AI systems are increasingly deployed in real-world settings where their behavior is shaped by dynamic environments, evolving data distributions, and complex interactions with users and infrastructure. Traditional machine learning evaluation focuses on benchmarks and operates within sandboxed environments, providing only a limited view of the true system behavior in the wild. We argue for the development of principled auditing frameworks that monitor deployed AI systems throughout their lifecycle. We further propose framing auditing as a statistical problem of monitoring constraint violations under uncertainty, where desired properties (e.g., fairness and safety) are treated as risk-controlled constraints that must be continuously evaluated as systems evolve through iterative feedback. This perspective highlights the need for uncertainty-aware monitoring methods, socio-technical specifications of audit criteria, and auditing infrastructures that enable ongoing oversight of AI systems in the wild.

Computing's dominant concepts - innovation, efficiency, resilience, professionalism - often migrate from reflective ideals to instruments that limit behaviour, redirect responsibility, and foreclose critique. We call this drift weaponisation: the discursive repurposing of professional concepts so that they stabilise business-as-usual while making structural alternatives appear unreasonable, illegible, or out of scope. Using collective autoethnography across education, justice, public administration, research management, and computing, we identify recurring mechanisms (simplification, individualisation, binary framing, metric substitution, hero/resilience scripts, organised ignorance). From this synthesis we propose Reframing - peaceful, practice-ready shifts (e.g., From Simplified Slogans to Structural Literacy; From Performative Compliance to Meaningful Outcomes; From Coping to Justice) - each paired with a 'do-now' prompt. The levers restore complexity, surface assumptions, and redirect attention to structural conditions without requiring formal authority. We contribute: (1) a cross-field account of weaponisation as a patterned phenomenon; (2) a portable reframing toolkit grounded in narrative and systems thinking; and (3) implications for computing within limits, including day-to-day practice shifts toward care, sufficiency, and justice.

The CPU-side large language model (LLM) tokenizer is a critical security gap in LLM serving through a confidential computing stack with CPU and GPU trusted execution environments (TEEs). Tokenizers converts the prompts through table-driven lookups, and the resulting memory access patterns are a powerful source of side-channel leakage. Recent work demonstrates end-to-end recovery of user prompts from tokenizer access pattern on production Intel TDX. However, a drop-in use of the popular tree-based Oblivious RAMs (e.g., PathORAM) to prevent access-pattern leakage introduces $\sim$13$\times$ tokenizer slowdown, resulting in 10-58% higher time-to-first-token (TTFT). In this paper, we present OTRO, an efficient, oblivious tokenization path tailored to latency-critical LLM serving. OTRO relies on square-root ORAM for fast single-access lookups, but avoids its prohibitive $O(N\log^2N$) rebuild cost every $\sqrt{N}$ accesses through three key innovations. First, OTRO provides a pool of replicated square-root ORAM instances that utilize the read-only nature of tokenizer table. Second, an epoch-based rotation policy decouples accesses from rebuilds and pads each epoch with dummy accesses to its boundaries, minimizing observable information. Lastly, chunked KV-cache-aware tokenization further overlaps rebuilds with GPU prefill and minimizes the instance count. Implemented as modules in HuggingFace Tokenizers and nano-vLLM, running within a TDX-enabled CVM with an NVIDIA H100 GPU, OTRO limits TTFT overhead to at most 4.5%, keeps tokenizer-induced latency under 10\% of total TTFT, and adds less than 0.5 GB of memory overhead while reducing the tokenizer's observable leakage across various model families and sizes.

This article proposes a novel methodology for the classification of transient and stationary regimes in dynamic systems. Several sensor-based solutions for regime classification in the literature require the setting of several parameters, or are not suitable for scenarios involving multivariate systems that may contain periodic signals. The proposed method introduces a spatial curve representation of the considered system based on its sample mathematical moments. Then, by connecting concepts of stability theory, geometrical properties of spatial curves and stationary stochastic processes, two regime classifiers are designed using the arc length and the curvatures of the proposed curve. Both classifiers are capable of describing and detecting transient regimes, considering behaviors such as: multivariate asymptotically, marginally stability, and cyclostationarity. Furthermore, a quantitative comparison in performance and computation resources of the proposed classifiers against existing classifiers in the literature illustrates that the proposed regime classifier based on the arc length outperforms other techniques in classifying transient regimes for simulated linear, non-linear, and discontinuous multivariate systems under the specified studied conditions.

What happens to permacomputing when electricity grids shift to decentralised green energy, and local communities and municipalities have increased governance over this vital public service? Electricity and computational networks are more than just separate systems that plug together. Shifts to renewable energy generation in the grid are impacting computational systems, and computational demands on electrical power are impacting the electricity grid; one infrastructure limits the other. Permacomputing research tends to focus on 'off-grid' or 'behind-the-meter' energy. This sacrifices some of the social justice benefits that the public electricity grid, managed and regulated for universal service, was designed to provide. Our paper uses empirically-grounded 'speculative fabulation' to identify research opportunities in permacomputing that open up when energy systems are federated across communities. The speculative fabulation takes the form of an interview between the energy manager of a future energy island in the North Sea and a permacomputing podcaster. This allows us to conceive of computing-grid integration in tractable social and ecological terms, and introduce a notion of 'fair trade energy'.

Clustering in a big data setting is an intensively studied problem, with coresets emerging as one of the important paradigms in this line of work. Given a cost function $\text{cost}(P,S)$ mapping input points $P$ and a solution $S$ to an objective value, a coreset is a typically weighted sketch $Ω\subseteq P$ such that $\text{cost}(Ω,S)\approx \text{cost}(P,S)$. In practice, coreset sizes much smaller than those suggested by theoretical guarantees are often found to be sufficient. In this paper, we offer an explanation for this phenomenon. Smaller coreset sizes suffice if we only wish to preserve the costs of \emph{good} solutions, i.e., solutions with low cost. We define and devise \emph{approximation-preserving coresets}, which provide a weaker guarantee than strong coresets, which apply to all solutions, while providing stronger guarantees than weak coresets, which apply only to the optimum solution. We complement this result by showing that even a very small distortion in the approximation factor cannot admit coresets of this size.

Linear probing is one of the simplest and most space-efficient approaches to hash table design, and is widely used in sequential settings due to its compact memory layout. However, designing a concurrent linear-probing hash table with strong liveness guarantees has proved difficult, and only a handful of such algorithms have been proposed, all of which either restrict concurrency or rely on large per-entry metadata, thereby compromising space efficiency. We present a lock-free linear-probing hash table with wait-free lookups that retains the core advantages of sequential linear probing while handling contention gracefully. Our design uses only a small amount of metadata per table entry: a constant number of additional bits when using LL/SC, or a logarithmic number of bits when using CAS. The algorithm is linearizable and lock-free, supports insert, delete, and wait-free lookup operations, and is able to safely reclaim space used by deleted elements without rebuilding the table. We analyze the amortized step complexity of our hash table assuming no concurrent insertions of the same key, and show that each operation has expected amortized step complexity matching that of sequential linear probing, up to the point contention per key.

Transmission failures can lead to cascading failures and system blackout affecting millions of customers if not handled in time, and choosing the best locations to monitor the condition of the transmission system is crucial for power system reliability. In this paper, we propose a new sensitivity factor, the line outage impact factor (LOIF), which is especially useful for power system monitoring and can reveal the impacts of a transmission outage on the power flow of other lines more effectively than existing sensitivity factors, such as the line outage distribution factors (LODF). In this study, we apply the LOIF in transmission line outage detection in three test systems and compare it with LODF using a number of observed transmission line (OTL) selection methods based on these two sensitivity factors. Then we apply a machine learning algorithm to detect the outages of other lines by monitoring the selected OTLs, and the detection accuracy is evaluated using the F1-score. The results show that, in general, with the same number of OTLs, detection using the OTLs selected using LOIF achieved higher F1-scores. The pattern was especially consistent in large-scale systems, showing its potential in real-world applications.

Counts of $k$-cliques are commonly used metrics in subgraph mining. Since graphs often have sensitive data, there also has been a lot of work on $k$-clique counts with differential privacy. However, these metrics have very high global sensitivity, and so more sophisticated techniques have been developed for counting $k$-cliques with privacy. Smooth sensitivity and ladder functions were developed for reducing the noise magnitude for private estimates of these metrics. However, these are computationally very inefficient to estimate. No polynomial time algorithms are known for smooth sensitivity of $k$-cliques for $k>3$, while the time complexity of ladder functions is lower bounded by the time for exact counts, which does not scale very well. In this paper, we develop a new highly scalable algorithm for estimating $k$-clique counts with differential privacy. Our algorithm adapts the ladder function to serve as a smooth upper bound on its local sensitivity, and utilizes the approximation sensitivity framework to calibrate noise with magnitude proportional to an approximation of the bound. This gives us a significant improvement in the running time. Experiments show that our method is several orders of magnitude faster than the ladder function based estimates of $k$-clique counts, while the accuracy is similar. Our algorithm is the first to scale to graphs with millions of edges, and for larger $k$, for which the ladder function algorithm doesn't complete.

Safe set computation is a fundamental challenge in safety-critical control systems, especially in direct data-driven settings where safety analysis is performed directly from noise-affected measurements, without explicit modeling. A recently proposed method, Data-Driven Hamiltonian (DDH), enables reachability analysis directly from measurements, without relying on prior knowledge of the underlying system dynamics. This paper extends the DDH framework to a robust setting that accounts for measurement noise, exogenous disturbances, and sampling-induced state-velocity estimation error. A Robust Data-Driven Hamiltonian (R-DDH) is derived from noisy measurements and shown to yield a certified lower bound on the exact Hamiltonian. This results in a provable under-approximation of the value function and an inner approximation of the associated safe set. The gap between the data-driven and exact Hamiltonians is quantified, and it is shown to converge to zero with more data in a noise-free setting with additive disturbances. The effectiveness of the approach is shown through two case studies: a constrained double integrator and an aircraft taxiing system with a nonlinear closed-loop controller operating under perceptual uncertainty.

This paper presents STORX: Shape and Topology Optimization for Research and Experimentation, an open-source MATLAB-based educational framework for learning and teaching computational design optimization. STORX provides a platform for parametric and level-set shape optimization, as well as topology optimization methods including density, level-set, and topological sensitivity approaches such as evolutionary and Pareto-tracing methods. All modules follow a consistent object-oriented structure and integrate visualization, sensitivity analysis, and finite element routines, enabling users to explore the continuum between shape and topology optimization in a transparent and reproducible manner. The code is designed to complement graduate-level coursework and independent research by emphasizing modularity and extensibility through a clear separation of intent. Core software interfaces are defined via abstract base classes, enabling new objective functionals and design/manufacturing constraints to be implemented by adding derived classes without modifying the core code. The paper also describes the software architecture and demonstrates how the framework maps mathematical formulations directly to executable code through a series of illustrative problems.

We start from a small open question, where Hetzl and Vierling asked whether two theories of induction, open induction and clause set cycles, are incomparable. They proved one direction and left the other open. Here we close it, and the proof is almost embarrassingly short, because the rules for addition can only fire when the first argument is $0$ or a successor, a Skolem constant is neither, so the terms $a{+}b$ and $b{+}a$ can never be touched, and a machine that can never touch them can never prove they are equal. The thing that separates the two theories is the order of two constants, and that order is a fact about numbers, not about symbols. We extract from this proof a small general principle, the Syntactic Invariance Principle, that names the shape of such arguments. We then close with a few speculative remarks on how this same shape appears, informally, in the known barriers to settling $\mathsf{P}$ versus $\mathsf{NP}$, where each barrier seems to point to a level of description that the techniques in the barrier cannot reach. We raise this as a suggestion rather than a theorem, since the analogy is real but we do not push it past the point where we can defend it. Along the way we raise an open question that the analogy suggests but does not settle, on whether a fast algorithm for $\SAT$, were it to exist, would always be exhibitable as a machine you can write down or whether it could be found, in some cases, only as a function on the numbers.

In the perpetual pursuit of performance, modern computing systems rely ever more on stateful mechanisms to accommodate the dynamics of workloads and physical environments, bolstering efficiency but confounding benchmarking and thereby the optimization of software. Indeed, by their nature, adaptive mechanisms introduce temporal dependencies between measurements and render naive estimators of individual program performance biased. Observing that rectifying such biases necessitates speculative assumptions about system dynamics, we call for prioritizing performance differentials over absolute measures and formalize software benchmarking as the decision problem of identifying the fastest program, for which relative knowledge suffices. To this end, we propose simple experiment designs admitting consistent estimators of contrasts, whereby program-specific biases cancel under tenable assumptions. These designs asymptotically yield the correct decision and afford a robust methodology for finite-budget benchmarking in stateful environments, bearing broad implications for the development of performance-sensitive software.

Large Language Models and vision-language models have shown remarkable success in the front-end design of Very Large-Scale Integrated Circuits, yet their capabilities for VLSI physical design remain significantly underexplored. The primary cause is the lack of standardized benchmarks for evaluating agentic physical design workflows that require high-dimensional, multi-stage optimization under strict design constraints, coordinated interaction with diverse Electronic Design Automation tools, and iterative refinement. This work introduces PDAGENT-BENCH, a comprehensive and multi-dimensional benchmark for evaluating LLM/VLM-based agents across the physical design stack. PDAGENT-BENCH integrates both task-level assessment and workflow-level execution. The benchmark suite contains 353 curated problems that combine conceptual questions with real-world industrial artifacts, with expert-validated references and executable solutions. These tasks cover five key capability dimensions: foundational knowledge, report comprehension, root-cause analysis, script generation, and full-flow implementation. In addition, the benchmark provides a unified, human-aligned agentic physical design workflow framework that enables closed-loop evaluation of holistic physical design in realistic EDA environments. Experiments on 11 state-of-the-art models reveal that while modern LLMs/VLMs perform competitively on conceptual tasks, they remain substantially limited in tool-centric execution (e.g., 42.2% on Innovus script generation) and long-horizon, multi-stage reasoning. Our studies further show that human-skill-enhanced agentic workflows significantly improve end-to-end physical design performance. PDAGENT-BENCH establishes a standardized, reproducible, and realistic evaluation framework for advancing LLM/VLM-driven holistic physical design automation. We will open source the benchmark and framework soon.

Internet blackouts, occurring due to technological mishaps or intentional governmental action, prevent citizens from accessing the internet. Citizens in regions where internet blackouts are common have utilized blackout-resistant technologies to maintain communication. Such technologies often rely on mobile mesh networks to provide limited messaging services. However, no technology currently exists which can provide continued access to knowledge sources on the web during a blackout. We present Cache to the Future (CttF): a system to cache and deliver static content hosted on the web during a blackout. CttF's distributed community ratings crowdsources caching at scale while cryptographic constructs (digital signatures, proofs-of-work) mitigate adversarial interference. Our realistic simulations demonstrate CttF delivering content at city-scale across a wide range of benign and adversarial scenarios.

This paper develops a compact collecting semantics for the residual behaviour left by nonterminating computation. For sequential time this is the tail-cluster set of the stream in the Stone-Cech compactification of the observation space. It gives a common semantics to ordinary recurrence, mixed recurrent behaviour, and escape through noncompact parts of the observation space. The basic theory establishes tail invariance, functoriality under continuous observations, and a temporal reading for clopen observations: containment in the corresponding clopen region of beta-X is eventual truth, while nonempty intersection is recurrence. Progress and fairness assumptions are represented by strengthening the time filter. Relational meanings are obtained by compactifying products, so correlations between observations made along the same asymptotic view of time are retained. The main application is to residual behaviour in CCS. Infinite executions are read as streams of residual processes modulo structural congruence. The resulting semantics distinguishes stable divergence, finite recurrent divergence, mixed recurrence with escape, and escape through unbounded residual growth. It validates residual-tail laws for prefixing, guarded unfolding, finite choice, and finite prefix-choice forms, while also identifying the boundary of those laws under parallel composition and synchronisation. Finite observational quotients provide the computational interface to the compact semantics: abstract meanings become recurrent states and strongly connected component calculations, and resource observations detect unbounded escape without requiring individual points of the Stone-Cech remainder to be inspected.

Neuro-symbolic AI (NeSy) pairs neural perception with symbolic reasoning, making it attractive for high-stakes domains where explainability and structured inference are required. However, this hybrid architecture introduces an enlarged attack surface spanning five layers: neural perception, symbolic knowledge bases, reasoning engines, agentic orchestration, and data stores -- each exploitable in ways absent from purely neural systems. This paper makes six contributions: (1) formal definitions of NeSy Attack Surface, Symbolic Integrity Violation (SIV), and Cross-Layer Amplification Ratio $\mathcal{X}$, decomposed into neural-caused and autonomous symbolic sensitivity components; (2) a unified threat model extending MITRE ATLAS with 11 NeSy-specific tactic extensions and a five-profile attacker taxonomy; (3) a symbolic-layer threat catalogue covering knowledge graph (KG) poisoning, ontology-merging, and inference-engine subversion; (4) analysis of cognitive risks -- automation bias, authority bias, and sycophantic reinforcement -- structurally amplified by NeSy's explicit logical explanations relative to black-box neural outputs; (5) interdisciplinary mitigations with measurable acceptance criteria aligned to NIST AI 600-1 and the EU AI Act; (6) three empirical benchmarks: (E1) targeted KG poisoning achieves break-even SIV at injection budget $B=5$ on a 205-entity medical KG, with a KG-specific stealth/SIV trade-off; (E2) PGD-10 at $\varepsilon=0.01$ yields $\mathcal{X}=5.884$ (95% CI $[4.64,\, 8.00]$, $p<0.0001$), confirmed adversarially specific by a matched-random baseline ($E^{R}_{\mathrm{rand}}=0$), on a DistilBERT+ProbLog pipeline; (E3) single-axiom OWL edits achieve 93.3% SIV success with 100% Pellet-consistency stealth, but held-out STIX detection fails at 50% (random-guessing level), an open problem.

This paper develops and analyses the Fair Play Automatic Market Maker (FP-AMM), a programmable electricity allocation mechanism in which scarcity allocation is treated as a controlled, stateful, and auditable cyber-physical process. Existing mechanisms such as locational marginal pricing are memoryless and cannot account for historical service outcomes, preventing guarantees of equitable treatment across market intervals. The FP-AMM employs a two-stage stochastic clearing rule comprising service-priority sampling and inverse-fairness weighting, coupled with a DC-OPF feasibility set and bounded shortage memory updated through a saturated integrator. Four main results are established. First, the shortage-memory state is invariant in $[0,1]^N$ and the update map is a contraction with rate $1-β$. Second, the intra-interval clearing operator converges linearly to a unique fixed point with contraction factor $q\in(0,1)$. Third, under the Fair Play priority rule, the per-node delivery ratio converges almost surely to the contracted target $F^\star$, with a finite-time $O(1/\sqrt{T})$ bound obtained via Lyapunov analysis of the deficit recursion. Fourth, event-triggered execution guarantees practical ultimate boundedness of the allocation tracking error and quantifies the computation-fidelity trade-off. The mechanism is validated on the IEEE 14-, 57-, and 118-bus systems over $T=5000$ market intervals. Fairness convergence to $F^\star$ is achieved on all benchmarks, peak weak-bus fairness error is reduced by 54% on the IEEE-57 network and by up to 55% relative to an equal-weight baseline during scarcity periods, and DC feasibility is maintained throughout.

Dynamic Gaussian compression is normally optimized for complete files or complete progressive prefixes, but interactive rendering encounters partial representations: some spatiotemporal regions are present, others missing, and late refinements cannot affect the displayed frame. We study dynamic Gaussian representations whose incomplete delivery states remain directly renderable and whose degradation is optimized in image space. Gaussian primitives are organized into independently addressable spatiotemporal clusters with a base level and three refinements; training samples partial dependency graphs, renders many counterfactual states in one GPU batch, and minimizes expected distortion, tail distortion, temporal inconsistency, rate, and prefix regressions. A counterfactual utility layer measures the marginal render contribution of each completion group across valid receiver contexts. The same graph admits a concrete delivery realization with MTU-bounded entropy-coded chunks, deadline-aware scheduling, and receiver-side dependency closure. On held-out views, the finest refinement has negative mean marginal utility in 3/32 D-NeRF bouncingballs, 49/64 HyperNeRF broom2, and 28/64 HyperNeRF chicken clusters; its lower-tail utility is negative in 21/32, 61/64, and 42/64 clusters, respectively. On broom2, render-utility ordering removes both PSNR regressions produced by nominal layer order at matched byte budgets; on chicken, utilities measured on disjoint training cameras improve held-out PSNR by 3.03 dB at the lowest matched budget. These scoped results show why nominal refinement order cannot substitute for render-conditioned utility: the formulation treats network delivery as a distribution over renderable scene states rather than as an external wrapper around a graphics codec.

High-Level Synthesis (HLS) enables rapid hardware development by translating C/C++ programs into hardware implementations. Functional consistency verification between golden C specifications and HLS-oriented C implementations is a critical yet labor-intensive task in HLS design flows. While Large Language Models (LLMs) have recently shown promise in automated testbench generation, their stochastic nature often leads to insufficient coverage, inconsistent verification environments, and unreliable equivalence checking results. To address these limitations, we propose a knowledge-augmented, agent-driven shift-left verification framework for automated functional consistency checking between golden C and HLS-C implementations before synthesis. The framework introduces a Dual-Tier Consistency Checking mechanism that jointly enforces static structural alignment and dynamic behavioral equivalence between paired testbenches, while integrating symbolic execution and coverage-driven refinement to improve verification completeness. Furthermore, we construct a heterogeneous HLS Verification Knowledge Graph to provide topology-aware reasoning priors for testbench generation, and design an autonomous verification agent to orchestrate iterative refinement and failure diagnosis across heterogeneous toolchains. Experimental results on 107 HLS benchmark pairs demonstrate that the proposed framework achieves 98.26\% average coverage and 95.33\% dynamic consistency, outperforming representative AST-based, retrieval-augmented, and iterative agent-based baselines. https://github.com/cz-5f/HLS-LeVeri.git

Because of their ability to enable new forms of cryptanalysis, quantum computers pose a threat to the cryptographic algorithms that are widely used to secure contemporary computer systems. A practical quantum computer may emerge within the next ten years or so, but due to theorised "harvest now, decrypt later" style attacker behaviour, mitigations are necessary today. Recent advances in cryptography and security architecture show promise in supporting the design of systems that exhibit resilience against quantum-enabled cryptanalysis, however there is a key gap in the literature around the subject of deriving tolerances for such systems. In this paper, we introduce the concept of rotation time as a measure of crypto agility, and derive an approximation that links rotation time tolerance to security risk tolerance. Historical CVE data is used to calculate illustrative values for rotation time tolerance, which is found to be of the order of hours to days. This demonstrates that using crypto agility in conjunction with hybrid encryption is an effective approach for designing quantum-resilient systems, but may necessitate challenging technical and operational tolerances in order to meet organisational risk tolerances.

Modern blockchain state management faces a critical scalability bottleneck: maintaining cryptographic commitments over hundreds of millions of entries becomes computationally prohibitive. Ethereum's transition to Verkle Trees: polynomial commitment accumulators reducing proof sizes from O(width * depth) to O(depth) via constant-size IPA vector commitments, is a critical step toward stateless operation. Yet, current implementations exhibit pathological characteristics that burden home validators. We identify four inefficiencies in the reference go-verkle implementation \cite{kaur2025goverkle, kaur2025goethereum}: (1) phantom node creation during non-existent account deletion; (2) 64-byte database keys triggering excessive LSM-tree compaction; (3) redundant memory copying in proof deserialization; (4) a Proof of Absence wire format incompatibility causing non-deterministic serialization. We present Fractional Verkle Trees (FVT), a hypertree decomposition partitioning global state into N independent sub-accumulators coordinated by a Merkle commitment tree, achieving improved cache locality, zero-lock-contention goroutine-parallel commitment computation, and faster root recomputation (91 $μ$s vs $\sim$500 ms). We address each inefficiency via existence checks, 32-byte SHA256 node references, zero-copy reference-counted buffers, and HashMap-based lexicographic deduplication. Benchmarks on Apple M1 Pro show 57\% heap allocation reduction (566,760 to 242,004 bytes per 10K proofs), parallel insertion at 2,433 ns/op, and network-wide elimination of 4.85 PB/year across 6,000 full nodes, advancing the Ethereum stateless roadmap.

This position paper examines a paradox encountered in UX research practice: a situation where real human participants delivered less authentic insights than AI personas might have, due to context-induced biases. We share our experience developing research-based AI personas using OpenAI's custom GPT builder and conducting a design thinking workshop with high-net-worth banking clients. The workshop setting, including a luxury hotel, present portfolio managers, and hospitality dynamics, introduced biases that compromised the feedback. We propose that AI personas offer an underexplored opportunity to mitigate certain human limitations in user research, and call for frameworks that help teams recognize when traditional research contexts introduce biases that AI personas might help avoid.

Logs record the runtime behavior of software and are widely used in various tasks such as debugging, testing, and fault diagnosis. With the increase in system size and complexity, log analysis has gradually become a challenging task. Current industrial systems typically use log aggregation systems such as Grafana Loki and ELK to simplify the log collection and analysis process. Engineers write queries using the DSL query language provided by these systems can complete a variety of log analysis tasks. However, writing these queries is often time-consuming and labor-intensive, as it requires engineers to have a thorough understanding of the DSL syntax and the detailed information contained in the logs. To address these challenges, this paper proposes LogCopilot, an automated log aggregation analysis framework based on large language models (LLMs). LogCopilot accepts natural language log analysis instructions and accomplishes automated log analysis through knowledge retrieval and tool calling. LogCopilot constructs a hierarchical knowledge base to represent and provide key knowledge in logs. And it achieves automated log aggregation analysis by generating and executing LogQL queries. The evaluation based on four log datasets confirm the effectiveness of LogCopilot, which achieves an average accuracy of 76.8% and outperforms baseline approaches. Moreover, experiment results shows that LogCopilot is effective in LogQL query generation.

Building automation and control systems integrate heating, ventilation, air conditioning, lighting, sensing, and management functions through specialized communication protocols. While this integration enables flexible building operation, it also creates complex cyber-physical environments that are difficult to inspect, secure, and explain to new analysts. This paper presents a practical security and human-centered case study of a BACnet/IP building automation testbed with DALI lighting infrastructure, investigated during a domotics-oriented cybersecurity hackathon in Thun, Switzerland in April 2026. The study combines network-oriented enumeration, object-level inspection, physical rack analysis, and reflective HCI analysis of tool-supported learning. Using Yabe and BACteria, the work documents observable BACnet services, reconstructs structured object hierarchies, identifies room-level lighting-control paths, and maps BACnet objects to DALI group-level infrastructure. The analysis emphasizes that BACS assessment is not only a technical protocol task: it also requires usable tool interfaces, physical observability, interpretable naming conventions, and safe mental models for command priorities. The paper contributes a compact case study of BACnet/DALI exploration in an educational testbed and discusses implications for cybersecurity education, human-centered security tooling, and responsible experimentation in cyber-physical building environments.

Large language model (LLM) coding agents are increasingly applied to code translation and optimization, yet their effectiveness in performance-critical high-performance computing (HPC) settings remains poorly characterized. This paper evaluates LLM-based coding workflows on SZ-family error-bounded lossy compression kernels, which combine numerical constraints with memory-intensive and control-flow-heavy implementations. We study two representative CUDA workloads (SZp and SZx) and target two heterogeneous execution platforms: NVIDIA GPUs and Cerebras wafer-scale accelerators. Focusing on single-agent iterative generation, we analyze not only final throughput but also agent runtime behavior, including iteration patterns, sensitivity to prompt specification, and characteristic failure modes. Our results reveal a pronounced cross-architecture divergence. On GPUs, stronger models can achieve substantially higher throughput but exhibit increased sensitivity to prompt precision and optimization guidance, whereas on Cerebras the dominant challenge lies in producing runnable programs under a PE-centric spatial execution model. We further observe that LLM agents are more effective on modular kernels (SZx) than on tightly coupled bit-level pipelines (SZp), where structural dependencies hinder optimization progress. These findings suggest that evaluating LLM coding agents for HPC requires accounting for both performance outcomes and architecture-specific robustness, and that success on thread-based platforms does not directly transfer to spatial accelerators.

We introduce Ergodic Deviation-Robust Equilibrium (EDRE), a dynamics-relative equilibrium concept for repeated finite games in which agents learn via entropic mirror descent (EMD). EDRE requires three properties to hold simultaneously for the same profile and learning run: (E1) the limit profile is an $\varepsilon$-Nash equilibrium at a product distribution; (E2) along the entire learning trajectory, every fixed coalition's cumulative aggregate (summed-unilateral) deviation gain is $\tilde{\mathcal{O}}(\sqrt{T})$ with high probability; and (E3) the limit profile is a fixed point of the EMD map, so that it is selected by the dynamics rather than merely certified as an equilibrium. We prove that the $\sqrt{T}$ deviation-regret rate is order-tight, establish existence in exact-potential games (via Nash's theorem, with a constructive proximal route under concavity) together with Lyapunov monotonicity of EMD (and pointwise convergence when the fixed-point set is a singleton), and extend the selection property to monotone polymatrix games through variational inequalities. Although a static EDRE coincides with an $\varepsilon$-Nash equilibrium, its content is dynamic: robust (positive-measure) selection under EMD excludes linearly unstable equilibria, so EDRE acts as a Nash equilibrium equipped with a dynamic certificate rather than a static refinement. On the complexity side, we show that computing EDRE is PPAD-hard in general polymatrix games and belongs to promise-PPAD for potential games. A worked $2\times 2$ coordination-game example illustrates all components of the framework. Additional results, including a bandit-feedback extension, a period-doubling route to Li-Yorke chaos for the two-strategy EMD map at large step size, a linear-program formulation for minimum-cost steering, and supporting simulations, appear in the appendices.

Channel charting (CC) in real-world coordinates is a recently proposed self-supervised machine learning method that maps high-dimensional channel state information (CSI) to user equipment (UE) position. In this paper, we extend CC to also estimate UE orientation, which can further assist tasks such as beamfinding, precoding, and beam- and cell-assignment. To this end, we propose a novel orientation triplet loss that accounts for angle periodicity and an alignment loss that embeds estimated orientations in real-world coordinates in a self-supervised fashion. Using real-world CSI measurements from a standard-compliant 5G NR system, we demonstrate that the proposed method achieves position and orientation estimation accuracy close to that of supervised approaches trained with ground-truth labels.

Channel state information (CSI)-based neural positioning learns a mapping from CSI measurements to user equipment (UE) positions using neural networks. However, most existing performance evaluations utilize randomly partitioned train/test CSI-dataset splits, which fail to reflect the generalization requirements of practical deployments and present optimistic results. In this paper, we study the spatial and temporal generalization of neural positioning with standard-compliant Wi-Fi and 5G NR systems for three real-world CSI datasets acquired in indoor and outdoor environments. We assess generalization with two different architectures, a conventional multilayer perceptron (MLP) and a novel transformer architecture, to unseen spatial regions, unseen UE trajectories, and CSI measurement campaigns separated by one week. Our experiments show that both architectures generalize well in space and time, and the proposed transformer consistently outperforms the MLP in positioning accuracy while requiring fewer model parameters.

Modern AI systems increasingly solve a task not with a single model call but with several imperfect agents working together: some propose pieces of a solution, others verify them, and the results are combined. These systems often outperform any single model, yet it is rarely clear why they succeed or when they will fail. We model such a system as message passing on a sparse graph, the structure that underlies low-density parity-check (LDPC) codes, and extend the density-evolution machinery of coding theory to this richer setting. In our model a task is a set of coupled binary subclaims, and an agent architecture is a sparse, role-typed factor graph whose check nodes are noisy Boolean verifier nodes, each computing a local Boolean function of the subclaims it touches. Three distinct failure modes, all modeled as erasures (an agent abstaining, a verifier returning no usable output, and a message lost between two agents), propagate as the agents exchange set-valued messages. The check agents combine these messages by a single logical-forcing rule that specializes to XOR, AND, OR, implication, and Horn constraints. This is more than a relabeling of LDPC theory: the verifier functions are nonlinear and value-asymmetric, and the three failure modes do not reduce to a single effective channel, so they require new threshold, finite-length, and converse results rather than a direct reuse of parity-check density evolution. We prove a density-evolution theorem that predicts the asymptotic fraction of unresolved subclaims on random role-typed architectures, with an extension to deterministic, locally tree-like graph sequences. The XOR case recovers the classical LDPC recursion on the binary erasure channel (BEC); the AND case exposes an asymmetry between positive and negative verifier certificates.