Peer Revenue Play credits. Real papers.

Papers

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

All of arXiv

Tuesday 8 September

Human-Computer Interaction

Healthcare Utilization, Chronic Condition Management, and Workplace Functioning Among Users of a Purpose-Built Mental Health AI (Ash): Cross-Sectional Study

Mental health challenges can exacerbate physical symptoms and complicate management of chronic conditions. Purpose-built artificial intelligence (AI) tools may offer scalable support for co-occurring mental and physical health concerns. This cross-sectional study compared past-6-month healthcare utilization, chronic condition management, physical health behaviors, mental health change, and workplace functioning between active (n = 169) and non-users (n = 73) of a mental health AI (Ash). Participants had at least one chronic condition (e.g. hypertension, chronic pain). Binary outcomes were modeled as adjusted risk differences (RDs) using linear probability models and continuous outcomes were modeled with linear regression; all models were adjusted for hypertension. Relative to non-users, active users were more likely to report improved mental health (61.4% vs. 34.3%; RD = 0.27), higher medication adherence (91.7% vs. 76.4%, RD = 0.15), fewer skipped or delayed chronic-condition care activities (b = -0.44), and were less likely to report repeat urgent care visits (9.5% vs. 23.3%; RD = -0.15) and monthly-or-more absenteeism (24.2% vs. 45.2%; RD = -0.20, all ps < .05). Findings provide preliminary evidence that use of purpose-built AI may be associated with positive symptom-based and utilization outcomes for those managing co-occurring mental and physical concerns.
Read the full abstract

All authors Kristen M. Van Swearingen, Thomas D. Hull, Jeffrey Swigert, Caitlin A. Stamatis

Information Theory

On Weighted Mathai-Haubold Entropy Measures

In this paper, we propose weighted Mathai-Haubold entropy along with their residual and past versions and study their properties. We develop aging classes based on the weighted Mathai-Haubold residual and past entropy measures. Also, some inequalities related to the three proposed measures are discussed. Non-parametric estimators of the proposed measures are introduced and their properties are investigated. Performance of this estimator is evaluated by means of bias and mean squared error using Monte-Carlo simulations.
Read the full abstract

Game Theory

Strengthening Proportionality in Participatory Budgeting with Additive Utilities

Proportional representation is a central goal in participatory budgeting, where voters select public projects subject to a shared budget. Full justified representation (FJR) accounts for groups whose members may value different projects, but computing an FJR outcome is strongly NP-hard for additive utilities. We show that FJR up to one project can be achieved in polynomial time for arbitrary nonnegative additive utilities and project costs. Our approach extends Residual-Budget Greedy and satisfies a stronger fractional axiom that can also be verified in polynomial time. For approval utilities, this axiom coincides with FJR+, providing exact FJR in that setting. We further show that every feasible completion of the algorithm's selected set preserves the representation guarantee, providing flexibility in allocating the remaining budget. In particular, we give a completion that ensures priceability at the original budget. For unit-cost projects, we strengthen the representation guarantee to the Droop quota and combine it with priceability whenever there are enough positively valued projects to fill the budget.
Read the full abstract

Information Retrieval

Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems

Evaluating first-stage retrievers in large-scale production RAG requires a benchmark that pairs a large-scale corpus with a large set of agent-reformulated search queries based on real user queries and their conversation threads, and that labels many relevant documents per query. No existing public benchmark evaluates this setting: large-scale collections typically provide only a small number of evaluation queries, whereas benchmarks with many queries generally contain only millions of documents. Moreover, most benchmarks assess human-written queries, while the first-stage retrievers in agentic RAG pipelines serve machine-written reformulations whose distribution differs from human search behavior. To overcome these evaluation gaps, we introduce Q2D-Web (Query2Doc-Web), a large-scale agentic retrieval benchmark consisting of a 190M-document web corpus and 70k agentic search queries in ten languages, reformulated from real-world user queries in production systems. Q2D-Web provides three sets of fixed relevance judgments: agent citations, production rankings, and a combined set that unions both signals and adds LLM-based judgments of unlabeled pooled documents to reduce false negatives. We benchmark 13 retrievers including lexical, dense, and late-interaction models and find that their relative ordering is largely insensitive to the choice of judgment set, while diverging substantially across topical domains, query languages, and query types. To enable fast evaluation, we also study subcorpus sampling as an approximation to full-corpus evaluations. Retaining a third of the corpus, selected by reciprocal rank fusion over pooled retriever runs, preserves the full-corpus model ranking under the combined judgments while raising absolute Recall@1000 only by 4 to 7 points. The public leaderboard is accessible under: https://huggingface.co/spaces/perplexity-ai/q2d-web-leaderboard
Read the full abstract

All authors Maximilian Schall, Sedigheh Eslami, Markus Krimmel, Antoine Chaffin, Louis Milliken, Bo Wang, Denis Bykov

Computer Vision

FRAME: Factored Retrieval via Attribute Readouts for Object-Centric Scene Memory

Language-guided robots need persistent scene memories to follow instructions, revisit objects, and resolve references to objects encountered over time. While much of language-guided scene-memory retrieval has emphasized spatial or relational references, many everyday object references specify objects by multiple persistent attributes, such as category, material, size, or surface appearance. We formalize this problem as attribute-compositional retrieval, where a fixed object-centric scene memory is queried with natural language to retrieve the object satisfying the requested attributes. To investigate this capability directly, we introduce a controlled evaluation protocol with fixed scene memories and attribute-defined targets, separating retrieval from perception and annotation ambiguities. We then propose FRAME, which turns language into query-relevant attribute weights, uses learned readouts to estimate per-attribute evidence from object embeddings, and ranks objects by aggregating this evidence according to the query. Across held-out scenes and object assets, FRAME outperforms representative scene-memory retrieval baselines while reducing post-decomposition object scoring to lightweight matrix-vector computation. These results position attribute-compositional retrieval as a complementary scene-memory capability for language-guided robots, showing that persistent object attributes can be exposed as composable evidence for accurate and efficient multi-attribute retrieval.
Read the full abstract

All authors Woosang Jeon, Sanghyeok Choi, Minwoo Kim, Taehyun Jung, Taehyeong Kim

Combinatorics

A $(\log n)^{1/4}$ Bound for the Komlós Problem

Let $A\in\mathbb{R}^{m\times n}$ have columns of Euclidean norm at most one. We prove that $\operatorname{disc}(A)\le2395\left(1+\log_+\frac n9\right)^{1/4}+2\sqrt2$. Here $\log_+t=\max\{0,\log t\}$. Building on Bansal and Jiang's affine spectral independence framework, we remove the $(\log\log n)^{7/4}$ factor from their bound. The fourth root comes from balancing the logarithmic decrease in the alive dimension against the fourth power of the row thresholds. Historical exponential sums control the covariance budget across size classes with summable thresholds. An exact threshold-sum certificate gives the coefficient $2395$, and rounding at most eight remaining fractional coordinates costs $2\sqrt2$. The finite construction also gives partial colourings from any prescribed starting point and at any prescribed depth, preserving existing signs. We formalize the partial- and full-colouring theorems in Lean, including the finite trajectory, exact threshold sum and final rounding, with Bansal–Jiang Theorem A.4 as the sole external research theorem assumption.
Read the full abstract

Game Theory

The Complexity of Membership, Uniqueness, and Counting for Optimal Proportional Approval Voting Committees

Proportional Approval Voting (PAV) chooses committees that maximize a sum of harmonic utilities. We study the set of maximizing committees: whether a candidate belongs to some or all of them, whether the optimum is unique, and how many optima exist. When the committee size is part of the input, the three decision problems are $\Delta_2^\mathrm{P}$-complete. Uniqueness remains hard for instances with at most two optimal committees. Counting optimal committees is $\#\!\cdot\!\mathrm{OptP}$-complete under metric reductions: every function $f$ in this class reduces to an election with exactly $f(x)+1$ optimal committees. The reductions encode satisfying assignments directly as committees and use harmonic marginal rewards to realize binary objectives with polynomially many voters. Each satisfying assignment has a unique committee representation, and fixed clause ballots give these representations the same clause score. We also prove Turing equivalence with $\#\mathrm{SAT}$ and show that membership of the counting problem in $\#\mathrm{P}$ would imply $\\mathrm{NP}=\mathrm{coNP}$.
Read the full abstract

Applied Physics

Dynamic Sensing via Photomodulated Gas Desorption in Plasmonic Nanoparticle Chemiresistors

Quasi-static sensing, i.e., measurement of a sensor signal change induced by analyte presence with respect to a baseline signal observed in a reference gas beforehand, is the state of the art for qualitative and quantitative analyte identification in chemiresistive sensing. However, this approach is prone to baseline drift and, especially for inexpensive miniaturized point-of-care sensors, repeated calibration with reference gas is not feasible. To access reliable baseline information, active switching between analyte and reference gas would be required, causing a limitation for miniaturized implementation. Dynamic excitation of sensors offers an alternative: Via external stimuli the sensor is reversibly driven out of equilibrium in a controlled way, and the resulting transient sensor response, which is dependent on analytes present, is recorded and interpreted. Correlation of excitation and response signals can reduce effects of baseline drift and furthermore, dynamic features in sensor responses may contain valuable information. Especially light activation is a powerful and potentially miniaturizable approach to agitate sorption processes and therefore induce dynamics. In this work we report photothermal heating of hybrid, chemiresistive gold nanoparticle composites via LED excitation matching the plasmon resonance, to dynamically shift the analyte sorption equilibrium and induce dynamic sensor responses in a highly controlled way. We demonstrate that these sensor responses enable the detection of volatile organic compounds (VOC) via interpretation of differential signal components and that this approach improves the chemiresistors' baseline stability.
Read the full abstract

All authors Lukas Mielke, Dahee Heo, Gabriele Carelli, Hendrik Schlicke

Probability

Phase transition for strongly correlated percolation models on supercritical Bernoulli clusters

We consider the level sets of the Gaussian free field and the vacant set of random interlacements, both defined on a typical realization of the infinite cluster of supercritical Bernoulli bond percolation on $\mathbb{Z}^d$, $d \geq 3$. We prove that in the entire supercritical regime of Bernoulli bond percolation, both the level sets of the Gaussian free field and the vacant set of random interlacements undergo non-trivial percolation phase transitions at deterministic critical levels. A key aspect of the proof is the development of certain quenched controls over tree embeddings, permitting the application of a static renormalization scheme in the presence of spatial irregularities, which may be of independent interest.
Read the full abstract

Trading and Market Microstructure

The Double-Edged Sword of Short-Selling Bans

We develop a theoretical model that endogenizes the regulator's decision to impose short-selling bans to prevent large stock price declines. Empirically, we test the model's predictions using the cross-sectional variation in short-selling restrictions implemented across European countries in 2020. Consistent with our model, we find that bans had a detrimental effect on liquidity and failed to support the average price levels, but were effective in limiting large price drawdowns. Finally, we show that the effectiveness of the bans depends on the share of informed stockholders, a central variable in our framework, thus informing the design of more effective regulatory responses.
Read the full abstract

All authors Pasquale Della Corte, Robert Kosowski, Dimitris Papadimitriou, Nikolaos P. Rapanos

Numerical Analysis

High-Order Discontinuous Cut Finite Element Methods for Scalar Hyperbolic Conservation Laws

In this paper, we present a family of high-order cut finite element methods based on the discontinuous Galerkin (DG) framework for scalar hyperbolic conservation laws on complex domains. Building on our previous work, we develop a multidimensional formulation that combines macro-element stabilization with flux limiting to obtain a scheme that preserves the maximum principle and remains robust with respect to arbitrary boundary cuts of the background mesh. The physical domain is embedded in a regular background mesh, which may produce arbitrarily small cut cells. To avoid the severe time step restrictions typically associated with such cells, ghost penalty stabilization terms are added on interior facets of macro-elements. The resulting method exhibits stability and accuracy properties similar to those of standard DG methods on fitted meshes. An $L^2$-stability result is derived for the semi-discrete scheme under both periodic and inflow-outflow boundary conditions. To enforce the maximum principle and suppress nonphysical oscillations, we adapt limiter techniques from standard DG methods to the CutFEM setting by defining limiting parameters on macro-elements. In particular, we present a macro-element-based parameterized flux limiter together with adaptations of the Zhang-Shu bound-preserving limiter and the Barth-Jespersen slope limiter. Numerical experiments in two and three spatial dimensions demonstrate optimal convergence orders, preservation of the maximum principle, and accurate shock capturing without spurious oscillations, even for challenging cut configurations involving very small-cut cell intersections.
Read the full abstract

All authors Pei Fu, Gunilla Kreiss, Zelin Xin, Sara Zahedi

Computer Vision

Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts

Cancer segmentation models can fail silently, generating plausible but incorrect masks that risk missed findings or unnecessary biopsies. A critical question arises: Do AI models "know" when they are wrong, and if so, can we use the signal to predict their own failures? Humans do have a "Feeling of Error" (FOE): a spontaneous sense of unease that flags a potential error during thinking. We investigate whether cancer segmentation models exhibit an analogous internal signal. Unlike output-level cues (e.g., prediction confidence or uncertainty), which offer no insight into why a failure occurs and suffer from a sensitivity-quality tradeoff where high detection sensitivity could degrade overall segmentation quality. We instead propose to capture the model's FOE from its inner workings. Using mechanistic interpretability tools, specifically Sparse Autoencoders, we decompose internal neural activations into a dictionary of human-interpretable concepts and show that failure cases exhibit a distinct latent signature: fewer active concepts with lower activation magnitudes compared to successful segmentation. By training a classifier on these concept activations, we achieve accurate failure detection along with explanations for the model's mistakes. Experiments on prostate, pancreatic, and brain cancer segmentation demonstrate that our approach outperforms output-based methods in failure detection while preserving segmentation quality.
Read the full abstract

All authors Mengmeng Ma, Yunxiang Peng, Tang Li, Lu Lin, Binsheng Zhao, Oguz Akin, Xi Peng

Materials Science

Controlling Hydrogen Isotope Retention at Helium Cavities through Radiation-Induced Segregation in Fusion Steels

Hydrogen isotope retention in plasma facing and structural alloys is a central materials challenge for deuterium-tritium fusion. Motivated by ion beam irradiation experiments and first principles calculations, we identify an irradiation-enabled mechanism whereby solute segregation to defect sinks enhances hydrogen isotope trapping. Triple-ion irradiation of reduced activation ferritic-martensitic steel F82H reveals pronounced segregation of Cr and Ta to cavity surfaces. Density functional theory shows that these segregants markedly increase H stability at cavities by strengthening binding energies and increasing migration barriers, leading to substantially higher attention. The effect originates from solute-tuned electronic structure: Ta promotes strong H 1s-metal d orbital hybridization, whereas Cr shifts the surface d-band toward a more favorable bonding configuration. These findings provide an atomistic link between irradiation-induced segregation and elevated-temperature hydrogen isotope retention and alloy chemistry routes to control tritium inventory in fusion environments.
Read the full abstract

All authors Lihao Shi, Logan N. Clowers, Qing Peng, Gary S. Was, Fei Gao

Optimization and Control

Equilibria for Time-inconsistent Regular-singular Control Problems with Non-exponential Discount

This paper studies a time-inconsistent mixed regular-singular control problem in continuous time with non-exponential discount. We seek time-consistent equilibria in an intrapersonal game framework and propose two novel definitions of regular-singular equilibrium where both regular and singular controls are unified via control laws. The standard equilibrium definition allows simultaneous perturbations of both controls, while a mild definition restricts perturbations to one control at a time. Verification theorems providing sufficient conditions are established for both definitions. We illustrate the applicability of the theory through the effort and dividend problem. First, a mild equilibrium is constructed, yet not a standard equilibrium, highlighting the distinction between the two definitions. Moreover, we derive semi-explicit threshold-type equilibria under both a mixture of exponential discount functions and a pseudo-exponential discount function. In both cases, the convexity of the value function is rigorously established, the equilibrium conditions are verified, and the existence of the effort and dividend thresholds is proved. Numerical results reveal the impacts of exogenous parameters on the effort and dividend thresholds and the equilibrium value function, along with their economic implications.
Read the full abstract

Algebraic Geometry

The derived length of subgroups of the Cremona group

We prove that the maximal derived length of a solvable subgroup of the plane Cremona group over $\mathbb C$ is equal to $5$. The main difficulty is the case of subgroups containing loxodromic elements. To treat this case, we prove that the maximal derived length of a finite solvable subgroup is $4$ and establish a centraliser theorem: the centraliser of a finite solvable subgroup of derived length $4$ contains no loxodromic element. The proof of the centraliser theorem relies on Blanc's classification of maximal algebraic subgroups and then uses equivariant Sarkisov theory, orbit estimates, superrigidity, and fixed curves of genus at least two.
Read the full abstract

High Energy Physics (Phenomenology)

How to choose a good rational basis for elliptic Feynman integrals?

Representing multi-loop scattering amplitudes as linear combinations of multivalued transcendental functions with process-dependent rational coefficients has long been understood to be advantageous. In general, these transcendental functions satisfy a system of differential equations with coupled homogeneous blocks. When these coupled blocks can be removed through algebraic basis transformations, the relation between the rational and algebraic bases is universal and minimal. Here, we ask whether an analogous universal and minimal relation exists when decoupling requires transformations involving complete elliptic integrals. We elaborate on the method proposed in ref. arXiv:2504.20897, in which we suggested that a basis constructed using an elliptic generalization of leading singularities may provide an answer to this question. We extend this analysis to the off-diagonal blocks of the rational differential equations satisfied by the bases obtained through this construction. We find that the $\epsilon$ dependence of these blocks can be organized into a universal structure that is preserved under the decoupling transformation used to express the solutions in terms of iterated integrals.
Read the full abstract

High Energy Physics (Theory)

Covariant Phase Space and Carroll-Weyl $\chi$ Symmetry of Carroll Non-BPS D$_p$-branes

We analyze the covariant phase space of Klusoň's canonical Carroll non-BPS D$_p$-brane actions. The Carroll limit is formulated as a contraction of the canonical phase space: the canonical one-form is invariant under the scaling of conjugate pairs, while the leading Hamiltonian constraint differs between the electric-like and magnetic-like sectors. This difference controls the weak closure of the electric-like constraint algebra and the stronger closure of the magnetic-like Hamiltonian brackets. We separate the generic non-BPS sector, which carries $D-1$ local phase-space degrees of freedom, from the tachyon-vacuum sector, which carries $D-2$ only after imposing second-class background conditions. We also identify the rank condition for the generic electric-like sector and its strengthening in the vacuum sector. Finally, we show that the Carroll–Weyl $\chi$ transformation, the matter-sector analogue of the null-string Carroll–Weyl symmetry, preserves the symplectic form and admits a charge, but is obstructed by the constraints and cannot be promoted to a first-class gauge generator except in highly restricted corners, a global vacuum sector or the singular potential $V\propto T^{-1}$ at $p=1$. The obstruction is algebraic in $\chi$, so no restriction of its spacetime profile can remove it. This contrasts with null string theory, where a restricted $\chi$-symmetry can be completed to an additional first-class constraint.
Read the full abstract

Data Structures and Algorithms

High-Magnetization Sampling at Low Temperatures: Ising Models and Bayesian Sparse Linear Regression

Sparsity is a powerful structural resource in optimization and statistics. We develop frameworks for leveraging sparsity in sampling problems over the Hamming slice $\mathcal{X}_k^d:=\{\mathbf{x}\in\{\pm 1\}^d:|\{i:\mathbf{x}_i=1\}|=k\}$, in high-dimensional regimes where $k\ll d$ (i.e., where $\mathcal{X}_k^d$ is highly magnetized). We use our frameworks to design improved samplers for canonical problems in the study of Ising models and Bayesian sparse linear regression. Our first main result considers the Sherrington–Kirkpatrick (SK) model restricted to fixed-magnetization slices $\mathcal{X}_k^d$. We give a polynomial-time sampler for fixed-magnetization SK models at any inverse temperature $\beta>0$, under arbitrary external fields, provided that $k\le c_\beta d$ for an appropriate constant $c_\beta$. By combining this result with an annealing strategy for estimating normalizing constants, we obtain polynomial-time samplers for the SK model at arbitrarily low temperatures under a sufficiently strong external field of strength $h$. In the large-$\beta$ limit, our framework permits sampling at field strengths within constant factors of the Almeida–Thouless line delineating the replica-symmetric and replica-symmetry-breaking regions ([dAT78]), improving polynomially over the field strength $h(\beta)$ required by the recent work of [BAR26]. Our second main result concerns the measurement complexity of polynomial-time Bayesian sparse linear regression. Recent work by [KSTZ25] shows how to sample from the canonical Gaussian spike-and-slab posterior with expected sparsity $k$, at any signal-to-noise ratio, given $n\gtrsim k^3\log^3 d$ Gaussian measurements. We improve this requirement to $n\gtrsim k^{3/2}\log^2 d+k\log^3 d$, using a common sparsity-aware framework underlying both our results.
Read the full abstract

All authors Syamantak Kumar, Purnamrita Sarkar, Kevin Tian, Yusong Zhu

Numerical Analysis

Strong convergence rates of tamed exponential Euler schemes for superlinear hyperbolic SPDEs

In this paper, we prove pathwise uniform convergence at rates up to $1/2$ for tamed exponential Euler schemes for semilinear hyperbolic stochastic evolution equations with superlinearly growing nonlinearities and multiplicative noise. We take the term hyperbolic to mean that the leading operator generates a contractive $C_0$-semigroup but no parabolic smoothing occurs. Under local Lipschitz, polynomial growth, coercivity, and monotonicity conditions on the nonlinearities, we establish pathwise uniform strong error estimates of the form \begin{equation*} \Big(\mathbb{E}\max_{0\le j \le N} \|U(t_j)-U^j\|_X^p\Big)^{1/p} \lesssim \sqrt{k} \end{equation*} on a Hilbert space $X$ for $p\in [2,\infty)$. Here, $U$ is the mild solution and $U^j$ is the tamed exponential Euler approximation at time $t_j=jk$ with step size $k>0$. This extends previous convergence results for non-parabolic SPDEs from globally to locally Lipschitz nonlinearities, allowing both drift and diffusion to grow polynomially. In a stochastic Kato framework, we further establish local and global well-posedness as well as uniform a priori estimates for the mild solution and its approximation. Applications to nonlinear stochastic transport, Airy, wave-type, and dissipatively damped nonlinear Schrödinger equations are included, covering different nonlinearities-stopped and fractionally tamed schemes. For the Klein-Gordon equation with cubic velocity damping, this complements previous results obtained for additive noise.
Read the full abstract

Cryptography and Security

Towards Standardized Evaluation of GPU Memory Safety with GMSBench

As GPUs become increasingly integral to high-performance computing and machine learning, ensuring memory safety in GPU programs has become crucial for reliable and secure execution. However, evaluating GPU memory safety techniques remains challenging due to the lack of comprehensive and standardized benchmarks. In this paper, we present GMSBench, a GPU memory safety benchmark designed to evaluate a broad range of memory safety violations across different GPU memory spaces and execution scenarios. GMSBench comprises 149 self-contained CUDA tests spanning spatial, temporal, and concurrency errors. The suite provides a standardized foundation for the evaluation and comparative analysis of GPU memory safety mechanisms and helps expose gaps in their detection coverage. We demonstrate the utility of GMSBench by evaluating Compute Sanitizer, a widely used GPU memory error detection tool across multiple GPU architectures.
Read the full abstract

All authors Saurabh Singh, Jaewon Lee, Seonjin Na, Hyesoon Kim

Statistical Mechanics

Stochastic Processes as Non-Metric Geodesics in Information Geometry

We establish a one-to-one correspondence between geodesics associated with the one-parameter family of $\alpha$-connections on the Gaussian statistical manifold and a class of continuous stochastic processes characterized by a time-independent noise intensity. We demonstrate that geodesics in expectation parameters naturally classify into three distinct geometric categories, among which the Boundary-connecting class allows us to construct an explicit linear stochastic realization with constant diffusion, representing a generalized bridge process. This result demonstrates how continuous stochastic processes within this Gaussian class can be extended along geometric curves. Under appropriate operational limits, this generalized bridge process reduces to fundamental stochastic dynamics, either Ornstein-Uhlenbeck (OU) relaxation or free Brownian diffusion. Crucially, the physical restoring force governing the resulting OU relaxation directly determines the underlying connection parameter $\alpha$, providing a concrete physical observable to constrain the manifold geometry. Depending on the chosen affine connection representation, this restoring force can be attributed either to scalar curvature or purely to non-metricity, establishing a direct conceptual analogy with the Geometrical Trinity of Gravity. Furthermore, applying this framework to driven stochastic thermodynamics, we show that the work-minimizing optimal protocol in the slow-driving limit coincides precisely with an expectation geodesic of the statistical manifold with non-metricity equipped with $(g, {}^{(1/2)}\Gamma, {}^{(-1/2)}\Gamma)$, highlighting the active physical role of non-metricity in information geometry.
Read the full abstract

Emerging Technologies

OntoKG-EQ: Evidence-boundary auditing for analytical knowledge graphs

An analytical knowledge-graph result can be supported in its ambient graph while its delivered explanation omits deciding observations. OntoKG-EQ connects competency-question requirements to an executable audit of ambient observations, declared finding support and delivered evidence. A bounded declarative interpreter distinguishes positive, false and unknown numerical status, with same-witness unit readiness reported separately. A public-data application reconstructs England's August 2026 provider-level referral-to-treatment statistical screen. Independent source recomputation reconciles 532 providers with the publisher workbook: 91 meet the inclusive 92% threshold and 441 do not. One additional roster entry remains unavailable rather than zero-filled. All 533 application frames agree with an independently implemented standards-based validation and availability baseline. Transfer requires a disclosed source adapter and arithmetic compilation, but no change to the core interpreter. Twenty-six constructed analytical cases yield 78 status/readiness agreements. Actual financial release replay reproduces two omitted-volume defects: support and delivery suffice for 19 of 21 original findings and all 21 repaired findings after interface adaptation. A separate replay agrees on 487 overlapping financial records. Source audits expose scaling errors and unresolved comparator and temporal assumptions, so financial examples do not establish authenticated market effects. The contribution is a reproducible analytical audit interface and source-reconciled application, not new sufficiency logic or first evidence-boundary isolation. Historical ratings measure preference only; objective human audit benefits and independent production deployment remain untested.
Read the full abstract

All authors Furqan Nasir, Muhammad Atif Saeed, Muhammad Ehsan, Sher Jeel Ahmad, Abdul Moiz Altaf

Other Statistics

The Design and Implementation of a Virtual Statistical Computing Lab to Teach R Coding to Introductory Statistics Students

Motivated by national calls for computationally enriched, data-centric instruction across the statistics curriculum, this study investigates the design, implementation, and impact of a Virtual Statistical Computing Lab (VSCL) integrated into an introductory statistics course at a medium-sized minority-serving university in the USA. The redesigned course embedded R-based coding through two virtual lab formats: Design I (a static Posit Cloud environment) and Design II (an interactive learnr-based interface). Using a quasi-experimental design across three instructional formats, traditional (no lab), Design I, and Design II, we evaluated students' conceptual learning gains, levels of data science (DS) readiness, and DS aspirations. The results indicated significant learning gains across all groups, with the highest gains observed in Design II. Students in both VSCL formats achieved greater gains in DS readiness than the traditional group, with Design II again yielding the largest gains across the demographic subgroups. Conversely, DS aspirations remained low or declined, suggesting a gap between skill acquisition and long-term interest. These findings highlight the value of structured, interactive computing environments in supporting statistical reasoning and building confidence in modern data tools. They also point to the need for intentional curricular bridges and career mentoring to help students translate early computing exposure into sustained academic and professional pathways in statistics and data science.
Read the full abstract

All authors Sayed A Mostafa, Tamer M Elbayoumi, Seongtae Kim, Oluwatobi Akinbode

Computer Vision

SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation

Reasoning segmentation converts an implicit linguistic conclusion into a precise mask, requiring both semantic identification and spatial grounding. Existing MLLM-segmenter interfaces either use a special trigger or compress both signals into one context, although they receive different supervision and fail differently. This coupling obscures whether a failure arises from target interpretation or from localization. We present SeGDeP, an explicit what-where interface. A semantic prompt branch and an independent geometric projection path transform resolved MLLM states into semantic features and a DETR-predicted box, which jointly condition a SAM 3 mask decoder. Training first aligns this executable interface, then uses group reward-decoupled policy optimization (GDPO) to balance format, box-IoU, and mask-IoU feedback. SeGDeP-4B reaches 82.7 average cIoU over eight RefCOCO-family splits and 66.0/59.6 gIoU on ReasonSeg val/test while adapting only 0.38% of Qwen3-VL parameters through LoRA. Controlled stage-wise ablations, gradient diagnostics, and prompt interventions further show that the two paths develop complementary semantic and geometric specialization rather than duplicating the same evidence.
Read the full abstract

All authors Linnan Zhao, Xu Liu, Lingling Li, Licheng Jiao, Fang Liu, Wenping Ma

Statistics Applications

Bayesian palaeoclimate reconstruction from zero-inflated count-compositional pollen data: A case study of Lago Grande di Monticchio in southern Italy

Bayesian palaeoclimate reconstruction from fossil pollen counts relies on a modern pollen-climate calibration data set to infer the pollen-climate relationships used to reconstruct past climates. While geographically large calibration data sets improve coverage of climate space and reduce unreliable extrapolation, they also introduce substantial heterogeneity, structural zeros, and complex pollen-climate relationships. We propose a Bayesian modular framework for palaeoclimate reconstruction from count-compositional pollen data that addresses these challenges, and provides coherent uncertainty quantification. The framework employs the zero-and-$N$-inflated multinomial logistic-normal distribution to describe the compositional pollen counts coupled with Bayesian additive regression tree priors to model the nonlinear effects and interactions among the climate covariates. Inference is formulated through a cut posterior distribution that modularises the analysis into forward and reconstruction modules. The forward module is fitted once using a large modern calibration data set and its posterior uncertainty is subsequently propagated to reconstruct climate variables from fossil pollen counts. For the reconstruction module, we develop and compare three inverse posterior sampling schemes. Simulation studies and empirical validation on the modern data set demonstrate that a combination of sampling importance resampling with a multiple imputation technique and a continuous uniform prior over the domain of the modern climate variables achieves the best predictive performance, with well-calibrated uncertainty quantification for the climate reconstruction. In our motivating case study, we further illustrate the proposed methodology by reconstructing a three-dimensional climate vector from fossil pollen records collected at Lago Grande di Monticchio in southern Italy.
Read the full abstract

All authors André F. B. Menezes, Andrew C. Parnell, Brian Huntley, Keefe Murphy

Nuclear Theory

How strange: Phase diagrams with 3 critical points

We show that the Chiral Mean-Field model (CMF) can produce a phase diagram with three critical points: the nuclear liquid-gas transition, quark deconfinement, and a strangeness driven transition. The strangeness driven transition separates a mainly nucleonic phase from one dominated by hyperons and baryon resonances. We discuss the compositional change in these transitions and their possible signatures in heavy-ion collisions and neutron star mergers.
Read the full abstract

All authors Mateus Reinke Pelicer, Nikolas Cruz Camacho, Rajesh Kumar, Veronica Dexheimer, Jacquelyn Noronha-Hostler

Quantum Physics

Distributed Quantum Property Testing with Quantum Carrier Pigeons

We introduce a framework for distributed quantum inference under communication constraints. In our model, $m$ distributed nodes each receive one copy of an unknown $d$-dimensional quantum state $\rho$, before communicating via a constrained one-way communication channel with a central node, which aims to infer some property of $\rho$. This framework generalizes the classical distributed inference framework introduced by Acharya, Canonne, and Tyagi [COLT 2019], by allowing quantum resources such as quantum communication and shared entanglement. Within this setting, we focus on the fundamental problem of quantum state certification: Given a complete description of some state $\sigma$, decide whether $\rho=\sigma$ or $\|\rho-\sigma\|_1\geq \epsilon$. Additionally, we focus on the case of limited communication between distributed nodes and the central node: we assume each communication channel is limited to only $n_c$ bits and $n_q$ qubits with $n_c + n_q \leq \log d$. When all nodes can make use of a shared source of randomness, we show that the copy complexity of distributed state certification is $\Theta(\frac{d^2}{2^{n_q} 2^{n_c/2}\epsilon^2})$. We further demonstrate that shared randomness is necessary to achieve the above complexity, by proving an $\Omega(\frac{d^3}{4^{n_q} 2^{n_c} \epsilon^2})$ lower bound in the $\textit{private-coin}$ setting. Moreover, we develop a private-coin algorithm that matches this bound up to a $\sqrt{\log d}$ factor, showing this complexity is near-optimal. Together, our work establishes a general framework for distributed quantum inference with communication constraints and characterizes the complexity of distributed state certification with limited communication.
Read the full abstract

All authors Kenny Chen, Mina Doosti, Ryan Sweke, Chirag Wadhwa

Group Theory

Solvable groups defined by redundant cyclic presentations

We study the two-generator one-relator groups defined by $\langle x_0,x_1\mid U(x_0,x_1)U(x_1,x_0)^{-1}\rangle$, and determine exactly which of them fail to contain a free subgroup of rank $2$. We show that every such group is a solvable Baumslag–Solitar group $BS(1,m)$, and that every integer value $m$ can occur. This disproves a conjecture predicting that only $m\in \{-1,0,1\}$ can occur.
Read the full abstract

Solar and Stellar Astrophysics

The role of specific entropy in the onset of the luminosity bump

During their evolution, stars follow a distinct path in luminosity–temperature space. Low-mass stars that have exhausted hydrogen in their core follow the so-called red-giant branch which is predominantly in the direction of increasing luminosity and decreasing surface temperature. The luminosity bump is a temporary decrease in luminosity against this otherwise increasing trend. The bump is present in both observations and stellar evolution models. However, with canonical physics included in the models, the bump in computed evolutionary tracks appears at higher luminosities than the observed bump. To understand why the bump appears later in the models than in observations, the physics of the bump needs to be unravelled. The end point of the bump is well-understood; however, the onset of the bump is still an enigma. Here, we report on the physical origin of the onset of the luminosity bump. We show that the difference in specific entropy at the mean molecular weight discontinuity decreases due to the discontinuity moving in. This decrease is attributed to the decrease in the ratio of the temperature to the pressure at smaller radii. Upon reaching a critical value the specific entropy difference at the mean molecular weight discontinuity is reduced sufficiently to reduce the specific entropy in the convective envelope. The latter is a key signature of the bump. Hence the evolution of the specific entropy at the mean molecular weight discontinuity provides a viable description for the onset of the bump.
Read the full abstract

Artificial Intelligence

API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces

Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assumption underlying benchmark scores is that the model performance measured through APIs faithfully reflects the behavior of deployed systems. We challenge this assumption by auditing ChatGPT, Claude, and Gemini across seven systems and nine benchmarks spanning general capability, social bias, and sycophancy. We find systematic API–interface differences in both accuracy and consistency. On average, API evaluations score 3.4 percentage points higher in accuracy and 2.1 percentage points higher in test–retest agreement than corresponding interface evaluations. For ChatGPT, the performance difference between API and interface access rivals the API-only difference between GPT 5.3 and GPT 5.4. Put differently, switching access surfaces can degrade performance as much as downgrading a full model version. We further test whether exposed API controls can reproduce interface behavior by varying system prompts, sampling parameters, and reasoning settings. These controls shift behavior in some cases but do not reliably eliminate the gap. Our findings document a context-validity gap: measurements obtained through APIs do not necessarily generalize to corresponding deployed interfaces, complicating the use of API evaluations as proxies for deployed systems.
Read the full abstract

All authors Jennifer Wang, Joachim Baumann, Daniel E. Ho, Sanmi Koyejo