digitado

arXiv:2603.22447v1 Announce Type: new Abstract: Agent skills are modular instruction packages that combine YAML metadata, natural language instructions, and embedded code, and they have reached 196K publicly available instances, yet no mechanism exists to detect clone relationships among them. This gap creates systemic risks: a vulnerability in a widely copied skill silently persists across derivatives with no alert to maintainers. Existing clone detectors, designed for single-modality source code, cannot handle the multi-modal structure of skills, where clone evidence […]

Ver mais

arXiv:2603.22446v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study of RLVR’s distributional effects organized around three main analyses: (1) token-level characterization of distributional shifts between base and RL models, (2) the impact of token-level distributional shifts on sequence-level reasoning performance through cross-sampling interventions, and (3) fine-grained mechanics of these shifts at the […]

Ver mais

arXiv:2603.22445v1 Announce Type: new Abstract: This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while […]

Ver mais

arXiv:2603.22442v1 Announce Type: new Abstract: Cryptographic migration driven by algorithm deprecation, regulatory change, and post-quantum readiness requires more than an inventory of cryptographic assets. Existing Cryptographic Bills of Materials (CBOMs) are typically tool- or inventory-derived. They lack architectural intent, rationale, and security context, limiting their usefulness for migration planning. This paper introduces Security-Aware Architecture Tradeoff Analysis Method (SATAM), a security-aware adaptation of scenario-based architecture evaluation that derives an architecture-grounded, context-sensitive CBOM. SATAM integrates established approaches: ATAM, arc42, STRIDE, […]

Ver mais

arXiv:2603.22437v1 Announce Type: new Abstract: We present mmFHE, the first system that enables fully homomorphic encryption (FHE) for end-to-end mmWave radar sensing. mmFHE encrypts raw range profiles on a lightweight edge device and executes the entire mmWave signal-processing and ML inference pipeline homomorphically on an untrusted cloud that operates exclusively on ciphertexts. At the core of mmFHE is a library of seven composable, data-oblivious FHE kernels that replace standard DSP routines with fixed arithmetic circuits. These kernels can […]

Ver mais

arXiv:2603.22436v1 Announce Type: new Abstract: In this short position paper, I develop a dialectical framework for understanding the political ideology of technological projects. To do so, I draw on critical and emancipatory social science discussions, highlighting how both a project’s values and constraints are necessary for understanding its ideology. A brief example is then presented to aid comprehension.

Ver mais

arXiv:2603.22435v1 Announce Type: new Abstract: “Code-as-Policy” considers how executable code can complement data-intensive Vision-Language-Action (VLA) methods, yet their effectiveness as autonomous controllers for embodied manipulation remains underexplored. We present CaP-X, an open-access framework for systematically studying Code-as-Policy agents in robot manipulation. At its core is CaP-Gym, an interactive environment in which agents control robots by synthesizing and executing programs that compose perception and control primitives. Building on this foundation, CaP-Bench evaluates frontier language and vision-language models across varying […]

Ver mais

arXiv:2603.22434v1 Announce Type: new Abstract: While multi-vector retrieval models outperform single-vector models of comparable size in retrieval quality, their practicality is limited by substantially larger index sizes, driven by the additional sequence-length dimension in their document embeddings. Because document embedding size dictates both memory overhead and query latency, compression is essential for deployment. In this work, we present an evaluation of training-free methods targeting the token sequence length, a dimension unique to multi-vector retrieval. Our findings suggest that […]

Ver mais

arXiv:2603.22432v1 Announce Type: new Abstract: Spin-glasses are natural Gibbs distributions that have been studied in Theoretical CS for many decades. Recently, they have been gaining attention from the community as they emerge naturally in neural computation and learning, network inference, optimisation and other areas. We study the problem of efficiently sampling from spin-glass distributions when the underlying graph is a typical instance of $G(n,d/n)$, i.e., the random graph on $n$ vertices such that each edge appears independently with […]

Ver mais

arXiv:2603.22430v1 Announce Type: new Abstract: Offline Reinforcement Learning (RL) aims to learn optimal policies from fixed offline datasets, without further interactions with the environment. Such methods train an offline policy (or value function), and apply it at inference time without further refinement. We introduce an inference time adaptation framework inspired by model predictive control (MPC) that utilizes a pretrained policy along with a learned world model of state transitions and rewards. While existing world model and diffusion-planning methods […]

Ver mais