Peer Revenue Returns subject to peer review

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Wednesday 2 September

Astrophysics of Galaxies

Can diffuse X-rays be important in driving photoionisation in molecular clouds?

The ionisation balance in molecular clouds is regulated by several ionising sources, including cosmic rays, X-rays, and ultraviolet radiation. Their relative importance depends on the local physical conditions and on the shielding column density. We compute the contribution of the large-scale diffuse X-ray radiation field to the ionisation in molecular clouds in the absence of strong local X-ray sources, such as young stars. Our goal is to quantify its significance relative to the Galactic cosmic rays. Using measurements of diffuse X-ray emission from the first eROSITA all-sky survey, we estimate the depth-dependent X-ray ionisation rate in molecular clouds across different Galactic environments. We consider both the observed diffuse field and a deabsorbed field obtained by correcting for foreground Galactic attenuation using HI4PI line-of-sight column densities in a pixel-by-pixel framework. Diffuse Galactic X-rays are unlikely to dominate the ionisation balance in well-shielded molecular gas ($N_{\mathrm{H}} > 5 \times 10^{21} \mathrm{cm^{-2}}$), where cosmic rays remain the primary ionising agent. At low column densities, the deabsorbed diffuse X-ray field produces ionisation rate of $\zeta_X \sim 10^{-18}\mathrm{s^{-1}}$ at $N_{\mathrm H} \sim 10^{19}\mathrm{cm^{-2}}$, remaining below the lower end of Galactic cosmic ray ionisation rate ($\sim 10^{-17} \mathrm{s^{-1}}$). The X-ray contribution decreases rapidly with increasing shielding, falling to $\zeta_{X}\sim10^{-19}\mathrm{s^{-1}}$ by $N_{\rm H}\sim10^{21}\mathrm{cm^{-2}}$ and to $\zeta_X \sim5\times10^{-21}\mathrm{s^{-1}}$ by $N_{\rm H}\sim10^{22}\mathrm{cm^{-2}}$. Diffuse X-ray may therefore contribute to the thermal and chemical structure of low-extinction material and should be considered when interpreting ionisation tracers in diffuse or cloud-envelope environments.
Read the full abstract

All authors E. I. Makarenko, A. V. Ivlev, S. Bialy, X. Zheng, B. A. L. Gaches, P. Caselli, M. Padovani, M. C. H. Yeung

Cryptography and Security

PrimSynth: An Agentic Approach to Discover, Validate, and Synthesize Exploit Primitives for Linux Kernel Vulnerabilities

Linux kernel vulnerabilities are critical to downstream systems. Despite extensive research on automated kernel exploitation, a fundamental challenge remains the conceptual gap between abstract exploit strategies and concrete technical operations. To fill this gap, this paper introduces a systematic characterization that formalizes six classes of exploit primitives from logical capability to validatable effect. Then, an extended exploit strategy representation is proposed, which couples primitive upgrading strategies with primitive path code synthesis rules governing object constraints, temporal sequencing, environment prerequisites, and validation constraints. Building upon this foundation, this paper presents PrimSynth, a multi-agent framework that encapsulates these representations through coordinated agents to discover, validate, and synthesize exploit primitives for memory corruption vulnerabilities in the Linux kernel. These agents operate in an iterative closed loop until valid primitives are found, leveraging validation signals as evidence of exploitable state transitions to ground primitive synthesis decisions. An automated method for extracting and validating primitives is also proposed based on vulnerability-directed execution and a rebootable validation environment. PrimSynth is evaluated on 16 real-world Linux kernel CVEs spanning 5 vulnerability types. Experimental results show that PrimSynth achieves reliable primitive extraction, maintaining a 100% primitive match rate. For primitive synthesis, PrimSynth successfully synthesizes multi-primitive exploitation chains with 82.4% strategy synthesis rate (SSR) when the public PoC is available and a 61.3% SSR without the guidance of primitive hypotheses.
Read the full abstract

All authors Pengfei Wang, Anying Chen, Danjun Liu, Xu Zhou, Wei Xie

Machine Learning

Differentiable Electricity-Market Clearing for Gradient-Based Planning

Planning a large data center is difficult because a facility big enough to matter changes the electricity prices it will pay. Those prices are set by market clearing, a constrained optimization problem solved anew in every operating condition. However, simulating the market tells a planner how a candidate plan performs but not how to improve it. Here we treat market clearing as a differentiable optimization layer: each forward pass solves the market, and reverse-mode automatic differentiation propagates the planning cost back through the cleared prices to the plan. After validating these gradients against finite differences, we apply them to a concrete problem: allocating 50 MW of data-center load across six candidate buses in two synthetic networks, under a fixed cost per active site, evaluated over 36 operating states. Judged against exhaustive enumeration of all site combinations, gradient optimization recovers the continuous allocations almost exactly, with worst-case objective gaps of 2.3% and 8.5% of the cost difference between the best and worst single site. Its one systematic error is instructive: near the costs at which a site should close, the smooth relaxation of the discrete site count shrinks the site rather than closing it, so discrete transitions arrive late. Differentiable market clearing thus turns market-aware planning into a problem gradients can search.
Read the full abstract

Soft Condensed Matter

XPCS-Echo and broad relaxation measurements using a bunch-mode data acquisition scheme

Echoes observed in the intensity-intensity autocorrelation functions [$g_2(q, \tau)$] is a powerful method for probing nonaffine deformations and yielding behavior of soft viscoelastic materials subjected to an oscillatory shear. Multispeckle X-ray photon correlation spectroscopy (XPCS) measurements of large number of echoes with high time resolution impose severe constraints in terms of the computational hardware and potential degradation of the sample. These issues are alleviated by implementing a bunch-mode data acquisition scheme in which the highest resolution frames or bunches centered at the echo peaks. In addition, by placing the bunches in an aperiodic Fibonacci sequence, $g_2(q, \tau)$ over a long time span can be measured with orders of magnitude lesser number of frames. The performance of these XPCS acquisition schemes is demonstrated using slowly relaxing model colloidal suspensions. Furthermore, an analytical expression is provided for the quantitative description of full $g_2(q, \tau)$.
Read the full abstract

All authors William Chèvremont, Thomas Gibaud, Yuriy Chushkin, Theyencheri Narayanan

Computer Vision

Learning to Attract and Repel: Dual Quality Margin Learning for Face Recognition (DQM-Face)

Face recognition in unconstrained environments remains highly challenging due to diverse and extreme variations encountered in real-world scenarios. To mitigate these effects, existing margin-based approaches model sample quality through feature magnitude. However, magnitude-based modeling alone is susceptible to identity-agnostic noise, which can degrade the reliability and discriminative power of learned representations. In this paper, we propose Dual Quality Margin Learning for Face Recognition (DQM-Face), a novel framework that enables refined attraction and repulsion dynamics during representation learning. Our approach unifies conventional magnitude-based quality estimation with a newly introduced semantic quality learning mechanism, realized via squeeze-and-excitation semantic attention. By jointly leveraging magnitude and semantic cues, we construct enhanced quality-aware margins that adaptively strengthen intra-class compactness through improved attraction during learning. To further enhance inter-class discrimination, we introduce a repulsion margin formulation that explicitly enlarges inter-class separation. The unified integration of semantic quality modeling with dual attraction-repulsion margin optimization results in a more structured and discriminative feature geometry. Extensive experiments on multiple challenging benchmarks demonstrate that DQM-Face consistently outperforms state-of-the-art face recognition methods. Moreover, we show that the quality learned for margin optimization is highly effective for face image quality assessment within the proposed framework, demonstrating that the learned quality signal is intrinsically aligned with the recognition objective. The code is publicly available: https://github.com/RAIB-group/DQM-Face
Read the full abstract

Quantum Gases

Dynamical stabilisation of a quantum fluid using a single topological defect

The size and shape of a quantum fluid in equilibrium is strongly influenced by the inter-particle interactions. In the attractive interaction regime, atomic quantum fluids ultimately collapse in a violent process that expels most of the particles from the macroscopically occupied state. Here, we use a quantum fluid of light in propagating geometry as an analogue to a two-dimensional Bose-Einstein condensate (BEC) with large attractive interactions to show that non-trivial topology significantly alters the dynamical behaviour of the collapse, enhancing the BEC stability and delaying the collapse time by an order of magnitude. We measure direct experimental signatures of topology affecting quantum hydrodynamics, unveiling the inherent competition between attractive nonlinearities, that lead to the collapse, and the preservation of topological charge from a multi-charged vortex. We fully characterise the collapse process in coordinate space and the eventual `solitonification' of the system and connect it to the mode structure of the excitation spectrum.
Read the full abstract

All authors Deborah Capecchi, Paolo Comaron, Antonio Gianfrate, Milena De Giorgi, Dario Ballarini, Daniele Sanvitto, Franco Dalfovo, Dimitrios Trypogeorgos

Signal Processing

Active Inference for Joint Port Selection and Pilot Allocation in Fluid Antenna Systems Under Partial CSI

Fluid antenna systems (FAS) obtain spatial degrees of freedom by activating a few radiating ports from a dense grid of candidates, but deciding which ports to activate presupposes channel knowledge at ports that are never measured. Prior port-selection work assumes full or near-full channel state information (CSI) and treats the pilot overhead as a fixed cost. We instead formulate port selection and pilot allocation jointly as active inference. A spatio-temporal generative model – sub-wavelength spatial correlation together with an order-p autoregressive temporal prior – maintains a Gaussian belief over all N port channels, and the transmitter chooses both the ports it serves and the subset of them it pilots by minimizing an expected free energy that trades achievable rate against information gain and port-switching cost. Selection is greedy and submodular, at O(NM) per slot. On a 441-port grid with a hybrid front end at n_RF = 2K, the agent attains 91% of a full-CSI genie's sum rate while measuring only 2.3% of the candidate ports; pilots can then be withdrawn from ports that are still served, one fifth of them for 2% of the sum rate and two fifths for 8%. No training is required.
Read the full abstract

Quantum Physics

Transversal Gates and Magic State Distillation in an Optimally Synthesized Spin-Qubit Shuttling Bus

Fault-tolerant quantum computing requires not only reliable logical qubit storage, but also the ability to perform high-fidelity logical operations between error-corrected qubits at scale. While much of the existing literature focuses on optimizing syndrome extraction for a single logical qubit, the co-design of physical architectures that support both robust error correction and efficient logical computation remains an open challenge. In this work, we propose a multi-qubit spin-qubit shuttling bus architecture that addresses both requirements simultaneously. The architecture optimizes the physical qubit layout for syndrome extraction and supports transversal two-qubit logical gates between an arbitrary number of logical qubits, achieving all-to-all logical connectivity through coherent spin shuttling. We further propose an ancilla-sharing scheme that encodes multiple logical qubits within a single logical element, compressing the physical footprint of the processor and improving long-range gate fidelity. Extending the architecture from a one-dimensional bus to a two-dimensional grid of shuttling tracks reduces the inter-qubit distance, yielding consistent improvements in logical error. Finally, we apply the Quantum Reverse Mapping methodology at the logical level to optimize the layout of a 15-to-1 magic state distillation circuit, demonstrating how the transversal capabilities of the proposed architecture can be leveraged for universal fault-tolerant computation. Taken together, these results establish a principled co-design framework that bridges the physical, error-correction, and logical computation layers of the quantum stack, and demonstrate that spin-qubit shuttling architectures are a viable and flexible substrate for scalable fault-tolerant quantum computation.
Read the full abstract

All authors Pau Escofet, Andrii Semenov, Niall Murphy, Elena Blokhina, Carmen G. Almudéver, Sergi Abadal, Eduard Alarcón

Computer Vision

From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images

The rapid advancement of generative models has significantly worsened the problem of manipulated image detection, as these methods are capable of producing highly realistic forgeries, reinforcing the importance of multimedia forensics. Conventional approaches typically frame image manipulation detection as a binary classification task (real vs. generated), which limits the capability to distinguish and localize different forms of manipulation. To address these constraints, this work extends an existing detector by introducing a unified multiclass framework (real vs. fully generated vs. tampered). In addition to classifying image authenticity, the framework incorporates a segmentation branch to enable pixel-level localization of tampered regions. The proposed approach outperforms selected recent benchmarks, offering an efficient solution with improved classification accuracy and higher IoU scores for the localization task. Find the code at https://github.com/anngal01/From-Detection-to-Localization-A-Unified-Forensics-Framework-for-Fully-Synthetic-and-Tampered-Images.
Read the full abstract

All authors Annalisa Gallina, Marco Fiorucci, Marco Brigo, Federica Battisti, Lamberto Ballan

Computation and Language

TaRA: Training-Aware Low-Rank Adaptation Initialization

Low-Rank Adaptation (LoRA) has become a de facto standard for parameter-efficient fine-tuning (PEFT), yet its performance is highly sensitive to initialization due to the information bottleneck imposed by low-rank decomposition. Existing approaches attempt to construct high-quality LoRA initializations by exploiting principal components of pretrained weights, activations, or gradients. However, these methods do not directly account for the training dynamics of the full-rank model. In this paper, we propose Training-aware Low-Rank Adaptation Initialization (TaRA), a method that initializes LoRA such that the gradients induced by the low-rank factors closely approximate the gradient of the corresponding full-rank weight matrix. Derived from a mathematical formulation, TaRA improves gradient fidelity at the start of training while introducing negligible computational overhead. Across diverse and challenging fine-tuning tasks, TaRA consistently outperforms prior state-of-the-art methods, establishing a simple, robust, and scalable solution for effective LoRA initialization.
Read the full abstract

Machine Learning

Oracle, will I ever learn? A study of prediction convergence and complementarity across link prediction models

Knowledge graphs have become an important source of structured knowledge for Web applications, including search, question answering, and recommender systems. In these applications, link prediction can serve either as a prediction task itself or as a means to enrich incomplete knowledge graphs for downstream tasks. Interestingly, different link prediction models, or even different training runs of the same model, can produce substantially different predictions for the same query. This suggests a variability in the capture of the underlying knowledge by models, thus raising a fundamental question: to what extent do different models capture complementary knowledge, and how much of this knowledge could be recovered by combining them? We propose to measure model complementarity through the performance of an oracle that, for each query, selects the best prediction among a considered set of models, hence providing an upper bound on the performance achievable through model combination. Across several architectures and benchmarks, we find a substantial gap between individual models and their oracle, revealing that different models capture complementary knowledge. Yet, this complementarity rapidly saturates as more models are added, leaving a persistent subset of queries unsolved even by a large number of models. These findings reveal both the potential of model complementarity and a fundamental limit to what current link prediction models can collectively recover; thereby highlighting the need for further research to build robust Web applications.
Read the full abstract

Medical Physics

The 2024 MRSI Data Processing and Quantification Challenge Synthetic Dataset

Synthetic data is central to magnetic resonance spectroscopy method development because they provide ground truths for software validation, reproducible benchmarking, and machine- and deep-learning training. In MRSI, synthetic data must capture spatially varying anatomy, field inhomogeneity, nuisance signals, and measurement effects. The 2024 MRSI Data Processing and Quantification Challenge Synthetic Dataset is a simulated 3T brain FID-MRSI resource with ground-truth metabolite maps developed as a controlled testbed for MRSI processing and quantification methods. Subject-specific simulations used anatomical images and field maps from Human Connectome Project subjects. Tissue masks, quantum-mechanically simulated metabolite basis functions, in vivo-derived macromolecular components, Bloch-simulated post-WET residual water, registered in vivo lipid signals, spectral baseline, $B_0$-dependent frequency shifts, Voigt lineshape variations, and complex Gaussian noise were combined in a forward model. Water and lipid signals were synthesized on a high-resolution grid and Fourier-truncated to the final echo-planar spectroscopic imaging grid to model the finite spatial point spread function. This resource has 24 training and 8 testing datasets containing contaminated FID-MRSI data, anatomical images, $B_0$ maps, metadata, and ground-truth metabolite and component signals. Forward-model parameters are documented, including tissue-specific metabolite concentrations and relaxation times, macromolecular amplitude ratios, the water model, noise, and field-inhomogeneity ranges. This synthetic benchmark supports development and comparison of MRSI processing, nuisance-signal removal, and metabolite-quantification methods, while enabling method evaluation. It illustrates how characterized synthetic data can support rigorous evaluation when ground truth is difficult or impossible to obtain.
Read the full abstract

All authors John T. LaMaster, Julian P. Merkofer, Dennis M. J. van de Sande, Brian J. Soher, Bernhard Strasser, Chao Ma

Networking

Microcell Hot Spot and Smart Antennas Evaluation in WCDMA Macrocell System

The purpose of this contribution is to analyze a hierarchical cell structure with a hot spot embedded in a WCDMA macrocellular system. Particular attention is paid to the impact of introducing smart antennas in this context. A system-level simulation approach is employed, in which we consider two main solutions to address hot-spot traffic: the placement of a microcell antenna or the adoption of smart antenna technology at the macrocell. Relative gains in signal-to-interference ratio (SIR) are then evaluated. Distinct scenarios are defined based on the proportion of users of different service classes. An evaluation of which solution is best suited to each scenario is then conducted.
Read the full abstract

All authors Carlos H. M. Lima, Francisco R. P. Cavalcanti, Vicente A. de Sousa Jr., Emanuel B. Rodrigues

General Relativity and Quantum Cosmology

Frequency-domain extended-effective-source gravitational self-force for eccentric Schwarzschild orbits

Effective-source formulations provide a practical route to gravitational self-force (GSF) calculations when singular retarded fields cannot be handled directly mode by mode. Before this work, frequency-domain effective-source calculations of the first-order GSF had been performed only for circular Schwarzschild orbits. We construct and implement a frequency-domain extended effective-source (EES) formulation for first-order Lorenz-gauge GSF on eccentric orbits in Schwarzschild spacetime. The central obstacle is that radial libration forces the physical puncture and effective source to switch between interior and exterior branches, limiting their differentiability and producing slow spectral convergence. We overcome this obstruction by analytically extending both branches across the libration region and solving the coupled Lorenz-gauge perturbation equations for the resulting smooth extended sources. This provides an end-to-end gravitational EES implementation for eccentric motion and validates a computational ingredient needed for extending frequency-domain effective-source calculations toward second order.
Read the full abstract

All authors Xuchen Lu, Yungui Gong, Bokai Zhang, Chao Zhang, Wenting Zhou

2609.02635 · 2 Sep · 16 pages, 5 figures. Accepted for publication in Physical Review D. Compared with the previous version, we have included higher-order mode-sum regularization terms and an estimate of the large-l tail, accelerating convergence and yielding more accurate self-force results

Robotics

Latent Cluster Analysis for Vision-Language-Action Models

Vision-Language-Action (VLA) Models are increasingly used in robotics for their ability to ground language and perception into action, yet the internal representations driving their behaviour remain poorly understood. We propose LAVLA, a framework for latent cluster analysis of VLA models, and conduct a layer-wise study of the state-of-the-art GR00T N1.5 model, with particular focus on its action decoder. To better characterise the latent space during action diffusion, we introduce a cross-attention-based embedding-weighting method that amplifies relevant features while suppressing less informative ones. Quantitative evaluation shows that weighted clustering consistently outperforms the baseline. To improve interpretability, we extract human-interpretable concepts for each cluster, linking latent representations to semantic descriptions. Our analysis shows that latent clusters progressively disentangle spatiotemporal and kinematic features, with representations becoming more refined in the middle layers and stabilising toward the output. As such, LAVLA advances the interpretability of language-driven robotic systems.
Read the full abstract

All authors Theodor Wulff, Sergio Lanza, Tamara Bila, Angelo Cangelosi, Stefan Wermter, Igor Farkas

Quantum Physics

Heuristically optimizing, synthesizing, and prioritizing measurement settings for quantum state tomography

A key task in many quantum-computing applications, e.g., quantum simulation and quantum state tomography (QST), is to partition an arbitrary set of operators into mutually commuting subsets for efficient measurements. However, brute-force approaches to this task quickly become intractable as the number and dimensionality of operators grow. Here, we reformulate operator partitioning as a graph-coloring (GC) problem and develop an efficient computational framework to solve it, balancing accuracy and efficiency. Our framework enables leveraging a range of GC algorithms, which we benchmark for operator partitioning. Then, we demonstrate their utility in optimizing QST experiments, where determining non-overlapping data acquisition settings for QST is a major challenge, and prioritizing among these settings, i.e., selecting the experiments that provide the most information. We further show how to perform these experiments by synthesizing Clifford circuits for joint measurement of commuting Pauli operators in multi-qubit systems. We validate our framework across multi-qubit (up to five qubits), multi-qutrit (up to three qutrits), and hybrid qubit-qutrit systems. Our results show that heuristic GC methods substantially reduce the number of required measurement settings for QST and enable priority-based scheduling that maximizes the information gain per experiment. The optimization converges within minutes on a student-grade laptop, providing speedups of several orders of magnitude over brute-force methods already for these relatively small quantum systems. This demonstrates the potential of GC heuristics as a scalable and practical tool for characterization of noisy intermediate-scale quantum devices. We have made the Python implementation of our GC framework to optimize and schedule QST experiments publicly available at https://github.com/ssm8015/QST_GT.git.
Read the full abstract

Materials Science

Spin Hall Magnetoresistance in Antiferromagnetic Insulators

Antiferromagnetic materials promise improved performance for spintronic applications, as they are robust against external magnetic field perturbations and allow for faster magnetization dynamics compared to ferromagnets. The direct observation of the antiferromagnetic state, however, is challenging due to the absence of a macroscopic magnetization. We show that the spin Hall magnetoresistance (SMR) is a versatile tool to probe the antiferromagnetic spin structure via simple electrical transport experiments by investigating the easy-plane antiferromagnetic insulators alpha-Fe2O3 (hematite) and NiO in bilayer heterostructures with a Pt heavy-metal top electrode. While rotating an external magnetic field in three orthogonal planes, we record the longitudinal and the transverse resistivities of Pt and observe characteristic resistivity modulations consistent with the SMR effect. We analyze both their amplitude and phase and compare the data to the results from a prototypical collinear ferrimagnetic Y3Fe5O12/Pt bilayer. The observed magnetic field dependence is explained in a comprehensive model, based on two magnetic sublattices and taking into account magnetic field-induced modifications of the domain structure. Our results show that the SMR effect allows to readout the spin configuration and to investigate magnetoelastic effects in antiferromagnetic multi-domain materials. We demonstrate that the SMR amplitude scales with the sum of the absolute sublattice magnetizations in ferrimagnetic and antiferromagnetic materials. In alpha-Fe2O3/Pt bilayers, we find an unexpectedly large SMR amplitude of 2.5E-3, twice as high as for prototype Y3Fe5O12/Pt bilayers, making the system particularly interesting for room-temperature antiferromagnetic spintronic applications.
Read the full abstract

All authors Stephan Geprägs, Matthias Opel, Johanna Fischer, Philipp Schwenke, Matthias Althammer, Hans Huebl, Rudolf Gross

Mesoscale and Nanoscale Physics

Nonreciprocal Magnon Hanle Effect in Antiferromagnetic $\alpha$-Fe$_2$O$_3$

The precession of the magnon pseudospin about the equilibrium pseudofield, the latter capturing the nature of magnonic eigenexcitations in an antiferromagnet, gives rise to the magnon Hanle effect. Its realization via electrically injected and detected spin transport in an antiferromagnetic insulator demonstrates its high potential for devices and as a convenient probe for magnon eigenmodes and the underlying spin interactions in the antiferromagnet. Here, we observe a non-reciprocity in the Hanle signal measured in alpha-Fe2O3 using two spatially separated Pt electrodes as spin injector and detector. Interchanging their roles alters the detected magnon spin signal. The recorded difference depends on the applied magnetic field and reverses sign when the signal passes its nominal maximum at the so-called compensation field. Our findings unlock the high potential of antiferromagnetic magnonics towards the realization of electronics-inspired phenomena.
Read the full abstract

All authors Janine Gückelhorn, Sebastián de-la-Peña, Monika Scheufele, Matthias Grammer, Matthias Opel, Stephan Geprägs, Juan Carlos Cuevas, Rudolf Gross, Hans Huebl, Akashdeep Kamra, Matthias Althammer

Combinatorics

An Affine Semigroup from Orbifold Boundary Conditions: cut, phylogenetic and hierarchical models in the unit-weight sector, and weighted configurations beyond them

The equivalence classes of boundary conditions of a gauge theory on a two-dimensional orbifold are the fibres of a marginal map, indexed by an affine semigroup: one generator per alphabet label, graded by weight, embedded by its local data at the fixed points. This note identifies that semigroup. Without weights the configuration has a name and a literature, whose results about our cases are attributed here: over $\mathbb{Z}_2$ it is the cut configuration of an explicit graph in the sense of Sturmfels-Sullivant — the four-cycle for $T^2/\mathbb{Z}_2$, the wheel $W_4$ for $S^1/\mathbb{Z}_2\times S^1/\mathbb{Z}_2$ — verified as an equality of configurations; over $\mathbb{Z}_m$ with equal cone orders, the group-based phylogenetic model on a claw tree; with unequal orders, a mixed-order variant we do not find in the literature; for higher products, the binary hierarchical model of a cross-polytope boundary complex. The product orbifold's ring is a row of a 2008 table — codimension, degree, minimal generators, normality — every invariant of which our machinery reproduced without knowing of it. What none of the three covers is the alphabet with weights, which arise from induction to higher-dimensional irreducibles of a non-abelian space group and from conjugate-pair recombination over real or quaternionic ground. That sector is adjacent to, but not identified with, the non-abelian direction Sturmfels and Sullivant raised in 2005, and is where our contributions sit: gluing trees for the weighted alphabets and the orthogonal and symplectic columns, and the group-based model on the tripod, a complete intersection exactly when the finite abelian group has order at most three. The first group beyond $\mathbb{Z}_3$ separates local from global: the $\mathbb{Z}_4$ tripod is a complete intersection on the Zariski-open set the phylogenetics literature works in, and not globally.
Read the full abstract

2609.02630 · 2 Sep · 16 pages, 3 figures. Companion to Part IX-A, "The Alphabet of Orbifold Boundary Conditions", which determines the alphabet whose relations are computed here: https://doi.org/10.5281/zenodo.22254861 . This note's record, with every ancillary script and its archived receipt: https://doi.org/10.5281/zenodo.22254863

Materials Science

Colossal reversible conductivity switching by room-temperature oxygen-vacancy ordering in Aurivillius oxide films

Oxygen vacancies are central to the functionality of oxides, yet they typically exist as randomly distributed point defects, limiting the ability to precisely manipulate their collective behavior. Here, we report the room-temperature formation of a long-range-ordered oxygen-vacancy superstructure in single-crystalline Aurivillius-phase Bi2WO6 thin films via a mild nitrogen-plasma treatment. This structural transformation unlocks a colossal, reversible modulation of electrical conductivity by more than nine orders of magnitude, accompanied by a striking optical transition from transparent to black. Atomic-resolution imaging and spectroscopy reveal that the vacancies selectively order within the perovskite-like tungsten oxide layers, forming a coherent defect lattice that is absent in the pristine film. Oxygen-plasma treatment removes the vacancy superstructure and restores the initial state, whereas subsequent nitrogen-plasma treatment reconstructs it, enabling repeatable room-temperature switching between distinct structural, electronic and optical states. The phenomenon is also observed in another Aurivillius member, Bi2MoO6, suggesting its generality across the Aurivillius family. These findings establish a new paradigm for atomic-scale defect engineering - using gentle plasma chemistry to construct ordered defect lattices, opening avenues for reversible property modulation in complex oxides.
Read the full abstract

All authors Song Zhou, Songge Zhang, Lanting Shi, Ping Zhang, Na Li, Jiawei Huang, Bolin Meng, Chuangye Song, Shaoxiang Sheng, Yang Chai, Lede Xian, Jinxing Zheng, Guangyu Zhang, Kehui Wu

Systems and Control

Economic Model Predictive Control with Policy-Guided Terminal Ingredients

Conventional designs for model predictive control typically rely on terminal costs and constraints derived from a steady state to guarantee closed-loop stability and performance. However, this dependence on a steady-state assumption limits the applicability of this control method to systems in which such a fixed operating point is either not available or not desirable. This work introduces a novel framework, termed policy-guided MPC, to address this limitation. Our approach constructs terminal costs and constraints using a known sub-optimal control policy. Specifically, the terminal region is defined around a center determined by a rollout of the policy, and a penalty on deviation from this center is used to define the terminal cost. This method obviates the need for a steady state or reference trajectory. Closed-loop performance guarantees are established relative to the guiding policy, for both finite and infinite horizon problems. The effectiveness of the proposed framework is demonstrated through numerical simulations on an energy management example.
Read the full abstract

Soft Condensed Matter

Pure FENE Bond Potential for Soft Matter and Biological Simulations: Theory, HOOMD-blue Implementation, and Applications to Polymer, Colloidal, and Membrane Systems

The finitely extensible nonlinear elastic (FENE) potential is widely used as a bonded interaction in coarse-grained simulations of polymers, soft matter, colloids, and biological systems. In the classical Kremer–Grest framework, FENE bonding is combined with a short-range Weeks–Chandler–Andersen (WCA) interaction to provide finite bond extensibility together with excluded-volume repulsion. Although this combination is highly successful, it intrinsically couples bonded elasticity to the nonbonded interaction, limiting the ability to independently control these two contributions. Here, we introduce a standalone FENE bond potential in HOOMD-blue in which finite bond extensibility is implemented independently of the choice of nonbonded interaction. This formulation allows the same FENE bond potential to be combined with WCA, Lennard–Jones, or other pair interactions without modifying the bonded interaction itself. We demonstrate the utility of the standalone formulation in coarse-grained polymer chains, colloidal networks, and mesh-based biological membrane models. Across these systems, Pure FENE bonding without short-range excluded-volume stabilization produces pronounced structural contraction, whereas the addition of WCA repulsion suppresses this collapse and preserves finite, spatially extended structures. These results demonstrate that separating finite bond extensibility from steric interactions provides independent control over local bond mechanics and collective structural organization. The standalone FENE formulation therefore provides a modular framework for coarse-grained simulations in which molecular connectivity and nonbonded interactions represent distinct physical mechanisms.
Read the full abstract

Analysis of PDEs

Comparison principles and symmetry for subquadratic fractional $p$-Laplacian equations

This paper establishes a new comparison principle framework for the subquadratic fractional $p$-Laplacian, i.e.~$1 < p < 2$ under minimal regularity assumptions, that has remained a significant challenging issue due to the singularity of the operator. Our results provide the essential analytical tools required for the moving plane method in this setting. We prove first a weak comparison principle for $(-\Delta)_p^s u = f(u)$ in bounded domains with sufficiently small measure, where only the boundedness of the weak solution is required. More importantly, we establish a strong comparison principle for continuous weak solutions in the parameter range $s \in (0, \frac{1}{2})$ and $\frac{1}{1-s} < p < 2$. Our proof introduces a localized barrier function and does not require any Hölder regularity of the weak solution, nor any smoothness of the domain. This presents a substantial contrast over previous study, which relied heavily on Hölder or even $C^{1,1}$ regularity. As a direct application, we employ these comparison principles to prove the symmetry of weak solutions to $(-\Delta)_p^s u = f(u)$ under mild assumptions, which significantly extend existing symmetry theories for nonlocal quasilinear equations.
Read the full abstract

Networking

Integrating Wi-Fi into 3GPP 5G Network Slicing: An Experimental Prototype Study

Network Slicing (NS) is a fundamental pillar of 5G and beyond networks, enabling the provisioning of isolated, logical networks tailored to specific Quality of Service (QoS) requirements. While 3GPP standards comprehensively define slicing architectures over cellular access networks, the seamless integration of Non-3GPP technologies such as Wi-Fi into a unified slice instance remains an active area of investigation, particularly regarding empirical validation. This paper presents an end-to-end prototyping study that integrates 5G Standalone (SA) and Wi-Fi networks by adapting the Trusted Non-3GPP Gateway Function (TNGF) to extend NS to WLAN networks, enabling the unified management of Wi-Fi transmission resources. We implement a functional testbed leveraging an open-source 5G Core and an explicit Non-3GPP access to validate multi-Radio Access Technology (multi-RAT) slice operation. Our empirical results showcase the dynamic viability of multi-RAT slicing under varying bandwidth allocations and traffic steering policies, providing a concrete proof of concept for unified 3GPP and Non-3GPP service delivery.
Read the full abstract

All authors Nelson Ion de Oliveira, Marília Costa Muniz, William M. C. do Nascimento, João Pedro Brasil, Victor Farias Monteiro, Sérgio Barros, Maykon Silva, Augusto Venâncio Neto e Vicente A. de Sousa Jr

Software Engineering

Automated Vulnerability Injection in Smart Contracts Using Large Language Models

Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to build by hand. We propose an approach that uses Large Language Models (LLMs) to automatically inject vulnerabilities into Solidity smart contracts, and demonstrate it in a case study targeting 49 vulnerability types from OpenSCV. Injected contracts are validated through a multi-step pipeline checking compilation, execution, business logic, and the presence of the intended vulnerability. Applied to real-world contracts from SmartBugs, LLMs generate nearly 1,000 candidate variants; after deduplication and validation, 32 confirmed vulnerable contracts spanning 25 vulnerability types survive (a 16.58% survival rate). Surviving contracts concentrate in structurally simpler targets and vulnerability types with localized syntactic patterns. We report practical challenges including LLMs' non-determinism and the difficulty of preserving contract semantics. We then use the validated contracts to assess three static analyzers, revealing complementary and incomplete coverage profiles. Results show that LLM-based vulnerability injection is feasible, while exposing key limitations in scalability and diversity.
Read the full abstract

All authors Luca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira

Sound

Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction

Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-following TTS, where a system generates a new utterance that reflects a given direction relative to a reference utterance while preserving speaker identity and linguistic content. A key challenge is the lack of training data capturing such relative modifications. To address this, we propose a scalable pseudo-triplet construction pipeline that generates~(reference utterance, direction text, modified utterance) triplets. It generates controlled style variations using an impression-controllable TTS model and uses an LLM to produce natural language directions from estimated impression differences. Experimental results demonstrate that pseudo-triplets alone enable stable speaker-preserving modification, and that combining pseudo and recorded data further improves direction alignment while maintaining speaker similarity. Audio examples are available on our demo page https://ntt-hilab-gensp.github.io/IS2026pseudo/
Read the full abstract

Machine Learning

Source Distribution Estimation by Posterior Averaging

Simulation-based science often requires a distribution over simulator parameters whose push-forward reproduces a set of real observations: this is the source distribution estimation (SDE) problem. Existing methods fit the source against a likelihood surrogate trained once from a fixed proposal prior. Their objective is therefore stated only in terms of the surrogate instead of the true simulator, which may fail for inaccurate areas in parameter space where the surrogate was never trained. We instead solve SDE by expectation maximization: an E-step trains an amortized posterior on fresh simulations from the current source estimate, and an M-step refits the source to the average of that posterior over the observed data. We give two parameterizations, (1) separate source and posterior flows and (2) a single shared conditional flow. We evaluate our method on three benchmark tasks under both broad and misspecified initial priors. Both improve on existing fixed surrogate approaches and on iterated variants of each, most clearly on Lotka–Volterra, where no baseline falls below 0.96 data-space C2ST while our methods reach 0.64-0.68 in three of four initial-prior settings.
Read the full abstract

Commutative Algebra

Homology of non-matching complexes under edge additions and applications to their Stanley-Reisner ideals

For a bipartite graph $G$ and an integer $t\geq 2$, we study the $t$-non-matching complex $\NM_t(G)$ and its Stanley-Reisner ideal. We prove that, if adding an edge $e$ to $G$ preserves bipartiteness, the inclusion $\NM_t(G)\hookrightarrow\NM_t(G+e)$ induces an injection on reduced homology in degree $2t-3$. If $G$ contains a cycle of length at least $2t$, then $\NM_t(G)$ has Leray number $2t-2$, and its Stanley-Reisner ideal has regularity $2t-1$. We also obtain explicit lower bounds for certain graded Betti numbers and the projective dimension of this ideal. If $G$ contains a $2t$-cycle, we determine the maximal shifts of this ideal through homological degree $|E(G)|-2t+1$. For the complete bipartite graph $G=K_{r, s}$ with $2\leq t\leq r\leq s$, we determine the depth, projective dimension, all maximal shifts, and the unique extremal Betti number of the associated ideal, thereby settling a conjecture on facet ideals of chessboard complexes.
Read the full abstract

Artificial Intelligence

Collective creativity in hybrid societies

Generative AI is changing how cultural artifacts are created and circulated, and with it our understanding of creativity itself. Researchers disagree about whether these tools enrich or impoverish culture, and we argue that much of that disagreement comes from conflating two distinct components of creativity: novelty, a property of single artifacts, and diversity, a property of populations. We argue further that creativity in the context of generative AI is best understood as a property of hybrid collectives, or populations of interacting people and algorithms, rather than of individuals. AI-assisted ideation reliably raises the novelty of individual output while narrowing diversity in the aggregate, but this is not an inevitable consequence of putting machines in the loop. Because humans and models search in complementary ways, mixed groups can outperform and out-diversify groups of either kind alone, and machine-discovered solutions can enter human culture and persist there. What decides the outcome is composition: which agents are present, in what proportion, and how they are connected. The question is no longer whether AI helps or harms creativity, but which mixtures let individual gains accumulate without eroding collective diversity.
Read the full abstract

All authors Mason Youngblood, Katie Mudd, Manuel Anglada-Tort, Cameron Jones, Elena Miu, Diana Omigie, Margaret Schedel

Fluid Dynamics

Vortex promoters in MHD duct flow

We use 3D direct numerical simulations to study the effects of vortex promoters in liquid metal duct flow to sustain Q2D states which are formed in the presence of strong magnetic fields, such as those present in cooling blankets of fusion reactors. Both for electrically insulating and conducting walls. In case of insulating walls, disturbances are found to be sustained. For conducting walls, the disturbances may be extinguished immediately and replaced by a Walker- or Hunt-type flow with its own jet-detachment instability. Furthermore, we add heat transfer by imposing constant heat flux at the Shercliff walls. We classify and compare possible configurations with respect to their turbulent transport properties. For conducting ducts, no additional effect is observed. For insulating ducts in horizontal position, we observe a small effect. For vertical ducts, the buoyancy forces have a significant impact due to buoyancy-driven instabilities, which produce intermittent fluctuations. The analysis of the turbulent kinetic energy (TKE) and the Nusselt number show that flows with the largest TKE may not have the best heat transfer performance. This is caused by side jets removing heat faster than mixing the bulk flow. The buoyancy force and wall conductance ratio are found to play a key role in determining the flow structure. Part of our work is a parametric study at fixed Reynolds, Hartmann and Prandtl numbers, which allows us eventually to compose a phase diagram showcasing the different flow regimes.
Read the full abstract

All authors Andreu Queralt, Dmitry Krasnov, Yuri Kolesnikov, Jörg Schumacher