arXiv:2601.05307v1 Announce Type: new Abstract: U.S. AI security policy is increasingly shaped by an $textit{LLM Mirage}$, the belief that national security risks scale in proportion to the compute used to train frontier language models. That premise fails in two ways. It miscalibrates strategy because adversaries can obtain weaponizable capabilities with task-specific systems that use specialized data, algorithmic efficiency, and widely available hardware, while compute controls harden only a high-end perimeter. It also destabilizes regulation because, absent a settled […]

Ver mais

arXiv:2603.24704v1 Announce Type: cross Abstract: In deploying artificial intelligence (AI) models, selective prediction offers the option to abstain from making a prediction when uncertain about model quality. To fulfill its promise, it is crucial to enforce strict and precise error control over cases where the model is trusted. We propose Selective Conformal Risk control with E-values (SCoRE), a new framework for deriving such decisions for any trained model and any user-defined, bounded and continuously-valued risk. SCoRE offers two […]

Ver mais

Many healthcare payer organizations have made measurable progress in administrative automation at scale. The 2025 CAQH (Council for Affordable Quality Healthcare) Index reported that U.S. healthcare avoided an estimated $258 billion in administrative costs in 2024[1] through electronic transactions and improved data exchange, based on data from provider organizations and health plans representing 63% of insured lives. These findings indicate substantial automation maturity in core administrative workflows, including claims-related transactions, even as more complex decision points remain difficult […]

Ver mais

arXiv:2601.07973v1 Announce Type: new Abstract: Generative AI models ought to be useful and safe across cross-cultural contexts. One critical step toward this goal is understanding how AI models adhere to sociocultural norms. While this challenge has gained attention in NLP, existing work lacks both nuance and coverage in understanding and evaluating models’ norm adherence. We address these gaps by introducing a taxonomy of norms that clarifies their contexts (e.g., distinguishing between human-human norms that models should recognize and […]

Ver mais

arXiv:2601.05267v1 Announce Type: new Abstract: Evaluating complex texts across domains requires converting user defined criteria into quantitative, explainable indicators, which is a persistent challenge in search and recommendation systems. Single prompt LLM evaluations suffer from complexity and latency issues, while criterion specific decomposition approaches rely on naive averaging or opaque black-box aggregation methods. We present an interpretable aggregation framework combining LLM scoring with the Analytic Hierarchy Process. Our method generates criterion specific scores via LLM as judge, measures […]

Ver mais

Mood instability is a key behavioral indicator of mental health, yet traditional assessments rely on infrequent and retrospective reports that fail to capture its continuous nature. Smartphone-based mobile sensing enables passive, in-the-wild mood inference from everyday behaviors; however, deploying such systems at scale remains challenging due to privacy constraints, uneven sensing availability, and substantial variability in behavioral patterns. In this work, we study mood inference using smartphone sensing data in a cross-country federated learning setting, where each country […]

Ver mais

Let 1 < a1 < a2 < · · · be integers with ( sum_{k=1}^infty a_k^{-1}<infty ), and set ( F(s)=1+sum_{k=1}^infty a_k^{-s}, qquad Re s>1. ) A question of Erdős and Ingham, recorded as Erdős Problem #967 in a compilation by T. F. Bloom (accessed 2025–12–01), asks whether one always has ( F(1+it)neq 0 ) for all real t. This paper does not resolve the problem; instead, it develops a modern dynamical-systems framework for its study. Using the […]

Ver mais

arXiv:2603.06649v1 Announce Type: new Abstract: The coastal regions of the eastern and southern United States are impacted by severe storm events, leading to significant loss of life and properties. Accurately forecasting storm surge and wind impacts from hurricanes is essential for mitigating some of the impacts, e.g., timely preparation of evacuations and other countermeasures. Physical simulation models like the ADCIRC hydrodynamics model, which run on high-performance computing resources, are sophisticated tools that produce increasingly accurate forecasts as the […]

Ver mais

Human action recognition (HAR) remains challenging, particularly for skeleton-based methods due to issues like domain shift and limited deep semantic understanding. Traditional Graph Convolutional Networks often struggle with effective cross-domain adaptation and inferring complex semantic relationships. To address these limitations, we propose CD-SEAFNet, a novel framework meticulously designed to significantly enhance robustness and cross-domain generalization for skeleton-based action recognition. CD-SEAFNet integrates three core modules: an Adaptive Spatio-Temporal Graph Feature Extractor that dynamically learns and adjusts graph structures to […]

Ver mais

arXiv:2603.22295v1 Announce Type: new Abstract: Large language models appear to develop internal representations of emotion — “emotion circuits,” “emotion neurons,” and structured emotional manifolds have been reported across multiple model families. But every study making these claims uses stimuli signalled by explicit emotion keywords, leaving a fundamental question unanswered: do these circuits detect genuine emotional meaning, or do they detect the word “devastated”? We present the first clinical validity test of emotion circuit claims using mechanistic interpretability methods […]

Ver mais