Fluid Dynamics
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Tuesday 1 September
It is traditionally believed that the no-slip boundary condition is necessary for vorticity generation, as might be implied by the Lighthill vorticity generation mechanism. However, the investigations of Morton (1984) and Terrington et al. (2020) assert that the vorticity-generation mechanism is independent of the no-slip boundary condition. To investigate this hypothesis, we simulate viscous flow over a circular cylinder in the laminar periodic von Kármán vortex-shedding regime at Re = 170, without enforcing the no-slip condition at the wall. Instead, we close the wall tangential velocity and its normal derivative using one-sided finite-difference approximations. Accordingly, the wall tangential velocity is dynamically determined from the evolving interior solution rather than prescribed. The resulting flows exhibit qualitatively similar patterns of periodic vortex shedding across all three wall treatments (no-slip, second- and third-order one-sided approximations), although the mean drag coefficient, r.m.s. lift coefficient, and Strouhal number differ from those of the standard no-slip simulation. More significantly, the velocity distributions just outside the boundary layer closely match those of the standard no-slip simulation, regardless of the approximation order. In particular, the circulation evaluated along a contour at the edge of the boundary layer, which corresponds to the total vorticity contained within the layer in the no-slip case, is found to be remarkably insensitive to the wall treatment. These results suggest that the no-slip condition is not necessary for vorticity generation or periodic shedding. However, it may still be required for accurate quantitative prediction of the integral flow quantities and shedding dynamics.
Machine Learning
DeSyR: A decoupled symbolic recovery framework for PDEs with PINN-guided structure discovery and physics-based coefficient refinement
Recovering explicit symbolic solutions of partial differential equations (PDEs) from physics-informed neural networks (PINNs) is attractive, yet selecting and fitting expressions against neural predictions can lock the recovered solution into the teacher's approximation error. We propose DeSyR (Decoupled Symbolic Recovery) to break this dependence. DeSyR uses PINNs only to discover candidate structures and initial coefficient estimates; once a structure is fixed, the governing equations and constraints alone determine the refined coefficients. Multiple candidates with different fitting-error–complexity trade-offs are retained, evaluated after physics-only refinement, and reduced to the simplest expression within a physically near-optimal set. Joint refinement extends the same principle to coupled fields. For fixed candidate parameterizations, affine error identities and local nonlinear analysis show how teacher errors enter fitted coefficients and establish conditions under which physical residuals control coefficient and solution errors. Across seven benchmarks covering scalar evolution equations, multidimensional elliptic problems and coupled incompressible flows, DeSyR attains mean relative solution errors on the order of $10^{-14}$ or smaller and lower reported mean physical residuals than PINNs, physics-informed symbolic networks and teacher-fitted symbolic distillation. With the expression structure held fixed, estimating coefficients from physical constraints further yields more accurate frequency estimates and solutions than fitting teacher predictions. DeSyR therefore turns neural approximations into guides for structure discovery, while physical constraints determine the final explicit solution.
Read the full abstract
Optimization and Control
Variable-Coefficient Parabolic Equations and Finite-Horizon Hamilton–Jacobi–Bellman Equations in Augmented Spectral Barron Spaces
We establish a whole-space solution framework in augmented spectral Barron spaces for uniformly elliptic parabolic equations with state-dependent principal coefficients. A frozen-symbol parametrix yields bounded Green and terminal operators and a one-derivative smoothing estimate on arbitrary finite horizons, without requiring the spatial variation of the principal coefficient to be perturbatively small. We then apply this linear framework to a finite-horizon Hamilton–Jacobi–Bellman equation. A semi-explicit gradient iteration converges on sufficiently short horizons at a Gamma-factorial rate in a whole-space augmented Barron norm, and its limit is identified with the stochastic-control value function. Finally, temporal Jackson approximation and spatial spectral Barron approximation give joint shallow cosine-network approximations in space and time for the value function and the optimal feedback, with quantitative error and neuron-count bounds. Taken together, these results connect variable-coefficient parabolic well-posedness and smoothing in augmented spectral Barron spaces with nonlinear HJB solvability and quantitative neural-network approximation.
Read the full abstract
Machine Learning
Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials
We prove that the Hypergraph Neural Network, an invariant architecture with 3-body message passing, is a universal approximator for potential energy surfaces. Our main contribution is a multi-layer completeness theory. We show that $L$ layers of message passing on sparse, cutoff-based graphs achieve the same representational power as having access to the full $L$-hop neighborhood, provided the configurations are generic, satisfy an overlap condition and a connectivity condition. This provides the first rigorous justification for the common practice of using multi-layer message passing with a per-layer cutoff smaller than the physical interaction range, the setting used by virtually all practical graph neural network based machine-learned interatomic potentials. As immediate consequences, we show that both DPA3 and CHGNet architectures inherit universal approximation.
Read the full abstract
Human-Computer Interaction
Learning Feasibility-Aware Latent Spaces for Preference-Based Exploration of Procedural Automotive Wheel Designs
Intelligent design interfaces that rely on preference-based optimization are most useful when their suggestions are both meaningful to users and feasible within the target domain. Procedural models offer compact and editable design spaces, but their native parameters can be entangled and can generate many invalid outputs, causing human-in-the-loop optimizers to waste comparisons. We propose an interaction-oriented representation-learning pipeline for procedural models and study it in automotive wheel design. The method first screens procedurally generated samples using geometric rules and finite-element analysis, then learns a reduced latent space from the screened subset. We further introduce supervised functional alignment, which reserves selected latent dimensions for stiffness, strength-related stress response, or weight so that search can be biased toward functionally meaningful regions. Simulation experiments show that screened reduction improves target-shape retrieval and the feasibility rate of suggestions, whereas unscreened reduction degrades both. Additional simulations show that constraining search along learned functional dimensions accelerates exploration toward target functional properties. A controlled study with 40 participants further shows that a 5D feasibility-aware space yields higher shape similarity and more feasible suggestions than the original 9D procedural parameterization. These results suggest that, for intelligent user interfaces in engineering design, the representation exposed to the user is a central part of the interaction design, not merely a preprocessing step for the optimizer.
Read the full abstract
Astrophysics of Galaxies
Extragalactic Stellar Streams in Time-Dependent Cosmological Halos
Upcoming and ongoing surveys will detect thousands of stellar streams around galaxies other than the Milky Way. Studies from the Milky Way have shown that time-dependent evolution of the Galactic halo plays a key role in shaping stellar streams, but remains unexplored for extragalactic stellar streams. We use the FIRE-2 m12m cosmological zoom-in simulation, mock observed as an extragalactic system including three stellar streams, to examine how halo time-dependence affects progenitor and host halo inference from extragalactic systems. We show that two of the three m12m streams are well reproduced in a static halo if we only allow for tidal stripping near pericenter. We apply the extragalactic stream fitting code X-Stream to each mock observed stream, and obtain constraints on the host dark matter halo and stream properties. Using on-sky morphology alone and then fixing the progenitor radial velocities, we compare recovered orbits and halo parameters to the FIRE-2 m12m ground truth. For the longest stream with a looped segment, we find unbiased strong constraints on progenitor and halo properties. For the shortest stream, we find limits on orbital parameters, but no constraints on progenitor and halo mass unless we include fainter, more extended debris. For the most massive stream, which was not well produced in a static halo, the recovered orbital parameters are biased, reflecting unmodeled time-dependence. We conclude that imaging of stream debris from extragalactic dwarf galaxies can, in some cases, be used to infer present-day dark matter halo properties, even in a cosmological environment.
Read the full abstract
Computer Vision
GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
Modern image generation and editing systems can produce photorealistic, prompt-aligned images, but still often render familiar objects at implausible relative sizes. To measure this failure mode, we introduce GenScale, a benchmark and evaluation protocol for real-world relative object scale in image generation and editing. GenScale contains 900 image-level entries and 1,643 pairwise anchor-target scale relations across common-object generation, human-product generation with metric dimensions, and scale correction from failed generations. We further design a human-calibrated ordinal judge for scalable pairwise scale evaluation. Last but not least, we introduce Rescale, a model-agnostic post-processing agent for localized scale correction without modifying the source generator. Experiments reveal that state-of-the-art image generators and editors do not reliably render plausible relative scale, while Rescale consistently improves scale plausibility across generated and edited images. Together, GenScale establishes relative object scale as a distinct, measurable, and actionable capability for image generation systems.
Read the full abstract
Human-Computer Interaction
Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop Applications
Computer-use agents are emerging as a paradigm for agentic human-AI interaction, combining language reasoning with multi-modal interface grounding to operate GUIs. Yet their effectiveness for blind screen-reader users in real-world desktop workflows remains unclear. We present a three-week diary study with 8 blind users using OLLA, a screen-reader-accessible CUA prototype, collecting 1,258 commands across 12 applications with screenshots, UI trees, model responses, and action traces. We evaluate GPT-5 during deployment and re-execute the same commands with four additional models. GPT-5 achieved the highest success rate at 52.5%. Trace analysis reveals grounding, planning, constraint-tracking, and termination failures, while interviews reveal beyond-automation needs.
Read the full abstract
Cryptography and Security
Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM Agents
Long-term memory can turn untrusted external content into persistent influence over an LLM agent's future decisions, creating the threat of indirect memory poisoning. A successful attack must survive a multi-stage pipeline comprising memory writing, retrieval, and utilization. Existing attacks largely rely on intra-stage optimization, optimizing individual stages in isolation while overlooking inter-stage coupling. Specifically, these stages impose different requirements on the same poisoning content, and each stage operates on the transformed output of its predecessor. Consequently, optimizing one stage may undermine the effectiveness of other stages, while upstream transformations may erase improvements intended for downstream stages. Indirect memory poisoning should therefore be viewed as an end-to-end optimization problem. Based on this insight, we present PipePoison, which collects fine-grained stage feedback from local shadow systems, uses chain-structured losses to identify and optimize the stage bottlenecking end-to-end success, and applies stability-calibrated stage and configuration weights to improve transferability. Across three agent frameworks and four memory mechanisms, PipePoison improves attack utilization rate by 19.1 percentage points. Even on fully unseen victim configurations, it outperforms the strongest baseline by 16 percentage points and remains effective under eight representative defenses.
Read the full abstract
Information Theory
Capacity Achieving Torn Paper Codes
In the torn paper channel, a codeword is cut at random locations, and the resulting error-free fragments are delivered to the decoder as an unordered multiset. Although the capacity of this channel can be achieved using random code, decoding such codes generally requires exponential time. The interleaved-pilot construction of Shomorony and Vahid embeds a De Bruijn sequence among the symbols of a shifted erasure code and aligns only fragments that are sufficiently long through global statistical uniqueness. A subsequent local-alignment scheme by Liu and Raviv employs run-length-limited constraints and exclusive all-zero markers to identify pilot positions from local structure, substantially reducing the minimum fragment length that can be aligned. We further improve the method of Liu and Raviv by replacing its fixed pilot sequence with a multilevel successive local alignment and pilot-recycling procedure. In Liu and Raviv, the pilot sequence is chosen once and must simultaneously balance the length of the pilot sequence against the ability to align short fragments. Our construction removes this limitation by reusing pilot sequences across successive decoding levels. A pilot sequence with an independent random linear code is first used to align and decode the longest fragments. The information recovered at this stage is then recycled as a larger pilot sequence for the next stage.This process is repeated over multiple levels, so that progressively shorter fragments are recovered while the length of the pilot sequence remains small. Our construction depends on choosing a series of random linear codes, and we show that for any $\varepsilon>0$, there exists a choice of such codes which attains rate of at least $\varepsilon$ below the capacity, with high probability as the block length goes to infinity. Therefore, our construction achieves the capacity of the torn-paper channel.
Read the full abstract
Computer Vision
Soft-Argmax for the Projective Plane via the Veronese Embedding
From horizon detection to fibre structures in X-ray imaging, many vision tasks recover lines via peak detection in Hough space $H=S^1\times\mathbb{R}$, the domain of orientation-offset pairs $(\theta,\rho)$. Differentiable pipelines extract coordinates via soft-argmax, a probability-weighted average that is only meaningful in a globally linear space. However, $(\theta,\rho)$ and $(\theta+\pi,-\rho)$ describe the same undirected line, so $H$ double-covers the space of undirected lines $H/\mathbb{Z}_2$: a Möbius strip, obtained by identifying each pair under $\mathbb{Z}_2$ action. Soft-argmax operates on the cover $H$, but since $H/\mathbb{Z}_2$ admits no linear structure, it tears geometrically adjacent lines apart. Thus we need a $\mathbb{Z}_2$-invariant embedding of lines into a linear space, on which soft-argmax is well-defined. We achieve this by parametrising lines via unit-norm homogeneous vectors $\ell=(1+\rho^2)^{-1/2}(\cos\theta,\sin\theta,-\rho)^{\top}\in\mathbb{R}^3$ and applying the Veronese map $v_2(\ell)=\ell\ell^{\top}$ that satisfies $v_2(\ell)=v_2(-\ell)$. This descends continuously to an embedding of the quotient $H/\mathbb{Z}_2$ into the linear space $\mathrm{Sym}^2(\mathbb{R}^3)$, where the antipodal ambiguity vanishes. Line extraction becomes a barycentre in $\mathrm{Sym}^2(\mathbb{R}^3)$, projected back via its leading eigenvector. We validate our Veronese soft-argmax in a Hough transform-based network across all resolvable lines, confirming uniform and seam-free recovery. We further derive that the $L_2$-loss on isometrically weighted Veronese embeddings equals the squared chordal distance between lines in projective space, enabling a geometrically precise training objective.
Read the full abstract
Neurons and Cognition
A distributed-delay Wilson-Cowan model of sleep-related rhythms in the corticothalamic system
The corticothalamic circuit supports rhythms with timescales that differ by orders of magnitude: sleep spindles, the sigma-band events of non-rapid-eye-movement (NREM) sleep, and infra-slow fluctuations near 0.02Hz that organize when spindles occur. Because the anatomy is the same in both cases, architecture alone cannot determine which rhythm the circuit expresses. We ask whether the temporal structure of the circuit's own feedback can. In a four-population Wilson–Cowan model comprising cortical excitatory and inhibitory populations, thalamic relay cells, and the thalamic reticular nucleus (TRN), we first establish how connectivity controls access to oscillatory behavior, and then introduce temporal coupling as either a weak Gamma distributed delay or a discrete delay. We investigate three distinct connectivity levels: recurrent cortical excitation gates whether the circuit can oscillate at all, the reciprocal relay-TRN pair determines where the oscillation lies and how it is configured, sustained, and terminated, and reticular self-inhibition limits its extent. We then examine how these connectivity-dependent regimes are affected by delayed coupling. Although delay does not change the equilibria themselves, it can substantially alter their stability and the organization of the resulting oscillatory dynamics. Under weak Gamma integration, short delays support spindle-compatible oscillations in the sigma band, while longer delays give rise to a much slower regime near 0.02Hz. The discrete-delay formulation produces a qualitatively different and more complex bifurcation structure. Together, these results show that the dynamics of the corticothalamic circuit depend not only on its connectivity, but also on the temporal organization of interactions within the circuit.
Read the full abstract
Cryptography and Security
The Safeguard Worked. Is the LLM System Safer?
Safeguards for large language model services are typically evaluated by their attack-blocking rates on test suites. Deployment decisions also depend on how much harmful assistance attackers can still obtain from the system, which these rates do not measure. To determine what published evaluations establish about deployment safety, we develop a framework that translates reported results into the minimum and maximum harmful assistance that can remain under a specified outcome and threat model. For safeguards that block attacks through a check, we show that the most an attacker can obtain depends on three properties: whether attack paths pass through the check, its miss rate against every attacker in the threat model, and how much assistance remains after a block. We apply this framework to 85 safeguard evaluations from 52 papers. Of these, only five argue that every attack path passes through the check, and four provide evidence on what remains after a block. These evidence gaps have practical consequences: in NeMo Guardrails' default streaming configuration, the check blocked 94% of password leaks in our test, yet the client received the password in every leak, blocked or not. We identify which of the three properties each safeguard category's evaluations omit, and what to measure for each of four ways attacks bypass a check. Deployments that require these measurements before launch can choose and configure safeguards that limit what attackers obtain from the deployed system.
Read the full abstract
Machine Learning
Learning Task-Specific Antibody Representations via Function-Aware Masking
Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.
Read the full abstract
Mathematical Physics
Topological Recursion on Spectral Curves with Infinite Ramification Loci
Recently in the physics literature there have been a small, but growing, number of papers that have applied the Eynard-Orantin topological recursion procedure to spectral curves with ramification loci of infinite cardinality. However, there is a corresponding gap in the mathematics literature; indeed, it has not been checked rigorously whether the resulting infinite sums converge, or whether the resulting correlators have all the desired properties of the topological recursion. The present work aims to bridge this gap by defining topological recursion on a suitably broad class of spectral curves to cover the aforementioned physics applications and to rigorously prove that this definition has the properties one would intuitively expect. As a by-product, some interesting coincidences involving quantum curves are discovered, where two different spectral curves yield the same quantum curve, a situation that has, hitherto, not appeared in the literature.
Read the full abstract
Number Theory
Exceptional points on Atkin–Lehner quotients
We study the rational points on the star curve $X_0^*(N) := X_0(N)/W(N)$, the quotient of the classical modular curve $X_0(N)$ by the full group of Atkin–Lehner involutions, for squarefree levels $N$. Rational points on $X_0^*(N)$ parameterize $\mathbb{Q}$-curves, i.e.\ elliptic curves $E/\overline{\mathbb{Q}}$ that are isogenous to all of their Galois conjugates. Elkies conjectures that $X_0^*(N)$ has only CM or cuspidal rational points for all large enough $N$. We call any other rational points "exceptional". In this article, we provide new examples of exceptional points in genus 3 and 4, and we give evidence that no exceptional points exist in genus $g \geq 5$. Moreover, we investigate the underlying geometric reasons that might "explain" why these exceptional points arise in the first place, in the vein of Ogg and Mazur. In particular, we propose geometric explanations for Galbraith's exceptional points on $X_0^*(137)$ and $X_0^*(311)$.
Read the full abstract
Computation and Language
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
Large language models (LLMs) have recently demonstrated improved machine translation performance over strong supervised baselines. This raises questions as to what mechanisms underlie how LLMs perform machine translation between languages. Motivated by recent interpretability findings–namely, that LLMs use massively multilingual latent feature representations to perform language modeling–we propose the interlingua hypothesis. The hypothesis holds that language models translate by reading a source sentence into a latent feature space, and generate a target sentence by reading from the latent feature space. We show three lines of evidence in support of this hypothesis: (1) variance in BLEU across language pairs is largely predictable from language-specific competences with no language pair-specific interaction terms; (2) many model components are causally influential in both monolingual tasks and translation tasks; and (3) fine-tuning on monolingual data recovers a large proportion of translation improvements relative to fine-tuning on aligned documents. Together, these provide convergent evidence in support of the interlingua hypothesis, and suggest new ways of understanding and improving how LLMs can be leveraged to perform translation tasks.
Read the full abstract
Dynamical Systems
n-Scrambled Cantor sets
For all $n \ge 2$, we obtain a homeomorphism of Cantor space that has a distributionally $n$-scrambled Cantor set containing a distributionally $(n+1)$-scrambled uncountable set, but does not have an $(n+1)$-scrambled Cantor set.
Artificial Intelligence
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex reasoning paths of multi-hop question answering (QA). Graph-based RAG captures multi-step relationships but suffers from severe semantic drift and high online latency due to noisy global graph traversals. Thus, we propose ISO-RAG (ISOperimetric Retrieval-Augmented Generation), a geometry-aware RAG framework. By projecting the underlying knowledge graph into a hyperbolic Poincare ball to precompute node-wise isoperimetric profiles, ISO-RAG prunes spurious edges during retrieval, restricting the search space to a strictly localized subgraph. This topological purification regulates Personalized PageRank (PPR) diffusion driving the retrieval process, ensuring exact and low-latency convergence. Experiments on multi-hop QA benchmarks demonstrate that ISO-RAG outperforms state-of-the-art baselines by average absolute gains of 10.0% in retrieval recall and 4.3% in downstream exact match, achieving a superior accuracy-efficiency trade-off by fundamentally eliminating the latency bottleneck of global traversals. Our source code is available at https://github.com/ZaiizaiZHANG/ISO-RAG.
Read the full abstract
Materials Science
Optical-Phonon-Enabled Large Lattice Thermal Conductivity Anisotropy in Hexagonal Perovskites Cs$BX_3$ ($B$ = Mg, Cd; $X$ = Cl, Br, I)
Materials exhibiting strongly anisotropic lattice thermal conductivity are desirable for thermal-management applications, yet such behavior is commonly associated with layered or quasi-one-dimensional van der Waals crystals and highly anisotropic elastic properties. Here, we investigate lattice thermal transport in the hexagonal perovskites Cs$BX_3$ ($B=$ Mg, Cd; $X=$ Cl, Br, I) using first-principles calculations. At 300~K, the calculated in-plane and out-of-plane lattice thermal conductivities range from 0.13–0.83 and 0.34–6.26~Wm$^{-1}$K$^{-1}$, respectively, corresponding to anisotropy ratios of 2.6–7.5. This pronounced anisotropy is remarkable given the relatively modest elastic anisotropy, characterized by $C_{33}/C_{11}$ = 0.994–1.842. Our analysis reveals that medium-frequency optical phonons provide an efficient out-of-plane heat-transport channel, contrary to the conventional picture in which heat transport is dominated by acoustic phonons. These findings identify face-sharing octahedral frameworks as a promising platform for engineering strong thermal-conductivity anisotropy in mechanically near-isotropic, non–van der Waals crystals.
Read the full abstract
Materials Science
XUV Transmission Spectroscopy Using a Tabletop High-Harmonic Source
High-harmonic generation (HHG) provides a coherent ultrashort-pulse light source in the extreme- ultraviolet (XUV) region and has potential applications in time-resolved spectroscopy and materials characterization. In this study, we constructed an HHG system using a Yb:KGW laser system (PHAROS, Light Conversion) as the driving source and Ar gas as the nonlinear medium. High-order harmonics were observed up to a photon energy of 70.6 eV, corresponding to the 59th harmonic order. As an application of the developed XUV source, we measured the transmission of a Mg thin film and a Si3N4 membrane. In addition, the surface chemical state of the Mg thin film was characterized by X-ray photoelectron spectroscopy (XPS), and the results were compared with the transmission measured using the HHG source. This comparison was used to examine the relationship between the surface condition, including surface oxidation, and the XUV transmission of the Mg thin film. These results demonstrate the applicability of the developed Ar-based HHG source to the characterization of thin-film transmission in the XUV spectral region.
Read the full abstract
Artificial Intelligence
When the Algorithm Becomes the Brand Crisis: A Sociotechnical Theory of Distributed Responsibility and Accountable Transparency
Artificial intelligence systems increasingly enact market-facing promises through chatbots, recommendation systems, automated decisions, and generative interfaces. Their failures, misuse, and misrepresentation raise a question that conventional brand-crisis models do not fully specify: how do stakeholders assign responsibility when technical causation, customer-facing control, and governance duties are distributed across an AI system, developer, deployer, vendor, and user? This conceptual paper develops a sociotechnical process theory from a structured, federated scoping synthesis of verified academic and primary sources. It distinguishes an AI/algorithmic incident from an AI-related organisational crisis and, in turn, from an AI-related organisational scandal. The framework proposes that incident configuration shapes actor-specific attribution; attribution informs capability, integrity, fairness, and relationship appraisals; and public moralisation may, but need not, escalate an incident into scandal. The theory offers a reconciliation of findings that algorithm involvement can buffer negative brand reactions in some settings while robot and chatbot failures can redirect responsibility to an associated firm in others. It introduces accountable transparency as a proposed response configuration that combines timely notice, an intelligible account, role-responsibility acknowledgement, remedy, evidence of correction, and recourse. The evidence supports conditional, proximal inferences about blame, trust, satisfaction, firm evaluation, and communication credibility more strongly than claims about durable reputation, brand equity, or market performance.
Read the full abstract
Classical Physics
Some explorations of Kirchhoff dynamics
The classical problem of a rigid body in an ideal fluid is a six-dimensional dynamical system with three conserved quantities. Despite its long history and its importance as a reduced model of many fluid-structure problems, basic questions remain, including the shapes and connectivities of the three-dimensional submanifolds of solutions, and the nature of chaotic motions on these. We explore the problem with a particular ellipsoidal body, beginning with integrable motions— steady linear translation and rotation and periodic planar tumbling and fluttering. The stability of these states depends on the relative magnitudes of linear and angular momentum or energy. Linear stability, including Floquet, analysis of lower-dimensional perturbed systems is consistent with direct integration of the full system. We document instabilities leading to a variety of regular and chaotic motions, including flipping and twirling, whose trajectories appear to follow paths near connections between the integrable states. Such indirect observation of these connections provides insight into the structure underlying the rich dynamics of this simple system. For the submanifold where linear and angular momentum are perpendicular, we further examine how solutions fit together to fill momentum space in different zones of stability of the integrable states, and thereby uncover additional bifurcations in connectivity and what appear to be new integrable solutions.
Read the full abstract
Artificial Intelligence
CoVer: Conflict-Aware Claim Verification
Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support conflict verification tasks, we present ContraNote, a large-scale real-world dataset curated from X's Community Notes system. It includes 33,686 posts for evaluating evidence-level conflict resolution, and 54,474 instances for evaluating aggregation-level prioritization. Additionally, we propose CoVer, a factual adjudication framework with three-stage pipelines: evidence schema normalization, factual consensus and support verification. This prioritizes evidence over noise to prevent it from compromising the final verdict. Technical evaluations show that CoVer achieves strong performance compared with state-of-the-art baselines across ContraNote (86.0% Acc., 68.0% mac. F1, 64.5 bal. Acc. on Conflict; and 88.5% Acc., 88.5 mac. F1 and 89.2 bal. Acc. on Prioritization), CONFACT-HumC (88.4% Acc.) and CONFACT-ModC (89.4% Acc.).
Read the full abstract
Machine Learning
VATO: A Vortex-Force-Aware Transformer Operator for Unsteady Separated Aerofoil Flows
Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics. Although high-fidelity CFD resolves these mechanisms, its cost limits repeated use in design and control. Standard field-level surrogate training, however, does not distinguish the flow regions that contribute most strongly to the aerodynamic loads. We introduce VATO (Vortex-Force-Aware Transformer Operator), which couples the Vortex Force Map (VFM) method to a geometry-aware neural operator through two complementary mechanisms. VATO-S adds training-only supervision of the local VFM force-contribution field, with no increase in model size or inference cost. VATO-A uses VFM contribution and sensitivity fields to prioritise force-relevant source locations for residual cross attention. The methods are evaluated on unsteady CFD data for double-edged-plate aerofoils over 54 trajectories from nine geometries. Over lead times of 1-20~ms, VATO-S reduces velocity, pressure, and vorticity errors by 10.4%, 1.0%, and 15.6%, respectively, while VATO-A achieves reductions of 15.8%, 7.5%, and 31.2%. VATO-S gives the lowest VFM-derived drag error, whereas VATO-A gives the lowest pressure-derived lift and drag errors. Over lead times extending 50% beyond the training range, VATO-A retains a 26.9% reduction in vorticity error and larger improvements in all four force readouts, despite reduced gains in velocity and pressure. These results show that force-aware operator learning can improve both flow-field prediction and aerodynamic functional accuracy in unsteady separated flows.
Read the full abstract
Human-Computer Interaction
RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
Large language models are powerful, but their interfaces often devolve into a type $\rightarrow$ read $\rightarrow$ retype loop, creating conversational AI fatigue, cognitive load, and eventual task abandonment. To mitigate this, we present RecalibrateGPT, a system introducing five cross-turn operators (Anchor, Replay, Delta, Scope, and Steer) that each target a distinct fatigue type, recalibrating LLM responses through a structured panel by acting on the full conversation history with a single click. Users invoke these operators through the AssistiveButton in one of three operator palette layouts: Vertical, Arc, or Tablet. We conducted two pilot studies with the same 12 advanced LLM users. An initial formative qualitative study identifies a taxonomy of four fatigue types (retyping, scanning, decision paralysis, and context drift) and derives two design objectives for RecalibrateGPT. A follow-up quantitative evaluation finds it reduces perceived cognitive workload by half (NASA-TLX = 2.7) at high perceived usability (SUS = 86.5), suggesting AI fatigue is not just a model-quality issue but an interaction-flow cost that interfaces can remove.
Read the full abstract
Computer Vision
ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits
Video-text models adapted from image-text architectures (e.g., CLIP) frequently exhibit temporal blindness, the inability to perceive fundamental cues like order, direction, and motion dynamics. Standard datasets mask this limitation by enabling models to exploit static spatial shortcuts. To systematically evaluate this, we introduce XTE-Bench, a diagnostic probe revealing that even large-scale video-language models struggle with basic temporal reasoning, indicating that parameter scaling alone is insufficient to resolve this flaw. To address this, we propose Cross-Modal Temporal Edits (XTE), a self-supervised framework that injects precise temporal supervision. By performing synchronized video-text transformations, XTE generates hard temporal negatives without manual annotation. We instantiate this with ViTAL-X, a lightweight model that equips frozen image-text backbones with temporal awareness while preserving their foundational spatial knowledge. Across six temporal benchmarks, ViTAL-X achieves state-of-the-art performance. Utilizing only 0.4B parameters and 1M training clips, ViTAL-X outperforms 7B-parameter models and surpasses baselines trained on 600x more data. These results demonstrate that targeted, high-quality temporal alignment provides a highly efficient alternative to pure scaling.
Read the full abstract
Game Theory
Independent Reinforcement Learning in Discounted Markov Games
In this work, we study radically uncoupled learning in discounted general-sum Markov games. Assuming “$\mathsf{ETH}$ for $\mathsf{PPAD}$", we show that, for every fixed discount factor, there is no polynomial-time algorithm for computing inverse-polynomially accurate coarse correlated equilibria in discounted general-sum Markov games when players learn independently in decentralized settings. Complementing this hardness result, we provide what appears to be the first radically uncoupled algorithm with sub-exponential convergence guarantees to coarse correlated equilibria in discounted general-sum Markov games without imposing any structural restrictions on the game. Our algorithm is a layered variant of optimistic mirror descent with an increasing step-size schedule tailored to the multi-agent setting. Finally, we develop both full-feedback and partial feedback versions of the aforementioned algorithm and establish sub-exponential convergence guarantees for each case.
Read the full abstract
Artificial Intelligence
Wave Function Backpropagation with Explicit Temporal-Interval Dynamics
Conventional neural networks learn predominantly through affine transformations followed by nonlinear activations, while elapsed time is often treated as an auxiliary feature or assumed to be uniformly sampled. This paper introduces Wave Function Backpropagation (WFB), a wave-parameterized learning formulation in which neural responses are represented by learnable amplitude, wavenumber, angular frequency, and phase. The formulation associates an observed state with its temporal interval Delta t through the phase of a differentiable spatiotemporal wave. We derive standard WFB gradients and a spatial-curvature correction based on the Laplacian of the wave response. WFB is instantiated in a deliberately feed-forward trajectory predictor to provide a controlled proof of concept; sequence learning is outside the scope of the present evaluation. With motion features, STD-WFB using real intervals reduces average displacement error (ADE) by 20.4% relative to the original FFN baseline. In a new position-only evaluation that removes temporal leakage through precomputed velocity and acceleration, real-interval WFB reduces ADE by 10.4% relative to the original FFN and remains competitive with parameter-matched ReLU controls, obtaining 2.1% lower mean ADE than the matched FFN with explicit Delta t. Shuffled-interval WFB attains the lowest mean ADE, indicating that the present evidence supports the effectiveness of the wave representation but does not attribute the gain to interval alignment. These results establish WFB as a viable structured feed-forward learning formulation and define a clear basis for subsequent architectural studies.
Read the full abstract
Cryptography and Security
GlitchLab: A Hardware-in-the-Loop Optimizer for Physical Fault Injection
Physical fault injection can turn brief hardware disturbances into security failures such as key recovery, authentication bypass, and unintended control flow. Finding effective faults is difficult because many interacting parameters create a large search space, successful settings are sparse and target-dependent, and each hardware attempt provides limited feedback. Under fixed testing time, efficient search is therefore critical for assessing fault sensitivity. We present GlitchLab, an online hardware-in-the-loop platform that treats delay as a timing gate, voltage and pulse duration as severity controls, and hardware outcomes as structured feedback. It implements RL-Q (Q-learning-based reinforcement learning), a structured bandit for discovery, and Structured-Outcome-Based Adaptive Search (SOBAS), a model-based policy for fault reproduction. Both policies find a target fault in every AES, password, and control-flow campaign. On AES and control flow, they require 2-85x fewer attempts and 26-1,237x less time than the baselines; on password, both succeed while the baselines fail within 5,000 attempts. After discovery, SOBAS reproduces faults 7.3-21x more often, while RL-Q identifies 30% more distinct AES settings.