Peer Revenue Fully funded

Papers

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

All of arXiv

Wednesday 16 September

Geophysics

Period-Inverted Blast-Radius Normalization for a Non-Ablating Hypersonic Reentry Source Using OSIRIS-REx Capsule Infrasound

Elizabeth A. Silber

Cylindrical blast wave theory relates infrasound from hypersonic sources to energy deposition through a characteristic blast radius R_0, yet the normalization constant k in the scaling R_0 = k (E_0/p_0)^(1/2) differs by up to 40% across the formulations examined here. This uncertainty affects period-based source characterization for elevated atmospheric sources relevant to infrasound monitoring. Using infrasound from the OSIRIS-REx Sample Return Capsule reentry on 24 September 2023, observed periods at 39 stations spanning source altitudes of 44-62 km are inverted through a weak-shock propagation model to obtain period-inverted blast radii R_0,obs without prescribing a blast-wave normalization. Combining R_0,obs with aerodynamic drag energy yields a median k = 0.396, with a modified-bootstrap 95% interval of 0.378-0.474 when the reported period-measurement uncertainties are included. This result is consistent with the Sakurai (1965) and Jones et al. (1968)/Plooster (1970) normalizations, while Few (1969) lies outside the reference confidence interval. However, station-level k values exhibit significant along-trajectory structure (Spearman r_s = -0.84, p < 0.001), indicating that k_med is an ensemble-effective normalization rather than a station-invariant constant. The Mach-diameter approximation R_0 ~ M d_m overestimates R_0 by a factor of ~3.4 for this effectively non-ablating source. A period-based relation, R_0 = 23.99 tau - 0.73 (R^2 = 0.991, MAPE = 2.3%), provides a rapid blast-radius estimator whose residuals show no detectable altitude dependence. These results provide inverse calibration constraints and practical period-based source-characterization relations for OSIRIS-REx-like non-ablating hypersonic entries, while highlighting the need for multi-event validation before broader application.
Read the full abstract

Cryptography and Security

AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination

Matteo Golinelli, Idilio Drago, Matteo Boffa et al. (+2 more)

AI agents for security inspect web pages, source code, logs, configuration files, and command outputs. These environments may contain deceptive artifacts that influence the agent's behavior. We call this adversarial task contamination. Whereas prompt injection relies on attacker-supplied instructions, task contamination also includes non-instructional evidence, such as fake results and decoy endpoints. We present AgentLSD, a controlled framework for studying adversarial task contamination. AgentLSD uses Capture the Flag (CTF) challenges as its experimental environment. We inject trap artifacts, such as fake flags, misleading hints, decoy endpoints, and hidden cues, while preserving the intended CTF solution. The framework supports paired clean and trap-augmented experiments with deterministic trap generation, runtime injection, telemetry, and delivery verification. We evaluate six models on 11 web CTF challenges. In the clean condition, agents capture 41% of the flags, and no model solves every challenge. We then measure the impact of task contamination. Even when the agent still recovers the flag, traps increase the number of turns (+20) and reasoning tokens (+2k). Solve-rate effects are more heterogeneous, as some model-challenge pairs are largely unaffected while others follow decoys or submit wrong flags. These results show that clean CTF performance understates vulnerability to deceptive task evidence. AgentLSD isolates this effect and provides a reproducible benchmark for studying it. We release the framework, configurations, trap specifications, and raw traces.
Read the full abstract

All authors Matteo Golinelli, Idilio Drago, Matteo Boffa, Francesco Bergadano, Bruno Crispo

Genomics

STUART: Sequence Triage and qUAntification of Read Transcripts for Rapid Ionizing Radiation Exposure Assessment

Tomasz Strzoda, Lourdes Cruz-Garcia, Mustafa Najim et al. (+2 more)

Rapid medical triage following ionizing radiation exposure is critical for emergency management, yet traditional alignment-based bioinformatics are too computationally intensive for mass-casualty scenarios. To address this, we developed STUART (Sequence Triage and qUAntification of Read Transcripts), a mapping-free machine learning framework optimized for mobile biological dosimetry. Inspired by Natural Language Processing (NLP), the system converts raw sequencing reads into k-mer-based numerical profiles, completely bypassing standard alignment. While the architecture is universally applicable to any transcriptomic biomarker, this study focused on radiation exposure using the FDXR gene model. Evaluating Logistic Regression, Random Forest, and XGBoost, advanced signature selection strategies drastically reduced the initial 1024-dimensional feature space by over 98%. Highly robust performance - characterized by near-perfect balanced accuracy and F1-scores within the 95-100% range - was consistently achieved while retaining as few as 17 transcriptomic signatures. Crucially, learning curve analysis demonstrated that complete signal stabilization requires aggregating merely 1000 potentially related reads. Furthermore, external validation on an independent dataset yielded over 99% specificity, confirming the tissue-agnostic nature of the extracted signatures despite different cellular origins. The framework's exceptionally low data threshold enables a real-time, analyze-as-you-sequence diagnostic paradigm compatible with portable sequencers. By minimizing time-to-decision, this decentralized tool bridges the gap between advanced biomarkers and practical on-site biomonitoring, offering a scalable foundation for rapid epidemiological response and routine occupational radiation monitoring.
Read the full abstract

All authors Tomasz Strzoda, Lourdes Cruz-Garcia, Mustafa Najim, Christophe Badie, Joanna Polanska

Computer Vision

In-Context Robot Learning with VLM Agents

Dongzhou Cheng, Taoran Yi, Ye Fang et al. (+12 more)

Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No finite collection of demonstrations can cover every task and situation a robot will encounter, making the ability to learn from context at deployment essential for generalization. Such in-context learning (ICL), however, remains largely beyond the reach of existing robotic policies. The broad agentic capabilities of commercial vision-language models (VLMs), such as GPT-6 Astra, raise a compelling question: can these models learn from demonstrations, examples, and interaction feedback, then translate that information into executable and verifiable robot behavior from a new initial state without gradient updates or persistent changes to task-specific parameters? We introduce GPT-Policy, a general-agent framework for in-context robot learning. GPT-Policy integrates a context compiler that preserves task-relevant visual transitions, a VLM that proposes robot-tool actions, and a constrained controller that verifies and executes each action and reports its outcome. We evaluate its reliability and limitations through task success and efficiency metrics, matched comparisons across models, and controlled context ablations. In real-robot trials, human video demonstrations improve task completion even without robot action labels, while aligned action references yield further gains on contact-sensitive tasks. These findings position GPT-Policy as a step toward robot adaptation through in-context learning, providing an empirical foundation for translating the general-purpose capabilities of VLMs into physical behavior and clarifying the challenges that must be overcome for reliable deployment.
Read the full abstract

All authors Dongzhou Cheng, Taoran Yi, Ye Fang, Xingwu Zhang, Fan Feng, Yixuan Li, Gengxiong Zhuang, Rongze Wang, Shuai Yang, Wei Song, Weizhi Xue, Minyan Wu, Jie Gui, Jiaqi Wang, Tong Wu

Robotics

Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation

Guanhua Ji, Tianyu Li, Dayoon Suh et al. (+3 more)

Video generation models have advanced rapidly and can now synthesize plausible videos of robot manipulation from image and text prompts. Recent work extracts robot actions directly from such generated videos, but the result is purely kinematic and lacks force information, causing failures in contact-rich tasks where appropriate contact forces are essential for success. We present a pipeline that jointly leverages generated video and audio to derive motion trajectories and desired-force profiles. The force profile is shaped by the loudness of the generated contact sound, and we execute the resulting force-aware trajectories on a Franka robot using a closed-loop force regulator. We evaluate our pipeline on multiple tasks that require making contact and demonstrate successful zero-shot manipulation where a kinematic-only baseline fails. We also show that the pipeline can be used as a data generation engine to train policies that achieve the tasks in a closed-loop manner. Project website, videos, and dataset: https://dreamingcontactsound.github.io/
Read the full abstract

All authors Guanhua Ji, Tianyu Li, Dayoon Suh, Yuqian Zhang, Boyan Zhang, Nadia Figueroa

Data Structures and Algorithms

Maximum Matching Size for Bounded Arboricity Graphs in the Dynamic Graph Stream Model using $\tilde{O}(n^{2/3})$ space

Andrew McGregor

The paper presents a one-pass algorithm in the insert-delete graph stream model that returns a $(1+\varepsilon)(\alpha+2)$-approximation for the size of the maximum matching in a graph of arboricity at most $\alpha$. The algorithm uses $O(\varepsilon^{-4/3}\alpha^{4/3}n^{2/3} \text{polylog} n)$ space. For constant $\alpha$ and $\varepsilon$, this improves the best known previous space bound from $O(n^{4/5} \text{polylog} n)$ to $O(n^{2/3} \text{polylog} n)$. The algorithm is a linear sketch and requires no bounds on the number of deletions or on the arboricity of intermediate graphs.
Read the full abstract

Machine Learning

Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging

Pranaya Jajoo

Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on history. For every horizon $H \ge 3$, we construct two POMDPs with at most two latent states per stage, three actions, and a common logger with three memory states. Action coverage, belief coverage, and two behavior-marginal outcome-revealing conditions all have constants independent of $H$. Nevertheless, evaluating a known deterministic target policy to accuracy $1/8$ requires $\Theta((3/2)^H \log(1/\delta))$ logged episodes at confidence $1-\delta$, for $0 < \delta \le 1/4$, even when both candidate models are known. The mechanism is simple: a reset erases the unknown transition that determines the target value. We characterize the resulting statistical experiment exactly and obtain a matching optimal estimator. A directed two-lane gridworld realizes the construction, and trajectory simulations agree with its finite-sample prediction. The result establishes intractability for the history-dependent-logging, model-based case posed by Zhang and Jiang (2025, arXiv:2503.01134), under their behavior-marginal definition of revealing.
Read the full abstract

Computation and Language

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Hejia Geng, Zesen Huang, Haoyang Li et al. (+60 more)

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B/9B/4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE
Read the full abstract

All authors Hejia Geng, Zesen Huang, Haoyang Li, Wenbin Li, Koutian Wu, Zihan Zhou, Yuanbo Pang, Weihao Liu, Zigong Xu, Zhiping Li, Zongzheng Zhang, Chuanfei Dong, Jiankai Sun, Tianzhe Zheng, Fengyu Xie, Yue Ma, Yueheng Shi, Junkai Wang, Tong Xie, Zonglin Di, Xianrong Liu, Qucheng Gao, Yimin Liu, Jiaming Pan, Sheng Huang, Xiao-Han Ma, Lanqing Yuan, Zhenlin Zhu, Ziang Liu, Ziyang Xu, Kangkai Liang, Jiayi Xian, Zehong Zhao, Taigao Ma, Fuming Chang, Yuanzhe Hu, Liuwei Xu, Xianzhe Tang, Jingxu Xie, Peijin Zhang, Qiang Gao, Chengyi Xing, Zhe Zhao, Xi Wang, Leo Wang, Fang Wu, Jiacheng Ge, Weixuan Liao, Jungang Chen, Shuozhe Li, Yi Daniel Lu, Xu Pan, Shuhang Lin, Peihan Tu, Nan Liu, Zelin Tan, Yunze Xiao, Hao Xiao, Yaopeng Xing, Xing Meng, Zhenfei Yin, Yingcheng Wu, Ling Yang

Earth and Planetary Astrophysics

A Binary Flux Calibrator Reveals the Scientific Potential of Short-integration JWST MIRI Imaging to Directly Detect sub-Jupiter Exoplanets

Rachel Bowens-Rubin, Mary Anne Limbach, Alexander Venner et al. (+11 more)

We report the direct imaging detection of a stellar companion to HD 101452 (HIP 56925; Gaia DR3 5384905720847544192), an A star historically used as an infrared flux calibrator. The companion was identified from an asymmetry in the stellar PSF using short-integration (<1 min), noncoronagraphic JWST MIRI imaging from 15 - 25.5$\mu$m that was obtained as part of the absolute flux calibration program CAL 4496. We detect the stellar companion in four MIRI imaging filters at a projected separation of 1.3 arcsec with a mid-infrared flux ratio of approximately $27\times$ warranting its removal from the ensemble of JWST flux calibrator systems. This detection also demonstrates that noncoronagraphic MIRI imaging can recover companions at separations below $3\lambda/D$ when a reference star with a closely matched flux level to the science target is available. Using the measured contrast curves from the calibration data, we evaluate the predicted sensitivity achievable with similar short MIRI observations for nearby stars (<30 pc) that are of interest to the direct-imaging community with comparable brightness to HD 101452 (W4 ~ 6.8 mag). We find that integrations of only 17-42 s are be capable of detecting sub-Jupiter-mass planets at solar system-like separations around a subset of neighboring systems if the PSF subtraction is conducted with closely flux-matched references. These results demonstrate that minutes-length, noncoronagraphic MIRI observations can provide a powerful and efficient new avenue for exploring the cold giant planet population around nearby stars.
Read the full abstract

All authors Rachel Bowens-Rubin, Mary Anne Limbach, Alexander Venner, Kyle Franson, Emily K. Pass, Andrew Vanderburg, Kevin B. Stevenson, Logan Pearce, Taylor L. Tobin, Elisabeth Matthews, Aiza Kenzhebekova, Beth Biller, Ben J. Sutlieff, Klaus Subbotina Stephenson

Astrophysics of Galaxies

Massive Galaxy Halos Contain Less Inner Dark Matter Than Predicted

Yu-Chen Wang, Yingjie Peng, Xiaohu Yang et al. (+17 more)

The mass profiles of galaxy halos encode how baryons reshape dark matter distribution, yet direct observational constraints across the full radial range remain scarce. Here we combine stellar kinematics from MaNGA, H I dynamical measurements from ALFALFA, and independently calibrated halo masses of SDSS groups to statistically reconstruct the mass distribution of central galaxies over nearly two orders of magnitude in radius. We demonstrate that H I data alone do not provide reliable total halo mass estimates, necessitating an independent group-based halo-mass scale. Compared to the IllustrisTNG and EAGLE simulations, the observational profiles of low-mass halos are broadly consistent; in contrast, massive observed halos exhibit systematically lower dynamical masses at the H I radius, lower inner dark-matter masses, and lower central dark-matter fractions (about 4$\sigma$ difference in units of population scatter) at fixed total halo mass. After subtracting baryonic contributions, the inferred dark-matter profiles remain broadly consistent with an NFW form, but with lower effective concentrations than predicted for massive halos. These results suggest that the inner dark-matter content of massive halos has been reduced more significantly than predicted by current hydrodynamical simulations, plausibly due to long-term baryonic halo heating in massive systems.
Read the full abstract

All authors Yu-Chen Wang, Yingjie Peng, Xiaohu Yang, Luis C. Ho, Dingyi Zhao, Jing Dou, Hao Fu, Zeyu Gao, Qiusheng Gu, Fangzhou Jiang, Yukun Liu, Roberto Maiolino, Houjun Mo, Canpo Su, Bitao Wang, Kai Wang, Bingxiao Xu, Feng Yuan, Kunyao Zhao, Xingye Zhu

Earth and Planetary Astrophysics

An Updated Model for Epsilon Eridani b and Prospects for Imaging with the Roman Coronagraph

Jorge Llop-Sayson, Andre Fogal, James Mang et al. (+15 more)

Epsilon Eridani b, the nearest known Jupiter analog, has its orbit and mass constrained from radial velocity (RV) and absolute astrometry, and its atmosphere from JWST/NIRCam imaging upper limits in Sanghi et al. 2026. Here we follow up that work with a self-consistent model of Epsilon Eridani b that treats all available data within a single Bayesian framework. We extend the RV data with new measurements, update the treatment of the astrometry data with a new model, and include the NIRCam observations with a grid of evolutionary and atmospheric models. We find a mass of 0.91+-0.06 M_Jup and an orbit consistent with previous work. The imaging data helps constrain planet effective temperature, atmospheric metallicity and surface gravity. The constraints are dependent on model assumptions: for an atmosphere in chemical equilibrium, an otherwise low statistically significant feature in one of the epochs is recovered as the planet at high confidence. When assuming chemical disequilibrium, the posteriors exhibit a bimodal distribution, with one mode consistent with zero flux and the other coinciding with the flux of the tentative feature. Consistent with previous work, the clear atmosphere models are found to be viable at very enhanced metallicity, whereas the cloudy models yield more moderate values. Applying these models to the Roman Coronagraph, we find that the predicted reflected-light fluxes place every cloudy atmosphere our fit allows within the instrument's expected sensitivity. A non-detection would be very constraining: a final contrast sensitivity of 2e-9 would rule out all cloudy atmospheres under our model assumptions.
Read the full abstract

All authors Jorge Llop-Sayson, Andre Fogal, James Mang, William Thompson, Clarissa R. Do Ó, Aniket Sanghi, Isabela G. Huckabee, Laurent Pueyo, Charles Beichman, Geoffrey Bryden, Marie Ygouf, András Gáspár, Schuyler Wolff, Jarron Leisenring, Dimitri Mawet, Tiffany Meshkat, Caroline V. Morley, Jean-Baptiste Ruffio

Fluid Dynamics

IB-Flows: an open-source multi-GPU immersed boundary code for fluid-structure interaction

Giovanni Vagnoli, Martino Andrea Scarpolini, Fabio Guglietta et al. (+4 more)

We present IB-Flows, an open-source, multi-GPU solver for the direct numerical simulation of incompressible fluid-structure interaction (FSI) problems. The code couples a second-order finite-difference fractional-step Navier-Stokes solver on a staggered Cartesian grid with two immersed boundary methods: a Lagrangian method based on moving least-squares (MLS) interpolation and an Eulerian sharp-interface method. Rigid bodies are advanced with a quaternion-based Newton-Euler solver, while deformable surfaces embedded in three-dimensional flows are described by a structural solver based on the interaction potentials; a predictor-corrector scheme provides either loose or strong fluid-structure coupling. Non-Newtonian fluids with shear-thinning or shear-thickening rheology are handled through a strain-rate-dependent viscosity, and the same framework accommodates subgrid-scale eddy-viscosity models for large-eddy simulations of turbulent flows. The solver is written in CUDA Fortran with MPI domain decomposition, so that the fluid, interpolation and structural kernels are all executed on the GPUs, while the distributed transposes required by the Poisson and implicit solvers are further accelerated by the cuDecomp library through GPU-aware communication. Strong- and weak-scaling tests show near-ideal intra-node scaling and good multi-node efficiency. The solver is validated against a set of benchmark problems spanning wall-bounded turbulence, rigid-body and deformable-body fluid-structure interaction, and a biomedical application. IB-Flows is intended as a reproducible reference implementation for immersed boundary FSI simulations on modern GPU clusters and as a transparent platform to be used for tackling multiphysics problems.
Read the full abstract

All authors Giovanni Vagnoli, Martino Andrea Scarpolini, Fabio Guglietta, Joshua Romero, Massimiliano Fatica, Roberto Verzicco, Francesco Viola

Data Structures and Algorithms

A $2$-Approximation for Directed Feedback Vertex Set in Locally Semicomplete and Quasi-Transitive Digraphs

Sounak Modak

A directed feedback vertex set of a digraph is a set of vertices whose removal destroys all directed cycles. The Directed Feedback Vertex Set (DFVS) problem asks for such a set of minimum cardinality or minimum total weight. Although general DFVS admits no constant-factor approximation under the {Unique Games Conjecture}, tournaments admit a randomized factor-$2$ approximation due to Lokshtanov et al. [SODA'20]. We extend this guarantee to two broader classes of structured digraphs, both of which also contain sparse digraphs. Our first and main result is a randomized polynomial-time factor-$2$ approximation for weighted DFVS on locally semicomplete digraphs (LSDs), a class that strictly generalizes semicomplete digraphs and tournaments. To the best of our knowledge, this is the first non-trivial constant-factor approximation for DFVS on LSDs, even in the unweighted setting. Our second result is a randomized polynomial-time factor-$2$ approximation for weighted DFVS on quasi-transitive digraphs, improving the recent deterministic $9/4$-approximation of Ghorbani and Mnich~[ICALP'26]. The algorithm follows from a simple recursive application of our composition framework. The factor $2$ is optimal under the {Unique Games Conjecture}, since tournaments are subclass of LSDs as well as quasi-transitive digraphs.
Read the full abstract

Artificial Intelligence

Cognitive Extensions for Dual-Process Language Agents: Memory and Self-Reflection in Interactive Environments

João Meneses dos Santos and Arlindo L. Oliveira

Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective intervention. Both modules are implemented as feature-flagged extensions over the same execution substrate, enabling controlled ablations on ScienceWorld. Across four configurations—baseline, baseline+AMM, baseline+SRM, and the full system—the full system achieves the best mean final score (64.62), success rate (43.17%), and successful-step efficiency (19.33 steps), while SRM is the strongest standalone contributor. The results suggest that execution-time control is the dominant bottleneck in this setting, while episodic memory becomes most useful once the runtime loop is stabilized.
Read the full abstract

Human-Computer Interaction

EarStreAM: A Closed-Loop Earable System for Personalized Stress-Adaptive Meditation

Jonas Hummel, Luisa Faust, Elias Müller et al. (+7 more)

We present EarStreAM, a closed-loop earable system for stress-adaptive meditation that integrates in-ear physiological sensing with personalized, real-time intervention. Leveraging OpenEarable 2.0's multimodal sensing, EarStreAM continuously monitors physiological signals and detects elevated stress from heart rate and heart rate variability. Upon detection, the system initiates a personalized guided meditation generated by an LLM and adapted in real time to the user's stress state. The demo offers a hands-on experience of stress-adaptive meditation in two modes: a biosignal-adaptive meditation with optional stress induction to illustrate closed-loop adaptation, and a meditation-only mode focusing on EarStreAM's generative personalization capabilities. The demo highlights how in-ear sensing, closed-loop adaptation, and personalized generative meditation can be integrated into an earable system for real-time stress support in demanding office work contexts.
Read the full abstract

All authors Jonas Hummel, Luisa Faust, Elias Müller, Eva Bertog, Valeria Zitz, Marius Johannes Prill, Luca L. Bennardo, Luisa Weber, Tobias Röddiger, Michael Beigl

Complex Variables

Beyond Sendov's conjecture: the quadratic Tang–Zhang inequality

Teng Zhang

Very recently, Lech Mazur proved the celebrated Sendov conjecture, and Terence Tao subsequently distilled the main ideas of the proof in a blog post. In this paper, we establish a quantitative strengthening of Sendov's conjecture, namely the quadratic Tang–Zhang inequality. Let $p$ be a polynomial of degree $n\ge2$ whose zeros lie in the closed unit disk, and let $\zeta_1,\ldots,\zeta_{n-1}$ denote its critical points, counted with multiplicity. We prove that, for every zero $a$ of $p$, $$ \sum_{j=1}^{n-1}\frac{1}{|a-\zeta_j|^2}\ge n-1. $$ Moreover, equality holds if and only if $p(z)=c(z^n-\omega)$ for some $c\in\mathbb C\setminus\{0\}$ and $|\omega|=1$. We also provide a Lean 4 formalization of the main results.
Read the full abstract

Human-Computer Interaction

Affora: A Design System for Agent-Friendly Interfaces

Jin Gao

Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We present Affora, a design system that supports both readers while preserving visual freedom and familiar human workflows. Three controlled studies examine component implementations, visual variation, and interaction-design principles. Their findings inform guidance from individual components to complete sites, supported by reusable implementations and executable checks. Agent performance depends on the interaction meaning available through its interface representation; substantial visual variation remains possible when that meaning is preserved. Evaluation on independently authored interfaces shows gains where Affora addresses existing deficits, but limited effects where those deficits are absent or outside its coverage. A workflow case provides preliminary evidence of reduced interaction cost. Affora connects user experience and agent experience through a shared interface rather than a separate agent-only surface.
Read the full abstract

Artificial Intelligence

Flag Game: A Toy Model for Mechanistic Swarm Interpretability

Elizabeth Pavlova and Hidenori Tanaka

Emergent coordinated behaviors of AI agents are starting to present critical safety risks. A key phenomenon driving these behaviors is the rapid formation and spread of beliefs about the world, and mechanistic understanding is crucial for collective alignment. To this end, we introduce the Flag Game, a toy model for studying the mechanisms of collective belief formation. Concretely, a hidden country flag defines the ground truth, and each bounded agent directly observes only a private crop but can exchange beliefs and weigh social evidence from peers. Despite its simplicity, the Flag Game reproduces rich collective phenomenology: non-monotonic scaling of performance with population size, accuracy gains from social-awareness prompting and team diversity, and strong effects of organizational structure. In particular, we identify that collective belief collapse at small population sizes turns into collective belief polarization as the population grows. This polarization causes the performance decline at large population sizes, but creates diversity in collective beliefs. Finally, we dissect the mechanisms underlying collective belief collapse and polarization with two complementary approaches. We first introduce social circuit attribution, a technique to predict which agent, and what view, matters most to collective dynamics, and verify its predictions by causal interventions on agents, tracing how agent patching changes collective outcomes. However, the efficacy of causal interventions on agents decreases as the population grows. We therefore develop a statistical mechanical theory for larger populations and verify that it matches the empirical phase diagram. Together, these results take a first step toward mechanistic swarm interpretability, a science of how the properties of individual agents and their communication give rise to emergent collective behavior.
Read the full abstract

Combinatorics

A proof of Chvátal's conjecture via a sharp correlation inequality

Fan Chang, Hong Liu and Miao Liu

We prove Chvátal's conjecture, posed in 1972: every hereditary family of subsets of a finite set has a largest intersecting subfamily that is a star. More generally, we prove a sharp correlation inequality for increasing Boolean functions $f,g:\{0,1\}^n\to\{0,1\}$. Writing $g^*(x)=1-g(1-x)$, we show that $$ \sum_{\varnothing\ne S\subseteq[n]}\hat{g}(S)^2\max_{i\in S}\mathrm{Inf}_i[f]\le\frac{2\mathrm{Cov}(f,g)\mathrm{Cov}(f,g^*)}{\mathrm{Cov}(f,g)+\mathrm{Cov}(f,g^*)}. $$ When $g$ is antipodal, that is, $g=g^*$, this yields $\mathrm{Cov}(f,g)\ge\frac{1}{4}\min_{i\in[n]}\mathrm{Inf}_i[f]$, the correlation formulation of Chvátal's conjecture due to Friedgut, Kahn, Kalai and Keller.
Read the full abstract

Computer Vision

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

Meng'en Qin, Yinchen Liu, Mingxuan Cui et al. (+1 more)

Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is often manually selected during training. We propose a training-adaptive convolutional sparse coding framework for robust visual signal representation. Specifically, we unfold the CSC optimization with the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) and treat the sparsity coefficient as a differentiable variable jointly learned with the network parameters. From the information bottleneck perspective, this coefficient controls the trade-off between information retention and compression: the sparsity term promotes compact representations, while the reconstruction term together with task loss preserves task-relevant signal content. We further introduce a label-free post-training strategy that adjusts the compression strength for corrupted inputs with the main network parameters fixed. Experiments on CIFAR and ImageNet demonstrate competitive clean-data recognition and greatly improved robustness under different input perturbations.
Read the full abstract

All authors Meng'en Qin, Yinchen Liu, Mingxuan Cui, Youlu Xing

Number Theory

The non-spherical sup-norm problem for $\mathrm{GL}(n)$ and generalized spherical functions

Valentin Blomer, Gergely Harcos, Péter Maga et al. (+1 more)

We solve the sup-norm problem for minimal weight vectors in an arbitrary cuspidal representation $\pi$ of $\mathrm{GL}(n,\mathbb{Z})\backslash\mathrm{GL}(n,\mathbb{R})$ with a uniform power saving bound in terms of the archimedean data of $\pi$, including its spectral parameters and the dimension of its minimal $K$-type. As a key ingredient, we establish new uniform decay bounds for generalized spherical functions.
Read the full abstract

All authors Valentin Blomer, Gergely Harcos, Péter Maga, Djordje Milićević

Differential Geometry

Finite index constant mean curvature hypersurfaces in space forms of dimension at most seven

Zihao Wang

We study complete two-sided constant-mean-curvature hypersurfaces of dimensions $2\le n\le6$ and finite Morse index in simply connected space forms. In the round sphere the immersed domain is compact; in Euclidean space every noncompact example is minimal; in hyperbolic space of curvature $-1$ we obtain compactness under explicit dimension-dependent mean-curvature thresholds, from $H^2>1$ for surfaces to $H^2\ge5/3$ in dimension six. The conclusions also hold for the volume-constrained index, without properness, volume-growth, or curvature-bound assumptions. A common Green-function argument uses explicit rational combinations of eight identities and the stable Bernstein theorem of Hong-Li-Wang. Stable hyperbolic tubes show that no mean-curvature threshold independent of dimension can give compactness in all dimensions.
Read the full abstract

Computer Vision

Track, Articulate, Act: Generating Articulation from Casual Human Videos

Jiaming Zhang and Homanga Bharadhwaj

Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes in object state. In this work, we study articulated objects such as doors, drawers, cabinets, laptops, ovens, and hinged containers that are ubiquitous in daily life and present unique challenges for embodied interaction. These objects cannot be represented by a single pose; their motion depends on the underlying parts and joints. We introduce a real-to-sim framework that reconstructs a simulation-ready articulated object and hand-object interaction from a casual monocular RGB video, without RGB-D or multi-view input, prior scans, manually specified joints, or robot demonstrations. Our key insight is that dense 3D point tracks provide an embodiment-agnostic articulation cue: points on the fixed link remain approximately stationary, while points on the moving link follow coherent revolute or prismatic motion. Our method segments the links, estimates the joint and its state trajectory, reconstructs an articulated asset, and aligns the recovered 3D hand motion with the object. Central to our approach is a modular recipe that repurposes powerful pretrained models for single-image 3D reconstruction, mesh segmentation, and 3D scene flow, connecting their predictions through explicit geometric reasoning to infer articulation. We use the reconstructed articulated object and the human hand trajectory to replay interactions through contact in MuJoCo. The framework shows how pretrained vision models and explicit motion reasoning can turn casual human videos into articulated object models suitable for downstream embodied interactions. https://track-articulate-act.github.io/
Read the full abstract

Data Structures and Algorithms

On the Strong Matroid Secretary Conjecture and Beyond

Hamed Abdi, Kiarash Banihashem, MohammadTaghi Hajiaghayi et al. (+1 more)

The strong matroid secretary conjecture asserts that every matroid admits a $1/e$-competitive secretary algorithm, matching the classical single-choice guarantee. We formulate a finite linear program whose value is the optimal ordinal competitive ratio of any fixed matroid; for all matroids of positive rank on seven elements and nearly all on eight, this value exceeds $1/e$. The same computations suggested that the optimal ratio is monotone under truncation of the matroid; we prove this for uniform matroids, where the ratio is strictly increasing in the rank, and refute it for a graphic matroid. Guided by this evidence, we prove the conjecture for every linear matroid, a class that includes graphic matroids, regular matroids, laminar matroids, and gammoids, giving a $1/e$-competitive ordinal secretary algorithm. The algorithm maintains bounds on the expected intersection dimension of the accepted span with every ambient subspace. Uncrossing and separation show that these bounds can be preserved while admitting each current greedy-basis element with a prescribed probability and the construction uses finite linear programs. For every matroid, we also give a single-sample prophet algorithm with competitive ratio $1/2$ in any fixed arrival order independent of the samples and values. Its output, including the selected values, has exactly the law of an independent fair thinning of an optimum from a fresh product draw. The algorithm uses $O(n^2)$ independence queries on $n$ elements. Both constants are tight in their respective models. We also give a self-contained black-box reduction that converts a single-sample prophet ratio $\alpha$ into a secretary ratio $\alpha^2/16$, preserving polynomial running time. Our single-sample algorithm consequently yields a $1/64$-competitive ordinal secretary algorithm for arbitrary matroids.
Read the full abstract

All authors Hamed Abdi, Kiarash Banihashem, MohammadTaghi Hajiaghayi, Danny Mittal

Chemical Physics

Floquet-Plasmon Enhanced Charge Transfer at Catalytic Interfaces

Annabelle Canestraight, Phillip Christopher and Vojtech Vlcek

Plasmonic excitation of metallic nanostructures can generate energetic carriers capable of transferring charge into nearby adsorbed molecules, providing a possible pathway for driving chemical transformations. In many theoretical descriptions of this process, charge transfer is determined by the equilibrium electronic structure of the molecule and substrate together with the time-dependent carrier distribution produced during plasmon decay. However, the intense transient electric fields associated with localized surface plasmons can also dynamically perturb the molecular electronic structure itself on ultrafast timescales. In this work, we investigate how these time-dependent fields modify the molecular spectral function and influence charge injection at catalytic interfaces. Using a model of CO2 adsorbed on Au(111), we compute the real-time molecular Green's function within a correlated frontier-orbital active space under plasmon-like driving. We find that the driving field rapidly produces transient Floquet-type replica bands in the molecular density of states, opening additional resonant pathways for hot-carrier injection that are absent without external driving or in time-local descriptions. Coupling the evolving molecular spectrum to a time-dependent hot-electron distribution described within a two-temperature Sommerfeld framework, we predict large enhancements in quasiparticle spectral overlap that governs injection during plasmon dephasing. These results suggest that dynamically generated non-equilibrium spectral structure may play an important role in plasmon-assisted catalysis and provide a framework for studying driven catalytic interfaces beyond static electronic structure descriptions.
Read the full abstract

Quantum Physics

Comparing magic state cultivation methods using matrix product states

Tom Hartweg and Asier Piñeiro Orioli

Magic state cultivation prepares high-fidelity magic states at low expected space-time costs; however, the exact performance of some schemes is unsettled due to the difficulty in simulating non-Clifford circuits. Here, we use matrix-product states (MPS) based methods to compute the exact performance of two types of fold-transversal cultivation schemes: (i) the Sahay et al method based on the regular surface code S gate, and (ii) a method we propose based on a partially fault-tolerant fold-transversal S gate. We show that for the former protocol at $d=5$, the $|T\rangle$ output reaches similar logical error rates to the $|S\rangle$ output, traditionally used as a cheap full Clifford proxy. This contrasts with the $\sim10\times$ discrepancy reported for the $d=5$ colour-code scheme of Gidney et al. We also find that our new $d=5$ scheme has $\sim1.3\times$ lower expected space-time cost while still reaching $10^{-9}$ logical error rate. We show that MPS and Clifford-augmented MPS (CAMPS) perform on par with or even better than the recently introduced near-Clifford simulator Clifft on the hardest $d=5$ regular surface code scheme. Additionally, to speed up simulation, we propose a new pre-screening method based on simple Pauli propagation, lowering by up to three orders of magnitude the required number of exact simulations, and use several simulator-agnostic sampling methods such as subset sampling.
Read the full abstract

Dynamical Systems

Singularity of harmonic measure for finitely supported random walks

Petr Kosenko and Giulio Tiozzo

In this paper we affirmatively resolve the singularity conjecture for finitely supported non-degenerate random walks on cocompact Fuchsian groups. The method we use is based on constructing a pair of geodesic currents, one for the Lebesgue measure and one for the random walk measure, and checking that they are different by using Fourier analysis on the boundary.
Read the full abstract

Combinatorics

Hamiltonicity in graphs defined by primes and primitive elements

Yue-Feng She

A prime circle of order $2n$ is a circular ordering of $1,\ldots,2n$ such that the sum of every two adjacent terms is prime. We prove that a prime circle exists for every sufficiently large $n$. The proof is based on a perfect matching and robust expansion. We also study Hamilton cycles in graphs and digraphs defined by primitive sums and differences over finite fields. In particular, the primitive-sum graph on $\F_q$ is Hamiltonian for every prime power $q>18\,888\,871$, and for the graph on a full prime field $\F_p$, the bound improves to $p>61$.
Read the full abstract

Computation and Language

Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry

Peter Potash

We evaluate six frontier language models on the two-agent $\log_2 N$-Questions game (Potash et al., 2019) to measure self-communication across an information asymmetry. A questioner with access to $N$ candidate Wikipedia lead paragraphs ($N = 4$ to $1024$) must identify a secret target using exactly $\log_2 N$ binary questions answered by an agent from the same provider that sees only the target. Across 408 games, win rate decays cleanly as a geometric power of horizon length, $p^{\log_2 N}$ ($p \approx 0.93$). Per-round failure rates are flat across the horizon, indicating that errors compound because more rounds must succeed rather than because individual rounds grow harder. Adjudication across three independent judges shows that losses divide between single-agent answer errors and discrimination failures, which become undetectable and unrecoverable under the two-agent structure rather than from channel breakdown. Claude Opus 5 lags behind due to systematic false-negative answers (82% answer errors), whereas the five leading models (GLM-5.3, GPT-5.6 Sol, Grok 4.6, Gemini 3.8 Flash, and Kimi K3) are closely clustered. Maximizing information gain requires structural partitioning (e.g., splitting on document titles), and neither reasoning-token expenditure nor API cost correlates with success ($r = -0.05$), highlighting communicative reliability as a distinct bottleneck from inference compute.
Read the full abstract

Materials Science

Divergence between long- and short-wavelength magnon damping in spinel ferrites

Christopher T. Parzyck, Octave Duros, Hari Paudyal et al. (+14 more)

The realization of practical, high-speed magnonic devices requires engineering magnetic materials with low dissipation over wide frequency ranges. While optical and microwave probes are used to infer the damping of low energy/long wavelength modes, the degree to which these $q\sim0$ properties translate into higher-energy, finite-momentum modes remains an important open question. Here, we utilize a combination of ferromagnetic resonance (FMR) and resonant inelastic x-ray scattering on spinel ferrites Li$_{0.5}$Al$_x$Fe$_{2.5-x}$O$_4$ to probe magnons in both the short- and long-wavelength limits. We observe that aluminum substitution both markedly reduces the magnon bandwidth and drastically shortens the high-$q$ magnon lifetimes, in sharp contrast to the ultralow magnon damping inferred from FMR. These findings demonstrate a disparity between how non-magnetic substituents impact magnon damping in the long- and short-wavelength limits, providing a new perspective for assessing candidate materials for magnonic devices.
Read the full abstract

All authors Christopher T. Parzyck, Octave Duros, Hari Paudyal, Noah M. Edmiston, Katya Mikhailova, Lerato Takana, Daisy O'Mahoney, Sauviz P. Alaei, Daniel J. Foster, Hiroki Suga, Naoya Kurahashi, Jun Miyawaki, Michael E. Flatte, Georgi Dakovski, Yuri Suzuki, Durga Paudyal, Wei-Sheng Lee