arXiv:2605.03542v2 Announce Type: replace Abstract: The dual norm characterisation of weak solutions of second-order linear elliptic partial differential equations is mathematically natural but computationally intractable: evaluating the $H^{-1}$ norm of the residual requires a supremum over an infinite-dimensional test space. We prove that the $H^{-1}$ norm of any functional is equivalent to its expected squared evaluation against a random test function whose probability distribution depends only on the domain. Crucially, realisations of this random test function have negative Sobolev regularity for $d \geq 2$, yet this roughness is not an obstacle: averaging over the distribution exactly recovers the correct weak topology, independently of the differential operator, and no supremum evaluation is necessary. This equivalence introduces the notion of stochastically weak solutions, which coincide with classical weak solutions, and motivates stochastic variational physics-informed neural networks (SV-PINNs): neural networks trained by minimising an empirical approximation of the stochastic norm of the PDE residual. Although instantiated here with neural networks, the underlying principle is independent of the trial space and suggests a broader paradigm for numerical methods based on stochastic rather than deterministic test spaces. The framework extends naturally to higher-order elliptic, parabolic and hyperbolic equations and to abstract operator equations on Hilbert spaces. As a proof of concept, we present numerical experiments on eight challenging second-order linear elliptic problems spanning high-frequency and multi-scale solutions, indefinite operators, variable coefficients, and non-standard domains, in which SV-PINNs consistently and significantly outperform standard PINNs, recovering solutions to within one percent relative error in hundreds of L-BFGS steps.
Science Journals
arXiv:2605.09667v2 Announce Type: replace Abstract: We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert
arXiv:2606.26421v1 Announce Type: new Abstract: State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This restricts usage for under-resourced groups and severely limits fast model iteration. Here we develop Otter Weather, a highly efficient spatiotemporal forecasting model designed to democratise high-performance weather prediction with AI. Evaluated on ERA5 reanalysis data at 1.5{\deg} resolution using standard WeatherBench protocols, the Otter family significantly advances the skill-compute Pareto frontier. The deterministic version outperforms the best NWP baseline by 9.6% at a 24-hour lead time while requiring fewer than 3.5 A100-days for training. It provides a 2x efficiency gain over lightweight AI models and a 100-fold reduction in compute compared to resource-intensive frontier architectures. We extend these efficiency gains into probabilistic forecasting by training via the Continuous Ranked Probability Score (CRPS). Scaling to a larger architecture, Otter-XL achieves a 9.7% CRPS improvement over the IFS ENS baseline. This yields an almost two-fold increase in predictive skill over comparable lightweight models at similar compute budgets. Otter-XL also outperforms frontier architectures like GenCast by over 2%, while using an order of magnitude less compute. Finally, Otter is applied out-of-the-box to a complex acoustic scattering PDE task where it outperforms a state-of-the-art foundation modelling approach, suggesting that the advances made here might apply across a range of scientific domains.
arXiv:2606.26422v1 Announce Type: new Abstract: Researchers increasingly use text classification--supervised models or large language models--to measure constructs from natural language, providing metrics such as recall and precision as evidence of their validity. Yet, though these metrics are point estimates subject to sampling variation, measures of uncertainty are inconsistently reported alongside them. Further, when they are reported, they are often estimated with methods that are not appropriate when relevant labelled datasets are small or performance is high. To increase and improve confidence interval reporting in the field, this paper evaluates confidence interval methods for performance metrics under conditions typical of social science text classification: small to moderate sample sizes, infrequent constructs, and texts nested within individuals. Across simulations, default methods such as the Wald interval and the basic percentile bootstrap are the least accurate, with coverage sometimes far below the nominal 95% level. Accuracy is improved with the use of Agresti-Coull, Wilson, Clopper-Pearson, and a novel pseudo-count regularized bootstrap (which is particularly relevant to the calculation of F1). When texts are nested within individuals, we demonstrate that adjustment for both effective N and the appropriate degrees of freedom is necessary for producing accurate analytic intervals. Among bootstrap intervals, the hierarchical bootstrap is more accurate than the cluster bootstrap when individuals produce a moderate number of texts but overly conservative when individuals produce only a few. By providing guidance to the field on appropriate interval estimation, we aim to improve the transparency of machine learning applications, and to encourage greater attention to the validation sample size at the design stage.
arXiv:2606.26849v1 Announce Type: new Abstract: General Salient Object Detection (SOD) aims to identify and segment visually interesting objects from uni-modality or multi-modality scenes, recently advanced by cutting-edge State Space Models (SSMs). However, a critical limitation of current approaches is their neglect of the inherent spectral biases exhibited by different neural network paradigms. By digging to the dataset-level spectral analysis of Convolutional Neural Networks (CNNs) and SSMs, their semantic representations are inherently complementary based on their complementary frequency preferences. Inspired by this, we harmonize heterogeneous representations from SSMs and CNNs to bridge their spectral biases for general salient object detection. To this end, inspired by the dynamic information propagation of Liquid Neural Networks (LNNs), we introduce a liquid fusion to dynamically integrates features from two backbones, including VMamba and ConvNeXt, referred to Liquid Fusion Network (LFNet). Concretely, by treating the continuous VMamba features and ConvNeXt features as evolving states and exogenous stimulus, respectively, LFNet employs a dynamic gating mechanism for content-aware feature aggregation. Crucially, this state-stimulus paradigm enables to scale to multi-modal cues, resulting in flexibility in general SOD. Besides, a Saliency-Guided Upsampling (SGU) operator to propagate the features to the shallow layer, which leverages a spectral-spatial co-design to suppress upsampling artifacts while preserving semantics. Extensive experiments across five diverse tasks (RGB, RGB-D, RGB-T, VSOD, and VDT) demonstrate that LFNet achieves state-of-the-art performance, offering a superior trade-off between detection accuracy and model efficiency. Code has been released at https://github.com/cke520/LFNet.
arXiv:2606.26852v1 Announce Type: new Abstract: Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing. While integrated models capture interactions between these decisions, practical warehouse systems often require decomposed approaches due to organizational boundaries, differing responsibilities, or limited data availability. Existing studies primarily evaluate algorithms for isolated subproblems or fixed subproblem combinations for specific warehouse settings, but lack a general mechanism to determine applicable algorithm configurations, compose them into valid solution pipelines, and assess their performance. With Context-Aware Synthesis of Optimization Pipelines (CASOP), we propose a framework for constructing and evaluating context-specific optimization pipelines and apply these to order fulfillment. The framework comprises: (1) a modular repository of algorithms for common order fulfillment problems; (2) semantic data and algorithm cards to describe warehouse context and algorithm requirements; (3) a taxonomy that structures order fulfillment problems into relevant subproblems; (4) a pipeline synthesizer that identifies applicable algorithms for a given warehouse context and composes all valid optimization pipelines; and (5) a pipeline evaluator that assesses all resulting pipelines. We demonstrate the framework on 7 benchmark instance sets covering four problem classes, resulting in 1,063,044 valid pipelines. The framework supports researchers and practitioners in designing, automatically synthesizing, and selecting valid, high-performing algorithmic pipelines for warehouse operations. The software is open-source and available at https://github.com/kit-dsm/ware_ops_pipes and https://github.com/kit-dsm/ware_ops_algos. Keywords: Warehouse optimization, Algorithm selection, Pipeline synthesis, Order fulfillment
arXiv:2606.26704v1 Announce Type: new Abstract: The tokenization of real-world assets (RWAs) has emerged as a transformative application of blockchain technology, with market projections estimating trillions of dollars in tokenized assets within the coming decade. However, a fundamental challenge remains unaddressed: physical assets such as precious metals, stored commodities, and warehoused goods incur structural negative carry -- custody, insurance, and audit costs that accumulate over time. While existing tokenization models have successfully established the market for digital gold and treasuries, they typically manage operational costs at the issuer level. The FRS introduces a framework to bring these economics directly on-chain, avoiding mechanisms such as token rebasing that compromise fungibility and composability with decentralized finance (DeFi) protocols. This paper proposes the Fungible Reserve Standard (FRS), a deterministic token design framework that encodes carrying costs transparently into on-chain logic. The FRS introduces an asset-per-token variable q(t) that decreases according to a predefined annualized carrying cost rate, coupled with a supply reconciliation mechanism that preserves holder balances and ERC-20 composability. While mathematically inspired by the daily expense ratio accrual in traditional asset management -- which often embed centralized profit margins -- the FRS design specifically encodes actual operational carrying costs to provide pure institutional-grade accounting clarity without compromising DeFi compatibility. The framework is asset-agnostic and applicable to any real-world asset with positive, predictable holding costs.
arXiv:2606.26705v1 Announce Type: new Abstract: Feedforward neural network (NN) expressivity is typically studied by emulating optimal basis-expansion schemes. While powerful, this perspective is incomplete: it primarily captures complexity through regularity, and therefore does not distinguish intuitively simple and complicated objects with comparable regularity, such as the square-root function and a typical Brownian path. The guiding message is that neural networks should be viewed not only as flexible basis functions, but also as models of computation. If a function is computable by a real-valued circuit over a prescribed elementary gate language, then it can be computed to comparable accuracy by an NN with explicit depth, width, and non-zero-parameter bounds controlled by the depth, width, gate count, and gate structure. Thus, neural-network complexity is not governed by regularity alone, but also by algorithmic complexity. We then show that any definable NN model satisfying a natural parallelization condition, allowing possibly multivariate non-linearities such as attention or layer normalization, is a universal approximator if and only if it contains a non-affine nonlinearity. The scope of our theory is illustrated by deducing universal approximation guarantees for continuous functions, minimax-optimal approximation guarantees for Besov classes, logarithmic-error complexity for holomorphic functions, and by showing that NNs can emulate numerical algorithms such as Newton-Raphson root finding and power iteration without architecture-specific arguments. Its precision is illustrated by shortest-path computation on $k$-vertex graphs: compiling the tropical dynamic-programming circuit yields NNs with O(log(1/{\epsilon})) non-zero parameters, exponentially improving in 1/{\epsilon} over the generic $O({\epsilon}^{-c k^2})$ Lipschitz-approximation scale, for a constant c>0.
arXiv:2606.26707v1 Announce Type: new Abstract: Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that, despite claims, existing problem-space attacks remain largely impractical. Most techniques leverage software transplantation to inject entire benign modules, introducing many side-effect features and often causing build-time failures. Fine-grained methods that inject only a narrow subset of components exhibit limited effectiveness, while those that also use obfuscation rely on brittle bytecode rewriting, producing APKs that are syntactically valid but semantically unusable. Prior work further overestimates attack success rates by running smoke tests that only validate installation and basic execution, without assessing whether the modified APK still preserves its intended behavior. To overcome these limitations, we present DROIDBREAKER, a practical (build-safe) and functional (semantics-preserving) problem-space attack framework that provides: (i) query-efficient white- and black-box attacks by manipulating only the APK components most influential to the target model; (ii) a set of fine-grained, build-safe manipulations (including injection and obfuscation of API calls, app modules, permissions, and URLs) with minimal side effects; and (iii) a semantics-preserving functionality test that enforces runtime equivalence by comparing execution logs and API-level traces between the initial and the modified APK. Evaluated on a recent corpus of Android applications, DROIDBREAKER achieves high evasion rates with few queries and minimal side effects in both white-box and black-box settings, and drastically reduces detections by commercial malware scanners hosted on VirusTotal.
arXiv:2606.26977v1 Announce Type: new Abstract: Modern compilers are complex software systems that must correctly translate high-level programming languages into machine code across multiple architectures. Cranelift, a fast and modern compiler backend originally developed for WebAssembly and recently adopted as an experimental backend for Rust, has gained increasing importance due to its superior compilation speed compared to LLVM and comprehensive multi-architecture support, including x86-64, AArch64, s390x, and RISCV64. However, despite decades of development in compiler testing, testing Cranelift still presents unique challenges, including (1) constructing valid IR under the strict enforcement of SSA form, (2) generating sequences with sufficient computational density to stress backend components, and (3) balancing broad backend coverage with efficient root cause analysis across heterogeneous architectures. To address these challenges, we propose CLIR, a differential testing framework that integrates a syntax-preserving hierarchical generation strategy to guarantee SSA validity, a liveness-guided instruction refinement mechanism to maximize computational density, and a diagnosis-guided cross-architecture adaptation scheme to facilitate efficient root cause analysis across heterogeneous backends. Our comprehensive evaluation demonstrates that CLIR significantly outperforms existing state-of-the-art baselines, detecting 8x, 24x, and 8x more unique bugs than cranelift-fuzzgen, wasm-smith, and WASMaker, respectively, while RustSmith uncovered no bugs. Consequently, within 72 hours of testing, CLIR discovered 24 bugs spanning all target architectures, with 21 confirmed and 9 fixed.
arXiv:2606.27126v1 Announce Type: new Abstract: Kolmogorov Arnold networks (KAN) have recently been introduced as a (deep) neural network architecture whose trainable parameters adapt the activation functions, instead of the coefficients of the affine transformations at the core of traditional architectures such as deep multilayer perceptrons (MLPs). This architecture builds on the Kolmogorov-Arnold theorem, which endows it with universal approximation properties. While the advent of KANs has been received with excitement, there is a current debate about the possible KAN supremacy over deep multilayer perceptrons (MLPs) for classic fields such as symbolic regression, generic-purpose machine learning, natural language processing or computer vision. Here we assess the performance of KANs --and its nuanced comparison against MLPs and graph neural networks (GNNs)-- in the realm of fluid dynamics surrogate modelling. To that aim, we consider the task of predicting the surface pressure distribution over subsonic and transonic airfoils, a canonical task in aerodynamics. Our results show that KAN models show good performance in predicting the whole pressure coefficients and is able to interpolate across Mach numbers and angles of attack, however its performance is comparable --marginally inferior-- to a suitably trained MLP, where best performance is achieved by a GNN at the expense or requiring lengthier training. While the optimal KAN model have typically much lower complexity than MLP and GNN --hence resulting in faster training--, we find that KANs suffer from training instabilities, and their performance is highly dependent on a proper hyperparameter optimisation.
arXiv:2606.27172v1 Announce Type: new Abstract: Parameterized verification of finite-state processes with rendez-vous synchronization is notoriously undecidable when processes are linearly ordered. In this paper we study two kinds of bounds under which we determine the complexity of safety checking over tree topologies. When bounding the depth we obtain that the complexity is related to the fast growing hierarchy. Our second bound limits the alternations between upwards and downwards synchronizations in the tree (phases), and occurs naturally in many concrete settings. If we fix the number of phases then the complexity of safety checking is EXPSPACE complete, and if the number of phases is part of the input it is 2EXPSPACE complete (both for arbitrary depth).
arXiv:2606.27176v1 Announce Type: new Abstract: In this paper, we consider Fourier phase retrieval from differential intensity measurements, i.e., the problem of determining the phase of a complex-valued function from a series of intensity measurements differing only by slight modulations in Fourier domain. These modulations may be induced by optical elements such as prisms or phase plates, or via spatial-light modulators. Generalizing the principles behind the transport of intensity equation, we show that given such differential intensity measurements, the phase can be determined as the solution of certain partial differential or integro-differential equations. This is then used to design efficient reconstruction algorithms for a number of Fourier-type wavefront sensors, such as the pyramid wavefront sensor, commonly used in adaptive optics. Numerical experiments illustrate the usefulness of our proposed approach.
arXiv:2606.27178v1 Announce Type: new Abstract: In the present paper, we introduce a numerical method for second-kind Fredholm integral equations (FIEs) based on de la Vall\'ee Poussin-type (VP) polynomial approximations at Jacobi zeros. This class of approximations offers several advantages over classical Lagrange interpolation at the same nodes. In particular, it guarantees uniformly bounded Lebesgue constants in suitable weighted function spaces and provides near-best uniform approximation for functions in these spaces, while also significantly mitigating the Gibbs phenomenon. We show how these properties can be exploited in the numerical solution of FIEs. In particular, the proposed approach effectively handles functions with possible algebraic endpoint singularities and kernel functions featuring weak singularities or highly oscillatory behavior. Under suitable assumptions, we prove stability and convergence of the method in weighted uniform spaces. Furthermore, we develop an efficient implementation based on the solution of a well-conditioned linear system. Numerical results confirm the theoretical error estimates and show that the proposed method achieves higher local accuracy than the corresponding Lagrange-based projection method.
arXiv:2606.27288v1 Announce Type: new Abstract: Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their gain is capped by a quantity the field rarely reports. For any policy whose output is one member model answer, accuracy cannot exceed one minus beta, where beta is the rate at which every model is wrong on the same query. In contrast, the usual diagnostic, average pairwise error correlation rho, cannot identify beta: error laws with identical marginals and pairwise correlations can have different all-wrong rates. A Clopper-Pearson bound on beta gives a finite-sample certificate on the largest gain any router, vote, or cascade could deliver before training a router. Across 67 models from 21 providers, a tetrachoric-calibrated single-factor model still underprices the all-wrong tail: on open-ended mathematics, observed beta is 0.052 versus 0.023 under the full 67-model Gaussian copula, about 2.5 times underpricing, with 90 percent CI 1.7 to 3.4 and k equals 17. The effect recurs on execution-graded code, where beta is 0.079. Re-asking the same GPQA-Diamond questions in free-response rather than multiple-choice form reopens the tail, with beta 0.127 and a five-judge panel with kappa 0.73 to 0.92, locating co-failure in answer format rather than subject. At matched quality, low-rho heterogeneous ensembles beat high-rho Self-MoA, but on checkable tasks in our pool, combining models rarely beats the single best model without a strong query-level routing signal. Gains come from models failing on different questions, not from adding more models.
arXiv:2606.27348v1 Announce Type: new Abstract: Autonomous drone racing is a fundamentally challenging regime for autonomous aerial robots, requiring time-optimal control while operating under persistent actuation saturation. While reinforcement learning (RL) has achieved human-level performance in this domain, current methods fail to generalize; policies trained on specific environments often crash immediately in unseen configurations. This failure reflects the intrinsic difficulty of zero-shot generalization in agile flight, arising from high-dimensional task variation and the tight coupling between safety and performance at high speeds. Existing approaches that improve generalization impose a substantial cost on flight speed: control policies must significantly degrade performance to achieve even modest levels of generalization. In this work, we propose a framework for zero-shot generalization in agile flight for RL-based drone racing. By combining task-aware switching based on learning progress with a physically informed procedural track generator, the framework produces a fast and robust generalist policy without test-time adaptation. Our method achieves strong zero-shot performance across a wide range of unseen racetracks in the real world, demonstrating a 7.4x improvement in generalization over the state-of-the-art approaches, while maintaining competitive racing speeds. We validate our method's results in both simulation and real-world settings, including a challenging vision-based, end-to-end control setting that operates without explicit state estimation, where all prior approaches fail to generalize.
arXiv:2606.26946v1 Announce Type: cross Abstract: The Casimir effect in its simplest form describes the attraction of two parallel conducting plates at close distance due to the vacuum fluctuation of the electromagnetic field. Its derivation can be found in many introductory works on quantum optics. Here we return to the original paper by Casimir and find subtle nuances in his derivation that are worth discussing to give a complete picture of a mathematically sound derivation of the effect.
arXiv:2510.20769v2 Announce Type: replace Abstract: Accurate medium-range precipitation forecasting is essential for hydrometeorological risk management but remains challenging for both numerical weather prediction (NWP) systems and data-driven models. We present CSU-PCAST, a deep learning-based ensemble forecasting framework for global precipitation prediction. The model is trained using ERA5 atmospheric and surface variables at 0.25{\deg} resolution with precipitation labels from NASA's IMERG dataset. CSU-PCAST uses 57 prognostic variables and static geographical fields to predict both atmospheric states and 6-h accumulated precipitation. The framework employs a Swin Transformer backbone with stochastic noise conditioning, temporal embeddings, and a dual-branch decoder for precipitation and non-precipitation variables. During inference, CSU-PCAST is initialized from operational GFS analyses and generates 30 ensemble members out to 15 days using an autoregressive strategy. Evaluation against GEFS over the full year of 2023 shows improved precipitation forecast skill at short lead times, including higher Critical Success Index (CSI) and lower RMSE during the first several forecast days. CSU-PCAST also reduces GEFS wet bias for light precipitation and dry bias at heavier precipitation thresholds. Probabilistic verification demonstrates lower CRPS, higher Brier Skill Scores at several thresholds, and improved ensemble reliability relative to GEFS, although both systems remain underdispersive. A case study of the Sanba extreme precipitation event further shows improved spatial structure and exceedance-probability guidance. These results demonstrate the potential of CSU-PCAST for short-to-medium-range ensemble precipitation forecasting while highlighting remaining challenges in extreme precipitation prediction and ensemble calibration.
arXiv:2604.17420v2 Announce Type: replace Abstract: Money laundering poses severe risks to global financial systems, driving the widespread adoption of machine learning for transaction monitoring. However, progress remains stifled by the lack of realistic benchmarks. Existing transaction-graph datasets suffer from two pervasive limitations: (i) they provide sparse node-level semantics beyond anonymized identifiers, and (ii) they rely on template-driven anomaly injection, which biases benchmarks toward static structural motifs and yields overly optimistic assessments of model robustness. We propose TransXion, a benchmark ecosystem for Anti-Money Laundering (AML) research that integrates profile-aware simulation of normal activity with stochastic, non-template synthesis of illicit subgraphs.TransXion jointly models persistent entity profiles and conditional transaction behavior, enabling evaluation of "out-of-character" anomalies where observed activity contradicts an entity's socio-economic context. The resulting dataset comprises approximately 3 million transactions among 50,000 entities, each endowed with rich demographic and behavioral attributes. Empirical analyses show that TransXion reproduces key structural properties of payment networks, including heavy-tailed activity distributions and localized subgraph structure. Across a diverse array of detection models spanning multiple algorithmic paradigms, TransXion yields substantially lower detection performance than widely used benchmarks, demonstrating increased difficulty and realism. TransXion provides a more faithful testbed for developing context-aware and robust AML detection methods. The dataset and code are publicly available at https://github.com/chaos-max/TransXion.
arXiv:2601.01776v2 Announce Type: replace Abstract: Understanding ultrathin liquid-film dynamics is crucial for unraveling complex interfacial phenomena, yet deriving governing equations directly from experimental observations remains challenging. This study proposes a data-driven approach to model droplet dynamics, capturing liquid-film thickness on the nanometer scale in the form of a partial differential equation. As a challenging test case, we examine the superspreading wetting of surfactant-free nanofluids, a phenomenon whose physical mechanism defies standard theoretical explanations. We apply a sparse identification algorithm to spatiotemporal film-thickness profiles resolved at the nanometer scale using phase-shifting imaging ellipsometry. For a pure solvent, the discovered governing equation recovers classical lubrication physics driven by disjoining pressure and evaporation. In contrast, the nanofluid dynamics necessitates an additional, unique transport term scaling with the gradient of the inverse film thickness. Theoretical scaling analysis suggests this term represents a nanoparticle-induced bias flux, consistent with a hypothesized capillary wicking mechanism within the precursor film. The identification of the current nanofluid-specific term underscores the efficacy of integrating high-precision experimental measurements with data-driven modeling to discover hidden physics and generate testable hypotheses in complex wetting dynamics.
arXiv:2602.08995v2 Announce Type: replace Abstract: Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such misaligned actions may arise from external attacks (e.g., indirect prompt injection) or from internal limitations (e.g., erroneous reasoning). They not only expose CUAs to safety risks, but also degrade task efficiency and reliability. This work makes the first effort to define and study misaligned action detection in CUAs, with comprehensive coverage of both externally induced and internally arising misaligned actions. We further identify three common categories in real-world CUA deployment and construct MisActBench, a benchmark of realistic trajectories with human-annotated, action-level alignment labels. Moreover, we propose DeAction, a practical and universal guardrail that detects misaligned actions before execution and iteratively corrects them through structured feedback. DeAction outperforms all existing baselines across offline and online evaluations with moderate latency overhead: (1) On MisActBench, it outperforms baselines by over 15% absolute in F1 score; (2) In online evaluation, it reduces attack success rate by over 90% under adversarial settings while preserving or even improving task success rate in benign environments.
arXiv:2605.24696v2 Announce Type: replace Abstract: Streaming intrusion detection systems must process flows continuously under bounded memory, yet most leave alerting-threshold selection as a post-hoc tuning problem incompatible with production, where operators commit in advance to alert budgets, misclassification costs, and Service Level Objectives. We present CALIBURN, a streaming alerting pipeline that derives its decision threshold from these operational inputs rather than a label-dependent search. CALIBURN composes five layers on one streaming substrate: truncated Bayesian online change-point detection; isotonic calibration of the posterior to a conditional attack probability; cost-sensitive thresholding from operator costs; a Conformal Risk Control (CRC) wrapper mapping an alert budget alpha to a false-positive-bounded threshold under exchangeability; and multi-window burn-rate alerting from Site Reliability Engineering. Each layer is established; the contribution is the integration and a falsifiable finding about it: the behaviour of calibration and conformal risk control is strongly regime-dependent across attack prevalence. Across three regimes -- LITNET-2020 (5.2%), CICIDS2017 (22%), UNSW-NB15 (64%) -- CALIBURN reaches AUC-PR 0.943 in the rare-attack regime it targets, beating the best streaming baseline by 2.21x and the best batch reference by 4.12x, with isotonic calibration cutting Brier score 30%; it stays strongest among streaming methods at moderate prevalence; and all converge to the prevalence floor under base-rate inversion. A TTL-feature ablation shows this high-prevalence collapse is intrinsic to streaming, not a dataset artifact. We further identify two mechanisms -- a theoretical CRC overshoot 2B/(n0+1) and an empirical-density degeneracy -- collapsing conformal alerting at very small alpha, and propose both as pre-deployment checks. Code and artifacts: Apache 2.0, Zenodo DOI 10.5281/zenodo.20074590.
arXiv:2603.11625v2 Announce Type: replace Abstract: While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies. Current architectures typically suffer from massive anatomical redundancy due to the direct concatenation of consecutive 2D slices and lack the flexibility to handle heterogeneous information densities across different slices using fixed pruning ratios. To address these challenges, we propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework specifically designed for efficient 3D medical image understanding. MedPruner introduces a two-stage mechanism: an Inter-slice Anchor-based Filtering module to eliminate slice-level temporal redundancy, followed by a Dynamic Information Nucleus Selection strategy that achieves adaptive token-level compression by quantifying cumulative attention weights. Extensive experiments on three 3D medical benchmarks and across three diverse medical VLMs reveal massive token redundancy in existing architectures. Notably, MedPruner enables models such as MedGemma-1.5 to maintain or even exceed their original performance while retaining fewer than 5\% of visual tokens, thereby reducing visual-token overhead and validating the necessity of dynamic token selection for practical clinical deployment. Our code is available at https://github.com/CUHK-AIM-Group/MedPruner.
arXiv:2604.20754v2 Announce Type: replace Abstract: It has been shown that, regarding a terminating right-linear overlay term rewrite system (TRS), any rewrite sequence terminating in a normal form can be simulated by an innermost reduction. In this paper, using this simulation property, we show that for a right-linear overlay TRS, there is no infinite minimal dependency-pair chain if and only if there is no infinite innermost minimal dependency-pair chain. As a consequence, termination and innermost termination coincide for the class of right-linear overlay TRSs.
arXiv:2604.27693v2 Announce Type: replace Abstract: We introduce a new logic, called \emph{cluster first-order logic}, a restricted fragment of first-order logic specifically designed to study order invariance. An order-invariant formula is one on a vocabulary that contains an order; however, whether a structure satisfies it or not is independent of the interpretation of the order. We show that while order-invariant cluster first-order logic can define properties outside the scope of plain first-order logic in general, its expressive power is included in that of first-order logic when it comes to classes of bounded degree. We establish this result by explicitly constructing linear orders such that similar structures remain similar when they are expanded with these orders. This similarity-preserving, local-to-global approach is technically involved and somewhat counterintuitive, since adding an order usually reveals distinctions that are otherwise hidden due to the locality of first-order logic. We believe that this work can be a stepping stone toward applying such techniques to plain first-order logic and toward settling the question of the expressive power of order-invariant plain first-order logic.