May 2026

arXiv:2605.18931v1 Announce Type: new Abstract: Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge for modern deep generative models. Standard Variational Autoencoders (VAEs) employ Gaussian decoder likelihoods and Lipschitz-constrained neural networks, a combination that is structurally incapable of producing heavy-tailed outputs: the Gaussian tail decays exponentially, and Lipschitz continuity prevents the decoder from amplifying rare events from the latent space input to sufficiently overcome this decay. We provide both […]

Ver mais

arXiv:2605.18927v1 Announce Type: new Abstract: Bayesian latent space models offer a principled approach to network representation, but rely on correct specification of both geometry and link function. Real-world networks often violate these assumptions, exhibiting geometric mismatch and structural anomalies that break standard metric properties. We show that such misspecification pushes the data-generating distribution outside the model class, causing Bayesian inference to become overconfident and poorly calibrated. To address this, we propose a generalized posterior framework for random geometric […]

Ver mais

arXiv:2605.18760v1 Announce Type: new Abstract: Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods struggle to adapt to the query-specific logic required for complex multi-hop tasks, often accumulating irrelevant context or missing correct relational paths. We propose DotRAG, a training-free GraphRAG framework that reformulates retrieval as a reasoning process over paths. Our approach generates query-conditioned constraints that guide graph exploration, prune irrelevant regions, and iteratively […]

Ver mais

arXiv:2605.18759v1 Announce Type: new Abstract: Artificial intelligence (AI), exemplified by large language models (LLMs), is rapidly approaching and in some cases surpassing human performance across a wide range of cognitive tasks. However, human nature is not limited to intelligence alone; it also encompasses sensibility, including the capacity to perceive and experience beauty in visual scenes. This raises a fundamental question: how humans and AI systems converge or diverge in such aesthetic experiences. Aesthetic evaluation depends not only on […]

Ver mais

arXiv:2605.18758v1 Announce Type: new Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to process transient audio cues and temporal video dynamics that are tightly coupled with the moment of action. To bridge this gap, we introduce OmniGUI, the first step-level benchmark designed to evaluate GUI agents in omni-modal smartphone environments. OmniGUI provides continuous, interleaved multimodal inputs comprising static images, synchronous audio, and video clips at […]

Ver mais

arXiv:2605.18757v1 Announce Type: new Abstract: We prove that Cypher 25, the graph query language of Neo4j, is Turing-complete. The proof shows that a single RETURN statement using reduce(), CASE expressions, and list comprehensions can simulate any 2-counter machine (Minsky 1967). We address the bounded-step objection via two complementary resolutions and present a third graph-native simulation using quantified path patterns (QPP) with allReduce. All three constructions were verified on a live Neo4j Aura instance.

Ver mais

arXiv:2605.18755v1 Announce Type: new Abstract: Kubernetes clusters generate rich operational events during pod lifecycle transitions, yet the platform’s native event retention model discards the most diagnostically valuable context. The LastTerminationState field, which records a container’s last failure, is overwritten shortly after a pod restart. We define this as the evidence horizon. During high-frequency crash loops, this horizon may be crossed multiple times before inspection, permanently losing critical evidence. This paper introduces the Operational Memory Architecture (OMA) to preserve […]

Ver mais