal component $R:=S_e$. We ask whether the given grading extends to a strong $\smash{\widehat{G}}$-grading without altering its $G$-homogeneous components. For every extension $\smash{\widehat{p}}$ of the Picard homomorphism of $S$, we construct a characteristic class in the relative third cohomology group \[ H^3_{\smash{\widehat{p}}}(\smash{\widehat{G}},G;\operatorname{U}(Z(R))), \] where $Z(R)$ denotes the center of $R$ and $\operatorname{U}(Z(R))$ its group of units. The~vanishing of this class is equivalent to the existence of a lift. When it vanishes, the relative second cohomology group \[ H^2_{\smash{\widehat{p}}}(\smash{\widehat{G}},G;\operatorname{U}(Z(R))) \] acts simply transitively on the equivalence classes of lifts with Picard homomorphism $\smash{\widehat{p}}$. We also prove that an $H$-grading is strong if and only if both its restriction to a normal subgroup $N \trianglelefteq H$ and its induced $H/N$-grading are strong. We illustrate the theory through a range of examples.

math.RA↗

arXiv2026

Hardware-Free Robotics Laboratories in Mixed Reality

Teaching robotics relies on screen-based simulation, showing robot motion in an abstract coordinate frame rather than at real scale in the learner's own space, while access to physical hardware is limited by cost, safety, and scheduling constraints. We present MR-Robotics LAB, a mixed-reality (MR) platform that replays MATLAB-generated robot trajectories at real scale within the learner's physical environment. A browser-based service validates a MATLAB workspace file (.mat), normalizes units, and publishes a versioned JSON trajectory; a Unity application on a Meta Quest 3 then reproduces the authored joint configurations under position control and replays them at the declared frame rate within a physics-enabled scene that supports collision detection and end-effector grasping. A formative single-group evaluation with engineering students found that participants reported low setup effort (M = 4.67 on a 5-point scale) and perceived support for workspace understanding from multi-viewpoint inspection (M = 4.56), and 83% of participants affirmed their willingness to use the platform in an introductory robotics course. The evaluation instrument records only perceived outcomes, without counterbalancing or a learning measure, so no comparative advantage over desktop simulation is claimed. The contribution is a reusable simulation-to-MR trajectory pathway and design guidance for hardware-free robot visualization in engineering education.

cs.RO↗

arXiv2026

Recovering Software Architecture Intent from Historical Work Items using Generative AI: A Mixed-Methods Industry Case Study

Software architecture is often only partially captured in code, while much of the design intent lives in evolving project artifacts. In agile projects, work items, user stories, and related tracking documents preserve valuable traces of that intent, but they rarely support direct architectural analysis. This work investigates the recovery of C4 architecture diagrams from historical agile work items using an LLM-based pipeline. The semi-automatic five-step workflow employs a prompt chain, bidirectional traceability, and Chain-of-Thought reasoning to transform unstructured Azure DevOps work items into visual artifacts. Evaluated on two industry projects, we use a mixed-methods design combining qualitative expert interviews with a quantitative stability analysis. Practitioners perceive the generated architectural baselines as accurate and highly useful for system comprehension. Strictly bound by their input data, the artifacts mirror the documented intent, thereby surfacing discrepancies and architectural drift when compared to the implemented reality. Quantitatively, the workflow exhibits high stability for architectural entities but lower stability for their relationships, with relative variance compounding across generation steps. The proposed workflow demonstrates the practical viability of LLM-assisted architectural recovery based on development process artifacts.

cs.SE↗

arXiv2026

Detecting Soft Skills in ML Engineering Roles CVs

Soft skills shape collaboration among ML engineers, data scientists, and software engineers building ML-enabled systems, yet what we know about them comes almost entirely from the demand side. Job advertisements, surveys, and hiring manager interviews capture what employers ask for. How candidates themselves articulate these competencies has not been studied, and existing CV-mining work is both keyword-based, so it cannot see skills conveyed through narrative, and descriptive, reporting frequency rankings without testing whether group differences exceed sampling variation. We close both gaps. Using a balanced corpus of 300 curated CVs spanning the three roles, we extract explicitly listed and implicitly narrated soft skills with an LLM-based pipeline validated against a human-annotated ground truth, a distinction that existing extractors were not designed to make. We then convert the demand-side literature's claims into 13 falsifiable hypotheses about role signatures, seniority progression, and disclosure style, and test them with effect sizes under family-wise error control, so that candidate-side data can corroborate or contradict the demand-side account rather than merely illustrate it. Eleven hypotheses are supported, one partially, and one refuted. Candidates disclose soft skills through narrative rather than keyword lists by roughly three to one, and most so for the competencies employers value most: leadership, coordination, and mentoring (88-96% narrative). Seniority nearly triples the odds of articulating leadership. That competency, assumed universal in prior work, is articulated by software engineers at half the rate of their peers. Technical candidates do articulate soft skills, but a keyword-based screening systematically misses them.

cs.LG↗

arXiv2026

Weak Centrality of unital C(X)-algebras

This paper establishes a fibrewise characterization of weak centrality for unital $C(X)$-algebras whose defining homomorphism maps $C(X)$ onto the center: such an algebra is weakly central if and only if each of its nonzero fibres has a unique maximal ideal. This yields a corresponding characterization for arbitrary unital $C^*$-algebras through their canonical fibres over the spectra of their centers. The resulting criterion explains Vesterstrøm's AF-algebra counterexample, whose obstruction is also interpreted through its Bratteli diagram. A parallel criterion characterizes centrality by simplicity of the fibres. Applications to full group $C^*$-algebras give an alternative proof for the discrete Heisenberg group and show that the full group $C^*$-algebra of every countable non-abelian torsion-free nilpotent group is not weakly central.

math.OA↗

arXiv2026

Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review

Background: Large language models (LLMs) are increasingly used to automate code review, but the reasoning behind their decisions remains hard to understand. Developers struggle to assess the validity of LLM-generated reviews, making it difficult to gauge how much trust to place in them. The role of Explainable AI (XAI) in code review and its impact on trust remain underexplored. Objective: We study the influence of XAI on developer trust in AI-assisted code reviews. Method: We conducted a within-subjects user study with 34 participants, comparing three LLM-based code review systems with varying levels of XAI support: Condition A (detailed explanation and review feedback), Condition B (review feedback only), and Condition C (no explanations). Participants reviewed real-world code change requests alongside the AI-generated reviews. We measured trust perceptions, agreement with the AI recommendation, the reasoning given for each decision, and the time taken. Results: The level of explanation significantly influences both trust and agreement with AI recommendations, but in different ways. Full explanations (A) yield the highest perceived trust (M = 3.99/5) but not the highest agreement, whereas moderate explanations (B) achieve the highest agreement (89.22%). This could suggest that more explanation prompts developers to question AI recommendations more frequently. No explanations (C) results in the lowest trust and agreement. Explanation level did not significantly affect review time. The most commonly cited reasons for decisions were code readability and correctness. Conclusion: Incorporating XAI into code review significantly changes trust perceptions and agreement with AI recommendations. These results inform the design and evaluation of trustworthy AI-based code review systems, as well as studies on the human factors of AI-assisted software development.

cs.SE↗

arXiv2026

Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal

Explainability has emerged as a critical requirement for AI-based systems, particularly in safety-critical and regulated domains. Although prior research has proposed frameworks, patterns, and user-centered approaches to support explainability, there is limited empirical understanding of how existing Requirements Engineering (RE) practices support explainability requirements across the RE lifecycle, especially in an industrial context. This paper reports early findings from an ongoing industry-based study investigating how explainability requirements are elicited, specified, and validated using established RE techniques. We conducted a multi-phase qualitative study with eight practitioners at Daimler Truck, employing think-aloud protocols and moderated group discussions across requirements elicitation, specification, and validation steps. Our preliminary analysis reveals recurring challenges across all steps, including conceptual ambiguity during elicitation, limited testability and expressiveness during specification, and fragmented validation due to vague criteria and regulatory uncertainty. These findings indicate that current RE practices provide limited support to systematically address explainability requirements. The paper contributes empirical insights into step-specific and cross-cutting challenges and outlines a research vision toward developing an empirically grounded RE framework for explainable AI-based systems.

cs.SE↗

arXiv2026

Automating Quality Assessment with NLP of LLM-Generated Defeaters

High-integrity systems, such as autonomous vehicle fleets and large-scale energy infrastructures, rely on structured assurance cases to justify safety claims. To remain valid under evolving operational conditions, such cases must be examined against potential challenges, known as defeaters. While large language models (LLMs) can support the scalable generation of candidate defeaters, assessing their quality remains largely manual and subjective process. This paper presents an automated approach for supporting the assessment of LLM-generated defeaters using natural language processing techniques. The method combines structural features from assurance case graphs with semantic embeddings and meta-classifiers trained on expert-assessed defeater annotations. We evaluate the approach through two case studies in the automotive and energy domains. The results show substantial human reviewer dissensus, with Cohen's kappa values below 0.442, highlighting the difficulty of consistent manual assessment. Against this background, the proposed classifiers achieve an average F1-score of 0.84 in validation and show improved alignment with individual expert ratings. The findings suggest that automated assessment can help reduce subjective variance and provide scalable decision support for assurance case review, while leaving final judgment to domain experts.

cs.SE↗

arXiv2026

RunSoC 2.0: Scheduling and Allocating Automotive Software Tasks to Hardware Partitions in Heterogeneous MPSoCs

Centralized automotive architectures increasingly consolidate compute-intensive workloads onto heterogeneous Multi-Processor System-on-Chip (MPSoC), creating strict execution, memory, and communication constraints. This paper presents RunSoC 2.0, a customizable framework for early-stage design-space exploration of task scheduling and allocation on heterogeneous MPSoCs. Building on RunSoC 1.0, which targeted allocation on homogeneous hardware, RunSoC 2.0 extends the framework to heterogeneous platforms by modeling processor-specific execution times, cluster-level organization, and domain-specific processing properties. It represents task sets as directed acyclic graphs (DAGs) subjected to strict end-to-end latency and core-affinity constraints, and formulates task scheduling and allocation as a multi-objective optimization problem that minimizes hierarchical memory-budget violations and inter-core/inter-cluster communication penalties. The framework supports multiple solving backends, including COIN-OR Branch and Cut (CBC), Google OR-Tools CP-SAT, and a Genetic Algorithm (GA), enabling comparative evaluation of exact, constraint-programming, and meta-heuristic approaches. We evaluate RunSoC 2.0 using synthetic automotive task sets ranging from 10 to 500 tasks, mapped to representative heterogeneous MPSoCs, including the Renesas R-Car V4H, NVIDIA Jetson AGX Orin, and TI TDA4VM. The results show that RunSoC 2.0 can generate feasible and optimal schedules, expose architectural bottlenecks, and support rapid comparison of platform alternatives. Notably, CP-SAT consistently outperforms both CBC and the GA across tightly constrained hard real-time scheduling instances. By incorporating cluster-aware communication and memory modeling, RunSoC 2.0 improves the realism of early-stage MPSoC analysis while retaining practical solution times for large automotive workloads. (..)

cs.AR↗