The Internet Quality Barometer (IQB) framework was designed to transform raw Internet measurement data into actionable insights about Internet quality. Specifically, the framework maps raw speed test measurements to network requirements (e.g., throughput, latency), maps these requirements to representative Internet use cases (such as video streaming or web browsing), and finally aggregates performance across use cases into a single IQB score. The IQB score is a composite index ranging from 0 to 1, intended to capture overall Internet quality in a way that is both interpretable and comparable across locations. We implemented the IQB framework in practice by developing an open-source IQB library and a prototype web application. These tools enabled us to compute IQB scores at scale, including global estimates aggregated at the level of countries, regions, and cities. In this report we conduct a preliminary sensitivity analysis of the IQB framework, investigating how different parameter choices affect the resulting IQB scores, identifying which parameters the framework is most sensitive to, and highlighting cases that may lead to outliers or potentially misleading results.

Distributed Software-Defined Networking (SDN) clusters replicate flow state asynchronously between a master node and its backups, leaving a window during which two backup nodes can each commit a contradictory rule, the master can serialize both into the data plane, and the kernel datapath can latch onto an action that no node believes authoritative. Existing SDN fuzzers miss this fault: they confine their oracle to the control plane, target a single controller, or do not steer concurrency to provoke replication races. We present GapFuzz, a stateful concurrency fuzzer for distributed SDN clusters. GapFuzz injects pairs of contradictory Northbound requests on two non-master nodes with controlled inter-injection delay $Δt$, and reconstructs the global cross-plane state by querying every replica and the kernel-datapath action through ovs-appctl ofproto/trace. A two-phase timing search detects whether a divergence exists, then doubles and bisects on $Δt$ to bound the injection-time window; a lifetime probe labels each verdict transient or persistent and assigns it to one of four cross-plane state classes derived from the ONOS 2.7 source. On a three-node ONOS 2.7 cluster, GapFuzz produces a divergent verdict in 81.7% of attempts ($N=50$, Wilson 95% CI $[77.3, 85.4]$%); every divergence sits between the cluster's authoritative state and the kernel datapath. Phase 2 separates a 5 ms race window for one template from a doubling-cap regime ($Δt_{\max}=10.24$ s) for six others, and 99.4% of divergences persist past 30 s. Replacing the kernel-datapath probe with the OpenFlow user-space probe used by prior fuzzers drops detection by 26.6 percentage points overall and by 46.5 points after excluding canonicalization-forced verdicts.

Advanced AI systems for code analysis, binary analysis, fuzzing orchestration, and penetration-test planningmay significantly increase the rate at which latent vulnerabilities are discovered. While improved discovery can benefit defenders, it can also overload remediation pipelines and accelerate adversarial weaponization. This paper develops a queueing and network-theoretic model of AI-accelerated vulnerability discovery in interconnected systems. We represent an enterprise as a weighted dependency graph with replenishing vulnerability pools, finite remediation capacity, triage degradation, exploit window compression, and dynamic compromise propagation. We derive stability conditions for vulnerability backlogs, formulate a dynamic coupling between unresolved backlog and cascade risk, and evaluate mitigation strategies through simulation. Results indicate that when actionable discovery arrivals exceed remediation throughput, backlogs grow rapidly and systemic risk increases nonlinearly. In hub-dominated topologies, segmentation can reduce propagated compromise more effectively than remediation speed alone, while the strongest defense combines remediation automation with reduced network coupling.

In this paper, we present a companion app for an autonomous vehicle aimed at user groups who would normally require an accompanying person to drive them. Two aspects of a companion app are presented in this paper: First, the possibility for a trusted person to track the ride of the person in need of support and second, to put the settings of the vehicle for persons in need of support in the hands of a trusted person. In addition, this article describes the requirements and addressed values and discusses the safety-relevant aspects of such a companion app. We also discuss and identify the values that influence passengers and trusted persons using the companion app. Overall, a companion app can provide new perspectives and opportunities for people in need of support, allowing them to take advantage of the features offered by autonomous vehicles. It enables trusted individuals to configure the vehicle according to the passengers needs. Also such an app can be a mechanism to involve trusted persons in the options given by the vehicle and give them the possibility to adapt the vehicle to the needs of the person in need of support.

This paper develops a cyclic labelled proof-theoretic framework for process logic -- an extension of dynamic logic in which formulas specify properties of execution traces rather than only final states. The main difficulty is that first-order process logic must reason about concrete computations while preserving temporal information along regular-program traces. Existing compositional calculi cover important fragments, but do not provide a complete treatment of full first-order process logic over regular programs. We address this difficulty by enriching process-logic formulas with labels that explicitly record trace and update information during derivations. Based on this construction, we define cyclic labelled proof systems for propositional and first-order process logic, respectively denoted by G3PPL and G3FOPL. We prove the soundness by using the cyclic conditions to obtain an infinite descent in a well-founded multiset ordering, and prove the completeness by showing that the labelled systems can derive the established proof rules of process logic and first-order dynamic logic. The result is a uniform framework for process logic in which for the first time, trace-based program properties and first-order computations can be handled within the same proof structure.

This contribution follows a four-year investigation (2022--2026) into the political economy of graphics card miniaturization. It begins from the premise that rethinking our relationship to artificial intelligence and its sociotechnical entanglements requires demystifying and opening the black box of this technical object. Within our algorithmic culture, the graphics card (GPU) enables the massive, parallel processing of large datasets, making possible the training of the models that underpin our intelligent systems. GPU miniaturization is equally crucial: as a key driver of the Internet of Things, this sociotechnical phenomenon enables the inclusion of these cards in increasingly compact and powerful systems while also enabling better management of energy resources. The development of these everyday objects and technologies nevertheless reinforces several major problems. Drawing on both the social sciences and the critical, reflexive, speculative, and fictional methodologies of research-creation, the author developed several investigative fieldwork sites -- among liquid nitrogen overclockers in Taiwan and urban miners in Ghana -- and conducted situated experimentations on some fifty acquired graphics cards. Structured around three themes (dismantle and dissolve, rebuild, remix), this paper demonstrates how research-creation methods constitute full epistemologies for apprehending what seems a priori external, opaque, or inaccessible, and for restoring artificial intelligence to its tangible materialities. In doing so, it contributes to the field of ICT for sustainability by affirming research-creation as a rigorous means of disentangling the material and environmental infrastructures that computational systems both depend on and obscure.

Deciding whether a graph has k-edge-disjoint spanning trees is a well-studied problem. We consider the problem of enumerating all sets of spanning trees with polynomial delay. This work is based on the alternate proof of Tutte and Nash-Williams' characterization of graphs with k edge-disjoint spanning trees by Kaiser [1]. The idea is to maintain a decision tree for all forest-packs and perform a Depth-First Search over it. We build this decision tree inductively by computing each node's children using a variant of Kaiser's technique [1].

AI-powered code generation systems have transformed software development but introduce critical inference-time security vulnerabilities. This research presents a systematic investigation of context-based adversarial attacks, where strategically crafted contextual inputs, including comments, documentation, variable names, bias large language models toward generating exploitable code. Through 2,800 controlled experiments across CodeT5+, CodeLlama, GPT-3.5-Turbo, and GPT-4, we quantify attack effectiveness and defense mechanisms. Results demonstrate that adversarial conditions increase vulnerability generation 10.7x (from 3.5% to 37.4%), with direct instruction attacks achieving 100% success on GPT-3.5-Turbo. Cross-model transferability reaches 60-100%, indicating systemic architectural vulnerabilities rather than model-specific flaws. Our dual-layer defense framework achieves 89.1% detection rate with 0.3% false positives and 520ms latency, demonstrating practical feasibility for real-time deployment in development environments.

In the bi-infinite Post Correspondence Problem ($\Z$PCP), it is asked whether the same bi-infinite word can be constructed correspondingly from a given finite set of pairs of words. In this article, we study its complexity with respect to the arithmetical hierarchy and prove that it is in $\Si^0_2 \setminus (Π^0_1 \cup \Si^0_1)$ and, therefore, at the level 2 of the arithmetical hierarchy. For the proof, we present a sequence of reductions starting from the nonhalting of the Turing machine all the way to $\Z$PCP via infinite PCP, an $s$-shift infinite PCP and $s$-shift $\Z$PCP for all natural numbers $s$. In the process, we prove that the infinite PCP is undecidable for injective morphisms, and that the infinite injective PCP, $s$-shift infinite PCP, $s$-shift $\Z$PCP and the non-termination problem for (deterministic and reversible) semi-Thue systems are all $Π^0_1$-complete.

Software vulnerability detection is increasingly important as modern applications combine multiple programming languages. This paper presents an early comparative evaluation of BERT, RoBERTa, and CodeBERT for binary vulnerability detection across HTML, Python, JavaScript, and PHP using the CVEFixes dataset and language-wise three-fold stratified cross-validation. The results show clear performance differences across languages, indicating that multilingual vulnerability detection requires more language-aware and robust transformer-based modelling strategies.

Multi-terminal DC (MTDC) transmission systems based on modular multilevel converters (MMCs) are a key component of the envisioned future energy sector, where sustainability and efficiency are increasingly prioritized. To ensure their reliable operation, MMC currents must be regulated safely and rapidly under a wide range of uncertain operating conditions. Consequently, the design of current controllers faces a fundamental challenge: achieving fast transient response while maintaining robustness against uncertainties. This paper addresses this challenge by proposing a linear matrix inequality (LMI)-based design framework that leverages Lyapunov stability conditions to synthesize a less conservative static state-feedback controller. The proposed design method explicitly accounts for system constraints, including input saturation and overcurrent limits. The proposed method effectiveness is assessed on the CIGRE MT-HVDC benchmark, simulated in RTDS, and compared with existing methods.

This paper investigates how Conflict-free Replicated Data Types (CRDTs) can be used for dynamic software updates of distributed applications. We propose to model application updates as a new App CRDT that stores the application code associated with a semantic version, which defines a total order of the code updates. The App CRDT works with an API-compatible message delivery middleware, which allows applications to continue working with partially updated components in the face of backwards-incompatible software updates. We implemented our approach in AmbientTalk, an ambient-oriented programming language designed for distributed systems. We show how this CRDT can be integrated with existing AmbientTalk applications, requiring minimal changes. We also implemented our approach in LuAT, an ambient-oriented programming framework for Lua. This shows that our approach of using CRDTs to replicate code can be generalised to other programming languages.

When a conversational assistant recommends a brand to a user with no recent observed engagement, that user's same-name Google search rises +4.3 percentage points (pp) [3.1, 5.5], visits to the brand's own site +2.4 pp [1.4, 3.5], and brand-specific retailer-page visits +1.0 pp [0.3, 1.7] over matched backward placebos. Recovering that estimate is the work. The mention creates a brand exposure no web log attributes to the assistant, and the naive all-mention funnel that seems to measure it is confounded: many mentions are incidental references to brands the user already uses ("your Netflix download"), whose downstream visits are that existing customer's own behavior and surface as a brand-specific pre-trend. We measure off-platform response on a panel that joins opt-in clickstream to the same users' ChatGPT, Claude, and Gemini conversations, and isolate the effect with a pre-trend event study, a stance classifier, non-customer conditioning, and a within-response same-category control: incidental name-drops then move behavior far less (+1.8/+1.1/+0.3), and the named brand moves far more than unnamed same-category brands in the same response. The downstream path is mostly search-mediated and reaches both own sites and retailer pages, with a destination mix that tracks baseline brand-directed behavior rather than redirecting toward either. The design is observational and we do not observe transactions, so retail is purchase-adjacent. Standard referrer-based and last-click measurement miss this upstream exposure: assistants move observably-unengaged users into open-web brand navigation along a path attributed elsewhere.

Multimodal large language models (MLLMs) now appear in safety-critical applications, but the visual channel leaves them open to adversarial attacks that predominantly text-oriented safety alignment addresses only in part. Retraining a model for each new vulnerability class is usually too expensive to be practical. We report a comparative empirical evaluation of three inference-time defense methods and their combinations, run on eight models from the InternVL and Qwen-VL families across seven safety benchmarks that span four attack classes and total 9,000 evaluation samples. Every figure below comes from the same unified proxy classifier. Five findings emerge from the evaluation. First, within the evaluated models and benchmarks, no single defense dominates across all settings: what works depends on the model's baseline safety and on the attack type. Second, combining defenses directly drives benign-query over-refusal to 97-100% across all eight evaluated models, and SmoothVLM on its own reaches 99.2-100%. Third, a simple safety prompt keeps utility largely intact (0.0-18.2% over-refusal across all eight models, five of them below 7%, although two exceeded 15%) while still yielding moderate safety gains. Fourth, different attack classes expose different weaknesses across the evaluated setup, which is why multi-benchmark evaluation matters. Fifth, in a preliminary whitebox test on two models (n=20), text-level defenses suppressed a PGD visual attack that had succeeded without any defense: the defenses act at the output stage, where gradient optimization has limited direct leverage in the tested configuration. Read together, these results argue for adaptive defense selection rather than a single fixed defense configuration.

Heat pumps are expected to dominate the heating sector, substantially increasing peak electricity demand. At the same time, building thermal inertia enables operational strategies, providing temporal flexibility in heat pump operation and short-term demand response. However, this dynamic behavior is not yet represented in large-scale energy system optimization models. To address this gap, we present an innovative formulation of building thermal inertia. The resulting temperature variable is integrated into a novel conic temperature-aware heat pump efficiency formulation, enabling a more precise emulation of smart control strategies. In a case study of the European energy system, we show that the approach captures operational heating flexibility while remaining computationally efficient. The results indicate substantial untapped flexibility potential, enabling up to a 22% reduction in heating-related electricity costs. This potential can be realized through a suitable energy market design that incentivizes coordinated heat pump control, individually or via aggregators.

Explainability is increasingly required in AI-enabled software systems to support transparency, user trust, and compliance. Yet, explainability requirements are often written ad hoc, and unguided large language model support can yield vague, inconsistent, or incomplete statements. This paper presents a sequential, guideline-driven workflow for formulating explainability requirements and evaluates its tool-based operationalization. We first elicited candidate quality properties through a structured literature review and developer interviews. We then prioritized these properties in an online survey with practitioners (n=20) and derived a concise guideline of ten core properties with actionable formulation instructions. Next, we operationalized the guideline in a web-based tool that supports an iterative workflow of drafting, property-based checks, and revision. We evaluated the workflow in two complementary studies. In a workshop with requirements engineers (n=6), tool support reduced formulation time by 23.5% on average (Wilcoxon p=0.021). In an independent online study with software developers (n=18), tool-supported and manually written requirements received comparable ratings for implementability and formulation quality, with a descriptive slight preference tendency toward the tool-supported versions. Overall, our results suggest that combining a prioritized quality guideline with lightweight LLM support can reduce formulation effort while producing requirements that are perceived comparably to manually written ones.

As software systems increasingly rely on natural-language explanations to address user-reported explanation needs in requirements communication and support, ensuring that such explanations are consistent, relevant, and well formulated remains a major challenge. Purely automatic large language model (LLM) generation often lacks reliable grounding and controllable output quality. In this paper, we present a guideline-based formulation support tool for software explanations that combines LLM-assisted text generation with an empirically derived quality guideline. The tool structures the writing process into generation, quality checking, and iterative revision, while keeping domain control with developers. We evaluated the approach in a two-phase study consisting of an interview-based developer experiment and a controlled user survey. Six industry practitioners with software development or DevOps experience formulated explanations for real explanation needs in a human-only manual condition and in a human-with-LLM-support condition. In this small-scale evaluation, tool-supported formulation was on average 24.4% faster, although inferential analyses indicated only a trend for efficiency. In a subsequent user study with 17 participants and 204 paired comparisons, tool-supported explanations were rated significantly higher in overall satisfaction than manual explanations (p=0.003, rank-biserial correlation=0.86). Our findings suggest potential efficiency gains and higher perceived formulation quality through guideline-driven LLM assistance. Future work should examine long-term industrial use and integration into existing development workflows.

The rapid advancement of autonomous driving systems (ADS) has introduced significant challenges, particularly in the creation of realistic and complex scenarios for testing and validation. This paper introduces Modular2Simple, a tool designed to address these challenges by simplifying and enhancing the process of creating complex ADS scenarios. Modular2Simple seamlessly integrates with the CARLA simulator and is applicable to any software that supports the OpenSCENARIO format. By leveraging existing simple scenarios in the OpenSCENARIO format, the tool enables developers to create easily customizable modular scenarios through the combination of multiple simple or modular scenarios, significantly simplifying the scenario creation process while maintaining flexibility in scenario design. This approach not only facilitates the development of complex scenarios, reducing both development time and effort, but also promotes scenario reuse and customization, which leads to a significant reduction in code complexity and enhanced efficiency in scenario design and testing compared to traditional scenario development methods.

Code Language Models (CodeLMs) have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical security concerns, particularly regarding susceptibility to backdoor attacks. Recent studies have uncovered naturally occurring backdoors, referred to as natural backdoors, in normally trained deep learning models. Despite posing threats as serious as those introduced through data poisoning, security implications of natural backdoor vulnerabilities in CodeLMs remain poorly understood. In this paper, we conduct a thorough empirical study of natural backdoor vulnerabilities in CodeLMs across various model architectures and code intelligence tasks. Specifically, we examine potential natural backdoor vulnerabilities across 44 scenarios, demonstrating that natural backdoors are prevalent and intrinsic to CodeLMs. We reveal differences between injected and natural backdoor vulnerabilities at both the model and parameter levels. We then analyze the transferability of natural backdoor vulnerabilities from three perspectives: datasets, model architectures, and shared knowledge. We further investigate the causes of natural backdoors from two aspects: training datasets and the model training procedure. We evaluate existing backdoor defense techniques, including pre-training, in-training, and post-training defenses, in mitigating natural backdoors. Finally, we propose ScanNBT, a novel detection method designed to improve comprehensive detection of natural backdoor vulnerabilities in CodeLMs. We aim for our findings to enhance understanding of these vulnerabilities and provide insights for strengthening CodeLM security against backdoor threats.

Social media has become a key channel for political advertising during election campaigns. However, algorithmic biases in the delivery of these ads may distort the public's exposure to political messaging. This can hinder citizens' ability to make informed choices and undermine equal access to political discourse, raising concerns about the integrity of electoral processes. In this study, we examine gender-based discrimination in the delivery of political ads during the 2024 European Parliament elections. Using a large-scale dataset of over 110000 ads from 453 political parties and 968 candidates that generated over 7 billion impressions across 25 EU countries, we find that men were significantly more likely to be shown ads from populist and far-right parties than women -- even after accounting for ad content, platform-level competition, and targeting strategies. All else equal, ads by populist parties reach, on average, a 6 percentage point higher male share. Such imbalances restrict the ability of parties to reach diverse audiences and prevent voters from engaging equally with the full range of political viewpoints. This pattern is particularly concerning given that far-right and populist ads may reinforce political polarization and widen existing gender gaps in political engagement. Our findings underscore the need for platforms and policymakers to audit algorithmic ad delivery in political campaigns on social media and to implement safeguards that ensure fairness and protect democratic processes.

Research in XR (Extended Reality) has conventionally centred upon concepts such as Presence, Embodiment, Social Presence, and Co-presence. Within these traditions, bodily action, sensory contingencies, synchronous interaction, and possibilities for action have generally been regarded as constitutive conditions for the experience of "being there" and of being with others. XR environments, however, permit the partial separation of conditions that ordinarily co-vary in everyday experience. Bodily co-presence, temporal simultaneity, spatial configuration, and social interaction need not remain inseparable. This paper approaches this possibility as a problem of other-presentness. Other-presentness refers to the conditions under which another individual is experienced as existing "here and now". The contribution of this paper does not lie in arguing that asynchronous others can evoke social responses; such observations have already been addressed within parasocial interaction and social presence research. Rather, the novelty lies in theorising XR as a technological condition capable of separating and operationalising the constitutive elements of other-presentness as design variables. Reconsidering Bodyless Presence as a methodological precedent and drawing upon experimental findings from Immersive Video research, this paper formulates Bodyless Presentness as a condition in which another individual continues to be experienced as presently existing despite attenuated bodily co-presence and weakened real-time simultaneity.

Operator filtering allows for the regularization and compression of dense integral operators, effectively mitigating the memory and computational costs associated with iterative solvers. Previous works introduced filters that leverage the analytical spectral truncation of kernels for operators of the 2D Electric Field Integral Equation (EFIE). In this contribution, we will demonstrate how to obtain filtered kernels in a discrete numerical form within the framework of an Adaptive Integral Method (AIM), yielding results entirely comparable to analytical filters. By operating directly on the discrete operator representations, the proposed strategy ensures a native and robust compatibility with fast solver schemes that analytical formulations often lack. The effectiveness of the proposed approach will be demonstrated through numerical results, including its application to the Calderón preconditioned EFIE.

This paper investigates a viable two-echelon supply chain network design problem with unreliable facilities subject to disruptions. Unlike existing studies that consider supply chain echelons in isolation, the proposed models explicitly capture cross-echelon disruptions and quantify the value of incorporating such interdependencies. Network viability is achieved by jointly integrating resilience (via backup reassignment), agility (via mobile facilities), and environmental impact (via emissions caps) to ensure demand satisfaction across both echelons and support long-term network survival. Two mixed-integer programming formulations are developed: a scenario-based formulation and an implicit formulation, both minimizing expected fixed and service costs. To handle probabilistic service requirements, the implicit formulation incorporates a machine learning-enhanced chance-constrained programming approach, in which intractable capacity chance constraints are replaced by learned linear cuts enforcing a 95% service confidence level. These cuts are trained using several classification methods, including logistic regression, L1-regularized logistic regression, stochastic gradient descent, the perceptron algorithm, and logistic regression with a regularization parameter of 0.1, with the best-performing classifier selected as a surrogate. To further enhance scalability, two fix-and-relax heuristics are developed for the implicit formulation, while a sample average approximation (SAA) method is applied to the scenario-based formulation. Computational experiments demonstrate that the implicit formulation offers a computationally efficient and high-quality alternative to the scenario-based formulation. Moreover, the proposed heuristics and SAA approach effectively address medium- and large-scale instances, delivering high-quality solutions within acceptable computational times.

The ability to take advantage of computationally efficient high-order finite element methods to perform adaptive finite element analysis of complex engineering problems over general 3D domains requires the ability to adapt meshes with curved elements that maintain the level of geometric approximation of the domain boundary required. This paper presents a conforming curved mesh adaptation procedure aimed at effectively supporting automated adaptive analysis of problems for which the domain geometry is defined in a CAD system. The local mesh modification procedures interact with the CAD geometry to curve the mesh edges and faces representing those boundaries to the order of approximation of the high-order elements being used. The curved mesh edges and faces representing the domain boundaries are based on Bézier approximation geometry, which provides more accurate evaluations of surface-related quantities of interest than the commonly used interpolation methods. To attain computational efficiency during mesh adaptation, the interior mesh entities have their geometric order kept as low as possible while still maintaining control of element shapes. The order of curved mesh entities is limited to no higher than cubic, which allows the definition of an effective procedure to define the shape of the limited number of interior mesh entities that must be curved. The procedures, which are fully parallelized, are demonstrated on the adaptive radio-frequency analysis of a magnetically confined fusion system containing a fully represented radio-frequency antenna.

Speech-driven 3D facial animation research has shown promising results, but most methods rely on representations that are not compatible with production pipelines. In this work, we present a deployable system that bridges this gap by enabling speech-driven 3D facial animation directly in Unreal Engine (UE) using ARKit-compatible representations. We construct 3DMEAD-ARKit dataset by converting the MEAD corpus into blendshape sequences using MediaPipe, and retrain FaceDiffuser and ProbTalk3D-X to generate stochastic and emotion controllable animations. We further develop a modular UE plugin with a Python backend that supports model selection, and parameter control. We compare the results to two existing commercial tools: Epic Games' MetaHuman speech-driven animator and Nvidia Audio2Face with a perceptual user study. The results highlight the importance of comparisons among academic and commercial pipelines. We recommend watching the supplementary video. We also plan to do live demonstrations of our work at Siggraph 2026 conference.

This study examines the role of top-tier conference publications in Hungarian computer science research. We show that the national scientometric practice, which is currently journal-oriented, diverges from international norms, creating incentive distortions in researcher evaluation. By linking multiple databases (iCore, DBLP, MTMT, MTA-ATT), we mapped Hungarian-affiliated CORE A* and A conference papers, their temporal and thematic distribution, and author trajectories. Our results indicate that, in theoretical fields, publishing at international conferences became common earlier than in applied fields. At the same time, in applied fields, successful researchers are more likely to continue their careers in foreign institutions or in industry positions. Overall, a substantial share of the already established, internationally most successful researchers are now affiliated with institutions abroad. We recommend recognizing CORE A* papers as equivalent to D1 and CORE A papers as equivalent to Q1 journals in national evaluation systems.

In preparation for potential international agreements on artificial intelligence, the development of verification infrastructure for AI data centres is vital. We propose a method for cryptographically committing all information entering and leaving a data centre: Hashes are computed by network taps placed on all the information-carrying wires between the cluster and the outside world, enabling an auditor to retroactively challenge the preimage data to be sent to a privacy-preserving verification facility performing compliance checks. Our goal is to make it infeasible to covertly exfiltrate the results of undisclosed workloads in the cluster through the tapped wires. To this end, we specify the architecture of a ``Secure Gateway Device'', which handles the erasure of covert channels that post-hoc verification on hashed data cannot address: analogue and timing side-channels, as well as steganography in network protocol headers. The architecture eliminates the need for any processors trusted by both the Prover and the Verifier, leveraging passive optical fibre splitters and coin-flip protocols for random number generation where needed. We expect development costs of a demonstration device to be roughly equivalent to the cost of a small team of engineers for a few months, with a comparatively small bill of materials.

A formal mechanism is presented in which a willing regulator-matchmaker fosters cooperation on resources among participants in the AGI race, collects a Pigouvian tax based on the speed-up it induces, and invests the proceeds into alignment research. The construction is derived in the continuous-time options framework of Tan (2025) in which cooperation is treated as a jump in the underlying asset value of participating players, the Pigouvian component is matched to the marginal effect of increasing expected loss, and the total collected fund endogenizes the rate of learning on safety. It is shown how the framework allows for determining participation and optimal activity levels. Conditions under which it is optimal to enter the market are derived, and it is proven that if the orthogonality condition holds between the supported portfolio and the abilities component, the Suicide Region collapses at finite time, and the upper bound for this time is derived as sum of a deterministic and random term. Finally, if orthogonality is violated, it is proven that enhancing matchmaker capacity does not recover the market's superiority. The construction links research areas including two-sided markets, Pigouvian taxes, self-regulatory organizations, private law enforcement, evolutionary modeling of AI races, real options and option games, measurement of comparative progress and analysis of the Suicide Region.

The agentic web, in which users interact with the internet largely through agents acting on their behalf, is now technically feasible. However, many of the consumer and social benefits that could be realized by online AI agents acting scrupulously in their principals' interest are currently obstructed by outdated laws, terms of service, and other less formal practices which allow online platforms to block and degrade agent access, often in secret. No distinction is currently drawn between "malicious bots" and AI agents acting with the express delegated authority of a user. For the agentic web to realize its promise, it needs not only the technical infrastructure of protocols and interfaces, but the normative infrastructure of a broadly-accepted and socially-beneficial set of laws, norms and practices governing agentic access to online properties. Building that normative infrastructure requires a society-wide conversation. This paper aims to help precipitate that conversation, to identify normative principles that can guide it, and to advocate for policies that enable users' appropriately delegated agents to act online on their behalf, with as few curbs on their doing so as is reasonable given the other legitimate interests at stake.

Traffic generators are essential tools for evaluating the robustness and performance of networked systems. P4TG is an open-source, hardware-accelerated traffic generator implemented in P4 for the Intel Tofino ASIC. It has been adopted by researchers and industry due to its flexibility and multi-terabit generation capability, and its low cost compared to other traffic generators. However, like most existing generators, it primarily produces constant bit rate traffic, which does not reflect the highly time-varying behavior observed in real networks, such as flashcrowds and microbursts. Such patterns are difficult to emulate at scale with current tools. We present a data plane mechanism for P4TG that shapes periodic, time-varying traffic patterns, including patterns representative of DDoS attacks and burst-load scenarios. Pattern shaping in P4TG can be applied to its generated traffic at an aggregate throughput of up to 4 Tbit/s. We evaluate pattern accuracy and analyze scalability across different sampling resolutions and periods. Further, we demonstrate practical use cases, including zero-loss throughput determination and buffer capacity measurement. Finally, we present microburst-based attack scenarios that overload UDP receivers, switch buffers, and degrade TCP throughput on shared links while remaining undetectable to conventional rate monitoring.