The rapid growth of AI models and increasing data sovereignty requirements are driving the transition toward geo-distributed AI training across multiple data centers. Such deployments introduce system-level challenges arising from synchronization-intensive communication, cross-site data exchange, and wide-area latency constraints. This paper investigates EVPN--VXLAN as an infrastructure foundation for geo-distributed AI training environments and presents a scalable emulation framework for systematically studying distributed AI workloads under realistic wide-area conditions. The proposed framework combines VXLAN overlays with EVPN-based inter-data-center connectivity and is implemented using ContainerLab and FRRouting (FRR). The framework further incorporates Equal-Cost Multi-Path (ECMP) routing, Bidirectional Forwarding Detection (BFD), and a queue-pair-aware traffic distribution mechanism designed to improve communication behavior for synchronization-intensive AI workloads while preserving compatibility with commodity infrastructure. Using realistic WAN emulation, we characterize communication and system behavior under distributed training workloads employing AllReduce and Parameter Server communication patterns. Results provide insights into traffic distribution, resilience, and infrastructure behavior in geo-distributed AI environments, highlighting the potential of reproducible multi-data-center infrastructure frameworks for scalable distributed AI training.

This paper studies output regulation for a class of unknown continuous-time nonlinear systems driven by almost periodic exosignals. The plant dynamics are assumed to be linearly parameterized over a prescribed nonlinear dictionary, while all coefficient matrices in the plant, input channel, output map, and exosignal channel are unknown. Since the plant model is unavailable, exact nonlinear output regulation would generally require model identification followed by the solution of nonlinear regulator equations. To avoid these steps, we pursue a frequency-selective regulation objective: the steady-state regulation error is allowed to be almost periodic, but its Fourier-Bohr coefficients at prescribed exosystem frequencies are guaranteed to vanish, and the residual error energy is explicitly bounded. To this end, a p-copy internal model is embedded in a dynamic controller, yielding an augmented nonlinear system whose unknown constant matrices are represented directly by measured data. A noise-robust semidefinite program is derived to synthesize the controller gain without model identification and without measuring the exosignal amplitudes or phases. The resulting closed-loop vector field is made exponentially contractive on a prescribed operating set, which implies the existence and uniqueness of a bounded and attracting trajectory. By combining contraction theory with Fourier-Bohr analysis, we prove that this steady-state trajectory is almost periodic, that the embedded-frequency components of the regulation error are eliminated, and that the unmodeled spectral components satisfy a Parseval-type time-averaged energy bound. Numerical and physics-based simulations on a quadrotor with a cable-suspended payload illustrate the effectiveness of the proposed data-driven internal-model design.

Large Language Model based Multi-Agent Systems (LLM-MAS) have emerged as a powerful paradigm for tackling complex tasks by breaking them into collaborative workflows of specialized LLM-powered agents. However, deploying such multi-agent workloads at scale poses significant system challenges. Each user query spawns an iterative pipeline of LLM calls, greatly amplifying resource consumption compared to single-turn queries. In resource-constrained cloud settings, these workflows face non-deterministic and input-dependent costs at decode stage, heavy-tailed multi-model requirements with memory fragmentation and over-provisioning, and cross-cluster scheduling trade-offs. We present Maestro, a workload-aware scheduling system designed for LLM-MAS serving under strict GPU budgets. Maestro explicitly leverages agent semantics and roles: it predicts the output length and memory usage of each stage and uses this prediction to drive a hierarchical scheduler. At the node level, Maestro enables dynamic multi-model co-location via hierarchical weight caching and elastic memory provisioning. At the cluster level, it performs latency-aware routing to avoid cold-start delays and memory overloads. At the global level, it enforces workflow-aware prioritization to minimize head-of-line blocking for interactive tasks. Across prototype experiments and trace-driven simulations, Maestro reduces KV-reservation HBM by 67.2% and improves high-contention SLO attainment over EDF by 23.6 percentage points.

Does the letter-grade evaluation system, while achieving its burden-reduction goals, affect the education system's stable understanding of students' academic structures? This paper introduces the concept of "data aphasia," referring to restrictions on diagnostic information expression caused by institutionally mandated forms of data presentation. Using data from 68 mathematics examinations administered to 75 primary school students, we employ an institutional counterfactual simulation method to convert percentage scores into A/B/C/D letter grades and conduct systematic tests at the information, structural, and diagnostic levels. Results show that information entropy decreases by approximately 69% after grade conversion; under the full sample, the letter-grade system appears superficially stable (K=4), but removing a single extreme anchor student causes the optimal K to increase from 4 to 8 and individual diagnostic identity consistency to fall from 95% to 62%; temporal consistency fluctuates between 52% and 96%, far below the 93%-96% baseline of the percentage system. Mechanism analysis indicates that discretization compresses the feature space by approximately nineteenfold across 68 examinations; after standardization, it creates extensive pseudo-heterogeneity regions, flattens density gradients, and makes clustering boundaries highly sensitive to minor perturbations. Based on these findings, this paper proposes a dual-track evaluation mechanism and provides a testable analytical framework for understanding the cognitive costs of educational evaluation reform.

A process is able to execute a set of actions with a predefined manner, while a truly concurrent process executes this set of actions with a manner with the flavour of true concurrency. The so-called truly concurrent process algebras bridge the true concurrency (such as Petri nets, event structures, etc), and the interleaving concurrency (such as CCS, CSP, ACP, etc). In this paper, we give truly concurrent processes testing semantics followed by Hennessy's great work, which inherits the trinity of operational semantics, axiomatic semantics and denotational semantics.

Bitcoin's Lightning Network (LN) can be exploited as a covert, low-cost command-and-control (C&C) channel for botnets, as demonstrated by the LNBot and D-LNBot designs. However, both remain proof-of-concept prototypes evaluated only through simulation, leaving key questions about real-world topology formation, propagation complexity, and resilience to takedowns unanswered. We present LNTest, the first reusable testbed for LN-based botnets, built from Core Lightning nodes containerized with Docker over a shared Bitcoin Core regtest chain. LNTest supports three overlay topology modes (a deterministic chain, autonomous peer discovery, and user-supplied graphs), enabling controlled experiments across different botnet structures. Using LNTest, we report three main findings. First, D-LNBot's autonomous formation protocol does not produce the uniform chain from its design; instead, it creates a clustered chain in which cliques are linked by bridge nodes whose removal fragments the network. Second, command propagation scales linearly with botnet size ($Θ(n)$), not the $O(m \log n)$ previously claimed, and gains nothing from higher neighbor connectivity. Third, the overlay topology determines the effectiveness of takedown strategies: uniform-degree chains resist targeted removal but fragment under random failure, scale-free topologies show the opposite pattern, and the autonomous clustered chain is fragile under both, making it the most vulnerable of the three. LNTest is released as open source, with a script that reproduces all our experiments, to support reproducible research on LN-based botnet defenses.

Mixed categorical-continuous optimization arises in many practical domains, yet remains challenging. In the black-box setting, evolution strategy-based approaches have shown promise in extending the efficiency and robustness of the CMA-ES to mixed-variable spaces. However, these methods exhibit worsened performance when strong categorical-continuous interactions are present, as their underlying search distributions assume independence between categorical and continuous variables. To address this limitation, we propose a bilevel optimization framework that explicitly captures such interactions by optimizing over categorical variables in an outer loop, and over continuous variables conditioned on each categorical configuration in an inner loop. We formulate each level of the bilevel problem as a stochastic relaxation under information-geometric optimization. To mitigate the high computational cost inherent to bilevel optimization, we introduce a warm-starting strategy that accelerates the lower-level search by selecting the best among multiple cached configurations and updating the cache after each iteration. Experimental results on binary-continuous domain demonstrate that the proposed method outperforms existing state-of-the-art approaches in interaction-handling capability while also being more computationally efficient across benchmarks encompassing both previously reported and newly proposed types of interaction.

Vehicle bunching is a major problem for transit operators. When vehicles bunch together, the lead vehicle will service the majority of passenger demand, leaving the following vehicles to operate below capacity, wasting fuel and money. Furthermore, after the last vehicle in the bunch passes, the time before the next vehicle's arrival (headway) will be large. Transit operators can combat bunching by holding buses at stops along a route, trading riding time for even headway times. While prior work has focused on developing holding policies to minimize average case bunching, no work has focused on analyzing the longest and shortest possible headway times under a broad group of such policies. We assume that dwell times at stops and travel times between stops are bounded and develop a dynamic program that computes the maximum and minimum headway times for a single bus route with an arbitrary number of control points, vehicles, and holding policies. These bounds are tight in the sense that it is always possible to identify the specific sequence of events that lead to their occurrence. We use these bounds to investigate the effects of different holding policies, stop placement, and number of vehicles on route headways and worst-case bunching. Finally, we apply these analysis techniques to a real-world transit system in Nashville, TN and show their utility for transit planning.

Wave propagation based on the spectral element method (SEM) is a representative HPC workload, but existing SEM implementations are not well matched to emerging ARM multicore CPUs with Scalable Matrix Extension (SME). We present an SME-enabled optimization of \textsc{SPECFEM3D} on the emerging LX2 processor that combines an SME-aware batched small-matrix kernel for SEM tensor-product operators, a memory-aware hybrid MPI+OpenMP execution scheme for limited-HBM systems, and a dispersion-based iso-accuracy study of the $(h,p)$ tradeoff. At fixed polynomial order, the optimized implementation improves full-application performance by 4--6$\times$ over the original code and delivers clear gains over optimized non-SME CPU baselines. Beyond these implementation-level gains, our results suggest that SME shifts the performance-favorable operating point toward higher polynomial orders along the dispersion-based iso-accuracy frontier, further reducing time-to-solution and working-set size. These results indicate that SME affects not only kernel efficiency, but also the practical discretization tradeoff for SEM on modern ARM multicore platforms.

The simultaneous solution of switched differential-algebraic equations (DAEs) in power system transient simulation may suffer convergence loss following discontinuous events. This difficulty is typically interpreted as a poor post-event initialization problem. This letter presents a geometric framework that explains the underlying convergence mechanism and clarifies why standard convergence-restoration methods may fail at discontinuities. Based on this interpretation, a homotopy-continuation based globalized re-initialization scheme is developed to restore convergence. The proposed method is validated through numerical simulations of representative discontinuities in power system transient simulation. Results show that in the cases where direct post-event solution fails, the proposed scheme can reliably recover convergence.

This study presents AiAWE, an open-source automated writing evaluation system that scores argumentative essays using a LoRA-adapted instruction-tuned large language model (Gemma-3-27B-it). Using a proprietary Educational Testing Service (ETS) dataset of 480 TOEFL Independent Writing essays, we fine-tune Gemma-3-27B and LLaMA-3.3-70B under identical LoRA configurations on a 120-essay training subset and evaluate on the remaining 360 essays under identical inference quantization. The fine-tuned Gemma model achieves a root mean square error of 0.474, a quadratic weighted kappa of 0.828, and an agreement rate of 90.56% within +/- 0.5 of the human score, outperforming both the larger LLaMA-3.3-70B model and the fine-tuned GPT-3.5 baseline reported in prior work on the same dataset. Three findings are of broader interest: open-weight LLMs can match or exceed proprietary fine-tuning for rubric-aligned scoring; model scale is not a reliable predictor of downstream performance under LoRA adaptation; and identical LoRA hyperparameters produce qualitatively different adaptation behaviors across architectures. The production system runs on a consumer-grade server and is publicly accessible at https://app.awade.gec.waseda.ac.jp. LoRA adapters, application code, and fine-tuning YAMLs are publicly available through their respective repositories.

Floating solar photovoltaic (FSPV) systems provide a land-efficient pathway to expand clean electricity access in energy-poor regions. South America has among the highest global FSPV potential (approx 38.26 TWh per million acres of water surface), yet deployment remains limited. This study presents a techno-socio-economic framework to assess FSPV for energy access, water security, and grid flexibility, with case studies in Nicaragua, Honduras, and Guyana. Estimated yields for 50 to 398 MW systems exceed 1,500 to 2,000 kWh per kW annually with capacity factors above 20 percent. At El Cajon, FSPV could significantly reduce emissions relative to fossil generation. Results show competitive costs with land-based PV when accounting for avoided land use, shared hydropower infrastructure, and water benefits. The framework also highlights co-location with hydropower and AI data centers, offering a scalable model for deployment in underserved regions.

Accurate identification of IoT devices is important for security management and policy enforcement. Existing approaches typically learn device signatures from packets or flow records. These methods operate on low-level communication observations whose traffic patterns may vary across deployments, software versions, and user interactions. This paper studies device identification using Manufacturer Usage Description (MUD) profiles. MUD profiles describe device behavior using Access Control Entries (ACEs), where each ACE represents a behavioral primitive consisting of protocol, endpoint, direction, and port semantics derived from device communication policy. Our contributions are threefold. First, using 28 publicly available MUD profiles containing 1,023 ACE instances, we construct ACE-level semantic representations from compact behavioral text and analyze their geometric properties. ACE-level representations preserve device-level behavioral distinctions more effectively than whole-profile embeddings and remain effective after whitening calibration. Second, we evaluate semantic ACE matching under controlled runtime variations, including unseen ACEs, drifted hostnames, and partial runtime observation. Exact ACE matching performs well when the overlap with the canonical MUD profile remains high, but degrades sharply when the overlap becomes sparse or disappears. In contrast, semantic ACE matching preserves useful identification evidence across these conditions. Third, we evaluate the same approach on real IoT traffic traces comprising more than 800,000 observed flows. Exact overlap remains the strongest signal when stable overlap exists, while semantic ACE matching provides stronger identification evidence during the early stages of observation, frequently retains the correct device among the highest-ranked candidates, and remains effective under sparse-overlap runtime traffic.

As the EU Carbon Border Adjustment Mechanism (CBAM) approaches, the global semiconductor value chain faces growing structural tensions between regulatory transparency and data sovereignty. This article proposes a RegTech reference architecture using the International Data Spaces (IDSA) framework to orchestrate trustworthy environmental telemetry across the semiconductor-petrochemical nexus. The framework distinguishes the mandatory CBAM requirements from voluntary Science Based Targets initiative (SBTi) frameworks, while addressing the additive complexities of the Safe-and-Sustainable-by-Design (SSbD) framework. Moving beyond standard linear technology stacks, we introduce a prospective roadmapping methodology that transforms upstream physical vulnerabilities into circular, negative feedback loops. Focusing on the Taipei and Penang technology corridor, the article details how sovereign data exchange enables Digital Product Passports (DPPs) to drive Global Business Services (GBSs) capability demands. Finally, we discuss the integration of Agentic AI for autonomous compliance and FinTech green financing, providing a scalable blueprint for global industrial clusters to achieve sovereign, sustainable, and transparent value chains.

Global Business Services (GBS) have emerged as a "living laboratory" for the Twin Transition of Green and Digital Transformation, as multinational corporations (MNCs) face increasing pressure to harmonize digital efficiency with environmental stewardship. Aiming to derive a socio-technical framework, this paper synthesizes Technology Roadmapping (TRM) with the International Telecommunication Union (ITU) ICT-centric innovation ecosystem toolkit. A bibliometric analysis of research clusters reveals an evolutionary shift from basic process automation toward "Sustainable Intelligence," identifying the GBS unit as a central "operational airlock" that mediates between landscape pressures -- such as the EU's dual mandate and Carbon Border Adjustment Mechanisms -- and niche innovations in AI-native workflows. The study further maps these clusters onto a stakeholder engagement canvas, highlighting how resilient "Middle Power" hubs in Poland, Portugal, and Malaysia are bypassing the middle-income trap to provide a "third way" for global value chains amidst a bifurcated geopolitical cloud. The results offer a data-driven design approach for leaders and entrepreneurial support networks to orchestrate talent and supply chain flows, thereby enriching the conceptual understanding of Industry 5.0 and the role of GBS as a primary mechanism for navigating a volatile, multipolar digital economy.

The group no-show paradox (GNSP) occurs when a group of agents abstaining from voting can make the new winner more preferred to them. Previous work has suggested that even for voting rules susceptible to this paradox, it is a rare occurrence in real elections and under various assumptions. However, we find that under one-dimensional preference models such as 1D-Euclidean, single-peaked, or single-crossing preferences, Single Transferable Vote (STV), a popular runoff rule, is highly vulnerable to GNSP. This is in stark contrast to Condorcet rules, another family of rules susceptible to GNSP, where the paradox cannot occur under these one-dimensional preferences. We theoretically identify tractable and prevalent sufficient conditions for GNSP to occur for STV under one-dimensional preference models. Through our theoretical results and experiments with synthetic preference profiles from these domains, we demonstrate that voters at the extremes of the 1D spectrum are particularly likely to cause GNSP by abstaining. Furthermore, the likelihood of occurrence increases substantially as the number of alternatives grows.

We propose an abstraction-free framework for controller synthesis for continuous-time dynamical systems subject to Linear Temporal Logic (LTL) specifications and bounded control inputs. The proposed method combines the sequential decomposition of LTL tasks with the use of formally certified Control Lyapunov-Barrier Functions (CLBFs). By formulating local specifications as a sequence of safe-stabilization problems, we systematically approximate and patch the winning sets of the decomposed subtasks. The satisfaction of these local constraints is guaranteed by the offline-computed level sets of the CLBFs. As a result, our framework yields formally verified switching feedback controllers that enable efficient online planning and dynamic re-planning. This ensures robust continuous specification satisfaction in the presence of state perturbations, avoiding the explicit state-space abstractions commonly required in the literature. The approach is validated through numerical simulations and a hardware demonstration on a Crazyflie quadrotor.

The transition of scientific applications to GPU-accelerated exascale systems is constrained by trade-offs between performance, portability, and productivity. This work evaluates the performance portability of directive-based GPU programming by porting gPLUTO, a production-grade magnetohydrodynamics code for astrophysical simulations, from OpenACC to OpenMP, and analyzing its performance on NVIDIA A100 (Leonardo Booster) and AMD MI250X (LUMI-G) devices. On NVIDIA platforms, OpenACC and OpenMP achieve comparable performance due to a shared compiler backend, providing a consistent baseline for assessing algorithmic efficiency. In contrast, the same OpenMP implementation is approximately three times slower at the application level on AMD MI250X with respect to the NVIDIA A100 OpenACC baseline, with kernel-level slowdowns reaching up to an order of magnitude, driven by sensitivity to strided memory-access patterns and compiler limitations. Kernel-level profiling shows that the dominant contributors to run-time are memory-latency-bound rather than limited by peak band-width. In low-parallelism kernels, C++ abstraction layers increase register pressure and spilling, leading to extreme slowdowns of up to 47x in specific cases. These results indicate that portable performance across GPU architectures requires not only application-level changes but also continued advances in compiler backends and architecture-aware optimization strategies

Many visualization designs feature phenomena referred to as ``visual multiplexing'', where multiple pieces of information associated with the same data point are conveyed simultaneously. Although visualization designers are able to bring such phenomena, often unconsciously, into their designs, the design space of visual multiplexing is huge, and it is uncommon to explore visual multiplexing systematically as design patterns. In this paper, we propose a design method for exploring a smaller design space constrained by an application. As an illustrative case study, we focus on machine learning (ML) workflows for developing ML models that approximate partial differential equations (PDEs). In these workflows, ML researchers need to analyze the inter-relationships among multiple 2D scalar fields frequently. Since superimposing one heatmap on top of another is not an effective design, we formulate three design steps to explore the design space of visual multiplexing in the context of multiple 2D scalar fields. Our design method also includes a pre-design step for domain grounding and theoretical analysis, and involves domain experts in both co-design and evaluation activities. The design process enables us to identify relatively optimal default multiplexing designs as well as the need for small variations that domain experts can control through a user interface.

Thermoplastic composite structures enable lightweight, recyclable, and high-throughput aerospace manufacturing, but reliable quality assurance of advanced joining processes remains a key challenge. This work presents a compact, low-cost, and wireless ultrasonic non-destructive testing system for real-time, inline monitoring of continuous ultrasonic welding of thermoplastic carbon fiber composites. The system integrates custom-fabricated polymer-based capacitive micromachined ultrasonic transducers (polyCMUTs) with the ultra-low-power WULPUS platform, enabling operation in the harsh, high-interference welding environment. An eight-element linear polyCMUT array operating at a center frequency of approximately 3.6 MHz is designed, fabricated, packaged, and integrated into an industrial welding setup. Inline measurements are performed during welding of carbon fiber laminates with intentionally introduced defects. Process-synchronous ultrasonic data reveal consistent depth-of-echo shifts at defect locations, in strong agreement with X-ray computed tomography ground truth. Across 21 welds, all induced defects are detected without false negatives and with limited false positives. The results demonstrate that polymer-based CMUT technology enables robust, scalable, and manufacturing-compatible ultrasonic sensing, representing a decisive step toward intelligent process monitoring and quality assurance for next-generation thermoplastic composite welding.

We propose a randomized local-improvement algorithm for the Maximum Weighted Matching (MWM) problem. Our method introduces a softmax-based biased sampling mechanism that achieves local $\varepsilon$-dominance and yields an expected $\frac{1}{2}-\varepsilon$ approximation ratio. We prove convergence guarantees and show that the algorithm runs in $O\!\left(m\log(1/\varepsilon)/p_{\min}\right)$ time, where $p_{\min}$ is the minimum softmax proposal probability over all edges; under mild conditions on the bias parameter and weight range, this simplifies to $O(m\log(1/\varepsilon))$. The framework provides a tunable tradeoff between convergence speed and approximation quality.

Every finite family of compact convex bodies in Euclidean space induces an apartness relation between disjoint index sets: two sets are apart when the convex hulls of the corresponding unions are disjoint. This paper studies the finite theory obtained by taking apartness as the primitive relation. Its basic laws are symmetry, bilateral subsumption, and vacuity, equivalently the separation-polarity form of acyclic separoids. The main contribution is an effective rational realization theorem with uniform margins and the exact consequence theory it supports. Every finite apartness separoid is realized by rational polytopes whose coordinates are indexed by maximal separations. Maximal separations and minimal Radon partitions can be enumerated from a full table, generators, or a membership oracle; the coordinate values have controlled bit height; and each coordinate records a readable certificate of one maximal separation. The realization separates every apart pair with clearance at least 2, remains correct under outer parallel enlargement by any radius below 1, and yields full-dimensional convex bodies after thickening. The distance-function layer records standard convex-analytic stability through Lipschitz comparison, monotonicity under inclusion, and outer parallel bodies. On the logical side, positive entailment is exactly one-premise subsumption. Boolean consequence over Euclidean scenes is sound, complete, and decidable; satisfiability is NP-complete, validity is coNP-complete, and positive entailment is linear for sorted encodings. A stratification theorem shows that Boolean reasoning introduces no new atomic apartness beyond separoid closure. Fixed-dimensional consequence relations form a strictly decreasing hierarchy that stabilizes in dimension n minus 1 for n sites.

The solid electrolyte interphase (SEI) - a critical passivation layer that governs the longevity, safety, and efficiency of lithium-ion batteries - is created during the last step in cell manufacturing called cell formation. Conventional cell formation protocols are largely empirical, resulting in long processing times and limited control over the SEI growth rate that influences SEI quality and lifetime performance. This paper develops a control-oriented, semi-empirical model to estimate SEI thickness growth from terminal voltage and cell expansion measurements acquired in-operando during manufacturing using low-cost micrometer-precision integrated-sensing fixture. Model parameters are calibrated against cell formation data, and an unscented Kalman filter is employed to estimate the SEI film growth. The results lay the foundation for future closed-loop control of SEI growth, enabling high-quality and more efficient formation processes.

The low-level GPU programming models (CUDA, HIP, OpenCL, etc.) provide detailed control of the data flow and execution plan of a program in order to extract close-to-metal performance. However, these have a steep learning curve due to the intricacies of their syntax and semantics. This reduces programmer productivity. On the other hand, high-level models (OpenMP, OpenACC, etc.) that serve as abstractions over the low-level models are aimed at improving programmer productivity but achieving performance on-par with the low-level models is a challenge. There are inherent trade-offs between productivity, portability and performance in both approaches and there is no one-size-fits-all solution which achieves all three simultaneously. However, we believe there is room to improve programmer productivity without sacrificing performance and portability by reusing optimization patterns specific to a given domain. To this end, we propose nomp: a framework for building domain specific compilers. nomp consists of a pragma based programming model and a runtime capable of code transformation and generation based on user provided metadata.

Data journalists routinely integrate records across multiple independently published sources to support accountability reporting, yet no existing interactive wrangling tool treats the collection of tables -- rather than the single table -- as its primary unit of work. We present OpenRoundup, an open-source, browser-based system that enables data journalists to consolidate multiple tables into a single analysis-ready output without writing code. The interface comprises five coordinated panels that implement a schema-first, values-on-demand paradigm with live schema previews, ambient data quality alerts, and a recursive treemap visualization of the evolving operation tree. A client-only architecture powered by DuckDB-WASM runs in the browser, providing strong data privacy guarantees suited to sensitive journalism data. The system introduces two conceptual contributions: eager table consolidation, in which a composite table is assembled early in the wrangling phase via interactive, incremental assembly of multiple source tables; and a declarative vocabulary for table consolidation consisting of two operations, Stack and Pack. We evaluate the system through a replication study in which the authors reproduce 17 published journalist programming workflows using only the interface, and a deployment study with four professional data journalists. The replication study demonstrates expressive coverage of real-world consolidation tasks. The deployment study confirms utility for practitioners who understand joins conceptually but lack the programming skills to execute them, and surfaces an unanticipated secondary value for data journalism education.

As distributed AI workloads grow in scale, multi-GPU systems have become essential for training large models. Although techniques like kernel fusion and overlapping communication with computation help reduce delays, they also introduce irregular and transient traffic patterns that are difficult to model using existing tools. These techniques rely heavily on fine-grained synchronization and peer-to-peer communication, which place significant pressure on interconnect bandwidth and latency. In this work, we introduce Eidola, a scalable extension to the gem5 simulation framework that enables detailed modeling of inter-GPU communication traffic. The extension is scalable as our GPU model serves as a succinct eidolon, emulating the minimal characteristics needed for traffic modeling. Eidola uses annotated timing profiles from real applications to emulate peer-to-peer GPU writes with cycle-level precision. This allows researchers to simulate and analyze synchronization behavior across large multi-GPU configurations. The simulator supports configurable per-GPU traffic patterns and enables isolated performance analysis under different communication scenarios. We demonstrate Eidola's effectiveness by reproducing variability in fused kernel execution and by implementing a SyncMon-inspired synchronization mechanism, confirming reductions in polling-related memory traffic. Our results show that Eidola provides a flexible and scalable platform for studying inter-GPU communication and supports architectural exploration in modern distributed GPU systems.

Razborov and Rudich (JCSS'97) observed that all known lower-bound proofs follow a certain pattern: when showing that a function $F$ is hard, along the way the proof provides us with a distinguisher, namely, an efficient algorithm which can distinguish easy functions from random functions. They called such lower-bound proofs natural proofs. They then showed a natural-proofs barrier: under standard cryptographic assumptions, natural proofs cannot show superpolynomial lower-bounds against Boolean circuits. Along similar lines it can be shown that under a suitable cryptographic assumption, natural proofs cannot significantly improve the current state-of-the-art lower bound against constant depth circuits (AC0). The state of the art, using Håstad's Switching Lemma (SL), is $2^{n^{1/(d-1)}}$ for depth-$d$ circuits, and (conditionally) no natural proof can prove lower bounds of $2^{n^{c/d}}$ for some large constant $c$. In this paper we revisit the natural-proofs barrier from an $\textit{unconditional}$ perspective. We focus on AC0-natural proofs, i.e. proofs whose distinguishers are computable by AC0 circuits. Razborov and Rudich observed that lower bounds based on SL are AC0-natural. We show that this is true for most known lower-bound techniques against constant-depth circuits. We then establish an unconditional barrier for such proofs. By localizing the Trevisan--Xue pseudorandom generator, we are able to show that no AC0-natural proof can prove a lower bound greater than $2^{n^{7/(d-5)}}$ against depth-$d$ circuits. This is in the same quantitative regime as the SL frontier which instead has $1/(d-1)$ in the power of $n$. The proof has a striking self-referential aspect: the proof of security of the Trevisan--Xue generator crucially relies on SL, and so SL has been used to show that AC0-natural proofs, such as SL itself, cannot prove AC0 lower bounds better than that of SL.

The Internet of Things (IoT) is experiencing rapid growth. Smart devices are emerging in smart homes and industrial applications, performing mission-critical tasks. Bugs in IoT software can lead to severe consequences. For example, a buggy smart lock can allow unauthorized access to a private property. Testing is a primary practice to expose software bugs and ensure software quality. However, little is known about how IoT software is tested. To bridge this gap, we conducted the first empirical study on test cases in open-source IoT software. Specifically, we evaluated the effectiveness of test cases in IoT software, explored the challenges inherent in testing IoT software, and analyzed the usage of mock objects. Our results indicate that while IoT software often contains a considerable number of tests, their effectiveness remains limited. We identified the primary challenges in testing IoT software as managing complex interactions with various external dependencies, such as other network-reliant IoT components, file systems, operating systems, and databases. We also observed that the use of mock objects in IoT software closely aligns with our identified testing challenges. This alignment demonstrates the potential of mocking as a solution to enhance test coverage and address the complexities of IoT software testing.

Vision-Language Agentic Systems (VLAS) connect visual perception to planning, tool use, and physical actions. This means backdoor-type triggers can propagate through both decision pipelines and their connected interfaces, thus making visual backdoors a system-level threat. Current evaluations on such backdoors focus on clean accuracy and attack success rate (ASR), metrics that capture whether a trigger works, but not whether an attack is actually "precise" -- i.e. whether it triggers hidden behaviors only when intended. In this work, we formalize the failure of trigger precision as "trigger leakage": inputs that are visually or semantically close to the intended trigger and therefore inadvertently activate the attacker-specified behavior. To quantify this leakage, we introduce Neighbor Leakage Rate (NLR). Our experiments show that at a 3% poisoning ratio, icon and text triggers remain robust to common visual transformations, but their neighboring variants leak heavily, with NLR reaching 0.996 (icon) and 0.944 (text). Using textual triggers as a controlled probe, we show that standard fine-tuning learns a broad activation region rather than an exact trigger condition, causing neighboring strings to invoke the malicious behavior even when the exact trigger is absent. Adding edit-distance-one hard-negative samples during training substantially narrows this activation region and reduces leakage, including in image-editing and embodied-manipulation workflows, where leaked triggers can propagate into executable programs and action sequences.

We introduce TTS, a dependent type theory in which semantic composition is represented by horn filling and distinctions between possible completions are witnessed relative to explicit measurement regimes. TTS replaces globally canonical composition with regime-indexed indiscernibility and constructive apartness, allowing filler spaces to be classified as canonical when all completions are observationally connected and forked when two warranted completions are positively separated. Separation witnesses enter the calculus only through measurement contexts recording actual instrument outputs, yielding conservativity, provenance, and a no-fork-from-the-empty-record result. We prove that forks persist under refinement while canonicity may fail, and characterize exactly when an identification made by one regime can consistently coexist with a separation made by another. This framework supports a geometric account of Fregean sense as a choice of filler, reference as the boundary constraining that choice, and hyperintensional difference as measured apartness, while providing a falsifiable bridge to stratified representation spaces and branching behaviour in language-model generation.