arXiv:2606.05849v1 Announce Type: new
Abstract: Metasurfaces enable precise manipulation of electromagnetic waves for applications such as beam steering, sensing, and stealth technology. However, inverse design of metasurfaces with targeted EM responses remains challenging due to the computational expense of iterative full wave simulation driven optimization and the limited conditioning fidelity and diversity of existing generative approaches. To address these challenges, this paper presents a generative inverse design framework for controllable and physically consistent metasurface synthesis under continuous spectral constraints. The proposed approach employs a progressively growing Wasserstein generative adversarial network with gradient penalty integrated with feature wise linear modulation based conditioning for stable propagation of continuous spectral and fabrication constraints. EM consistency is embedded directly into the generative learning process through a surrogate assisted spectral alignment loss, enabling physics constrained generation during training. Further, a determinantal point process based diversity regularization strategy is incorporated to generate geometrically diverse yet spectrally consistent realizations for the same target response. The effectiveness of the proposed framework is demonstrated through the generation of practically realizable metasurface absorbers exhibiting diverse reflection characteristics in the frequency range of 2 to 18 GHz. EM simulations validate that the generated designs meet the target specifications with high accuracy. The final proposed framework achieved an average mean squared error of 0.0052, diversity score of 0.8730, band alignment accuracy of 0.8533, and a valid EM design generation percentage of 89.57, clearly demonstrating its capability to generate highly accurate, diverse, electromagnetically consistent and fabrication realizable metasurface configurations.
Science Journals
arXiv:2606.05836v1 Announce Type: new
Abstract: Large language models have substantially advanced Text-to-SQL systems, yet applying them to enterprise-scale databases remains challenging. Real-world databases often contain large and heterogeneous schemas, incomplete metadata, dialect-specific SQL syntax, and complex analytical questions that are difficult to solve with a single SQL query. To address these challenges, we propose ProSPy, a Profiling-driven SQL--Python agentic framework for enterprise-scale Text-to-SQL. ProSPy structures the reasoning process into four stages: it first extracts fine-grained data evidence through automatic profiling, progressively prunes large schemas into task-relevant contexts, fetches intermediate views through a dialect-agnostic SQL interface, and finally performs flexible downstream analysis with Python. This design combines the efficiency of SQL over large databases with the flexibility of Python-based analysis, while reducing reliance on unreliable metadata and improving robustness across SQL dialects. Experiments on Spider 2.0-Lite and Spider 2.0-Snow show that ProSPy consistently outperforms strong baselines with both open-source and proprietary models, achieving execution accuracies of 60.15% and 60.51% with Claude-4.5-Opus, without majority voting. Further analysis shows that ProSPy is robust to SQL dialect variations and achieves a favorable trade-off between schema recall and precision.
arXiv:2606.05586v1 Announce Type: new
Abstract: In remote sensing object detection, Convolutional Neural Networks (CNNs) excel at capturing local details while Vision Transformers (ViTs) are better at global context modeling. However, existing detectors typically rely on a single fixed backbone or a manually designed hybrid architecture, and thus fail to adaptively exploit these complementary strengths across inputs of diverse complexity. To address this limitation, we propose Backbone Module Composition via Reinforcement Learning (BMCR). BMCR dynamically assembles input-adaptive inference paths from reusable modules decomposed from off-the-shelf CNN and ViT backbones. To enable such cross-family composition, we first construct an extensible module toolbox. Specifically, we decompose representative CNN and ViT backbones into reusable functional modules and encapsulate each module with explicit structural, semantic, and computational metadata for compatibility-aware assembly. To bridge the gap between grid-based CNN features and token-based ViT representations, we design a lightweight Optimal Transport (OT) based transition interface that ensures distribution-aware alignment while respecting spatial consistency. The backbone composition process is then formulated as a sequential decision problem, in which a policy network progressively selects task-relevant modules according to intermediate multi-scale observations. To stabilize the joint optimization of reusable modules and the routing policy, we further develop an Adaptive Module Cooperative Optimization (AMCO) strategy that coordinates module updating, routing exploration, and reward assignment during training. On DOTA-v1.0, DOTA-v1.5 and DIOR-R, BMCR achieves 79.31\%, 73.41\% and 71.86\% mAP, respectively, surpassing strong static and dynamic baselines by up to 2.5 points while maintaining competitive efficiency.
arXiv:2510.08934v3 Announce Type: replace-cross
Abstract: This paper studies a boundary between local self-application and global self-certification. Irrational quantities are treated operationally, as procedures whose approximations are refined by effective update rules. The golden ratio $\Phi$ is used as a model of stable local recurrence: the reciprocal update $R(x)=1+1/x$ has a unique positive fixed point and admits finite witnessed approximations. By contrast, global reflection asks a system to certify its own correctness uniformly. The proof-theoretic claim is therefore contrastive: primitive-recursive proof checking and local soundness preserve correctness through bounded checks and bounded witnesses, but they do not yield internal global reflection. No complexity advantage, decision procedure, or new reflection principle is claimed.
arXiv:2504.20728v2 Announce Type: replace-cross
Abstract: We study strong approximation of solutions of SDEs with bounded $\alpha$-H\"older continuous drift coefficient and constant diffusion coefficient at time point $1$. Recently, it was shown in [arXiv:1909.07961v4 (2021)] that for such SDEs the equidistant Euler scheme achieves an $L^p$-error rate of at least $(1+\alpha)/2$, up to an arbitrary small $\varepsilon$, for all $p\geq 1$ and $\alpha\in (0,1]$, in terms of the number of evaluations of the driving Brownian motion $W$. In this article, we prove a matching lower error bound for $\alpha\in (0,1)$. More precisely, we show that for every $\alpha\in (0,1)$, the $L^p$-error rate $(1+\alpha)/2$ of the Euler scheme in [arXiv:1909.07961v4 (2021)] cannot be improved in general by any numerical method based on finitely many evaluations of $W$ in $[0,1]$. Up to now, this result was known only for $\alpha=1$. Even stronger, an $L^p$-error rate better than $(1+\alpha )/2$ cannot be achieved, even if algorithms additionally use a finite number of time integrals of $W$. Thus, Wagner-Platen type schemes are not superior to the Euler scheme.
Additionally, we extend a result from [arXiv:2402.13732v2 (2024)] on final time approximation of SDEs with a bounded drift coefficient of fractional Sobolev regularity $\alpha\in (0,1)$. We prove that for every $\alpha\in (0,1)$, the $L^p$-error rate $(1+ \alpha )/2$ shown in [arXiv:2101.12185v2 (2022)] for the equidistant Euler scheme can essentially not be improved by any numerical method based on finitely many evaluations and time integrals of $W$ in $[0,1]$. This lower bound was known from [arXiv:2402.13732v2 (2024)] only for $\alpha\in (1/2,1)$, $p=2$ and numerical methods based on finitely many evaluations of $W$.
For the proof of our results we use variants of the Weierstrass function as a drift coefficient and we extend the coupling of noise technique introduced in [arXiv:2010.00915v1 (2020)].
arXiv:2403.09941v5 Announce Type: replace-cross
Abstract: We solve constrained optimal transport problems in which the marginal laws are given by the laws of solutions of stochastic differential equations (SDEs). We consider SDEs with irregular coefficients, making only minimal regularity assumptions. We show that the so-called synchronous coupling is optimal among bicausal couplings, that is couplings that respect the flow of information encoded in the stochastic processes. Our results provide a method to numerically compute the adapted Wasserstein distance between laws of SDEs with irregular coefficients. We show that this can be applied to quantifying model uncertainty in stochastic optimisation problems. Moreover, we introduce a transformation-based semi-implicit numerical scheme and establish the first strong convergence result for SDEs with exponentially growing and discontinuous drift.
arXiv:2606.04899v2 Announce Type: replace
Abstract: Trusted Execution Environments (TEEs)-aided federated learning protocols emerge as promising solutions to counter server-side adversaries and ensure the trustworthiness of the server. In this paper, we dissect existing protocols and demonstrate that server-side adversaries can still manipulate client selection and replay aggregation to compromise system robustness and privacy, by exploiting TEE limitations, i.e., state rollback and I/O manipulation. To this end, we present DIST-FL, a distributed system of servers guarded by multiple TEEs forming an append-only ledger for privacy-preserved, robust FL aggregation. Specifically, DIST-FL ensures operation linearizability to thwart state rollback attacks and incorporates inputs from reliable servers to mitigate I/O manipulation threats. We implement DIST-FL and conduct evaluations in WAN settings. Experimental results demonstrate that DIST-FL can effectively counter the proposed attacks and match the single-TEE's performance while offering a 6x throughput boost over its counterparts, leveraging TEE's computational advantages.
arXiv:2606.04882v2 Announce Type: replace
Abstract: Finite Difference Schemes are widely used in the approximation of different hyperbolic (wave-like) differential equations, and are particularly important for seismic wave modelling and its applications. Classical methods based on Taylor Series are dominant in the literature; however, it is known that these methods can suffer from excessive numerical dispersion. In this paper, we review and extend existing high-order in space finite difference schemes for acoustic wave propagation, featuring different stencil geometries ranging from classical cross stencils to stencils with rhombus or square-like shapes, and propose a general mathematical framework for their derivation. The numerical implementation is performed in a symbolic, high-level framework (Devito), which compiles and runs highly optimized, stencil-based computations, allowing for a low-level interpretation of the methods efficiency. We demonstrate that non-cross stencil shapes, such as rhombus and square-based stencils, do not necessarily provide added accuracy or dispersion reduction in general, despite their increased computational cost. However, results on both idealized and realistic velocity models confirm the benefits of using dispersion-optimized cross-stencils, indicating adequate accuracy with reduced computational cost on more compact stencils compared to classic approaches. Finally, our implementation of the methods provides ease of use for full-scale acoustic seismic inversion problems using Devito.
arXiv:2306.09712v2 Announce Type: replace
Abstract: In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline. Online methods explore the environment at significant time cost, and offline methods efficiently obtain reward signals by sacrificing exploration capability. We propose semi-offline RL, a novel paradigm that smoothly transits from offline to online settings, balances exploration capability and training cost, and provides a theoretical foundation for comparing different RL settings. Based on the semi-offline formulation, we present the RL setting that is optimal in terms of optimization cost, asymptotic error, and overfitting error bound. Extensive experiments show that our semi-offline approach is efficient and yields comparable or often better performance compared with state-of-the-art methods.
arXiv:1505.07152v3 Announce Type: replace
Abstract: We investigate the effect of series perturbation on the second-order dipole-dipole interactions between strontium atoms in the $5sns({^1}S_0)$ and $5snp({^1}P_1)$ Rydberg states as a means of engineering long-range interactions between atoms. The series perturbation in these atoms enables modifying the strength and the sign of the interaction by varying the principal quantum number $n$ of the Rydberg electron. We utilize experimentally available data to estimate the importance of perturber states, and find that van der Waals interaction between two strontium atoms in the $5snp({^1}P_1)$ states shows strong peaks outside the anticipated hydrogenic $n^{11}$ scaling. We identify this to be the result of the perturbation of $5snd({^1}D_2)$ intermediate states by the $4d^2({^1}D_2)$ and $4dn's({^1}D_2)$ states in the $n<20$ range. This demonstrates that divalent atoms offer a unique advantage for generating substantially stronger or weaker inter-atomic interactions than those that can be achieved using alkali metal atoms. This is due to the highly perturbed spectra of divalent atoms and other multivalent atoms that can persist up to high $n$. Such irregularities can be especially useful in engineering asymmetric Ry blockade requiring the simultaneous presence of both ``weak'' and ``strong'' interactions.
arXiv:2606.06444v1 Announce Type: cross
Abstract: Audio encoders are critical to modern audio applications as large language models (LLMs) increasingly rely on a single encoder for diverse inputs. While self-supervised learning (SSL) has yielded strong domain-specific encoders like speech or music experts, multi-domain approaches like USAD and SPEAR remain limited in coverage and evaluation. Recent studies also suggest supervised encoders align better with audio LLMs. We present USAD 2.0, a universal encoder integrating knowledge from both SSL and supervised foundation models. USAD 2.0 introduces domain-aware distillation to address teacher mismatch, extends coverage to the music domain, and adds second-stage supervised distillation for downstream use. We further scale the model to one billion parameters via depth scaling. Experiments show USAD 2.0 achieves strong or state-of-the-art performance across probing and LLM-based evaluations.
arXiv:2606.06284v1 Announce Type: new
Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step.
We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweight precondition-effect contracts to expose only the minimal next-step tool frontier needed to advance from the current state toward the user goal. Across multi-step tool-use tasks, we compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations, measuring task success, wrong-tool calls, premature actions, tool exposure, and token cost. In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success while reducing visible tools from 100 to one per step and reducing token usage by about 90% relative to all-tools exposure.
arXiv:2606.06281v1 Announce Type: new
Abstract: Touch sensing is beneficial for solving a wide variety of manipulation tasks. While there exists a wide range of tactile sensors with different properties, exploiting the fusion of multiple heterogeneous tactile sensors to improve manipulation learning remains underexplored. We present Multi-Resolution Tactile Sensing (MiTaS), a representation framework that leverages multiple tactile sensors operating at different temporal resolutions in order to solve complex contact-rich manipulation tasks. We propose a novel architecture using modality-specific convolutional stems and transformer-based fusion that effectively fuses information from an RGB camera stream, a vision-based GelSight Mini sensor and a high-frequency event-based Evetac sensor. This multi-sensor representation then conditions a flow-matching policy for solving downstream tasks. Experimental results across five contact-rich manipulation tasks demonstrate the effectiveness of multi-resolution tactile features in imitation learning. MiTaS achieves an average success rate of 80 %, while vision-only (31 %) and visual-tactile (54 %) baselines cannot solve the task reliably. Co-training a visuo-tactile model with multi-tactile data boosts performance by over 10 \% in certain tasks, without having access to the Evetac sensor during policy evaluation. A detailed sensor-reading and attention analysis reveals the importance of different sensors throughout task execution, validating our multi-resolution tactile sensing approach. Project Page: http://mitas-touch.github.io.
arXiv:2603.17925v2 Announce Type: replace-cross
Abstract: We consider a variant of sequential testing by betting where, at each time step, the statistician is presented with multiple data sources (arms) and obtains data by choosing one of the arms. We consider the composite global null hypothesis $\mathscr{P}$ that all arms are null in a certain sense (e.g. all dosages of a treatment are ineffective) and we are interested in rejecting $\mathscr{P}$ in favor of a composite alternative $\mathscr{Q}$ where at least one arm is non-null (e.g. there exists an effective treatment dosage). We posit an optimality desideratum that we describe informally as follows: even if several arms are non-null, we seek $e$-processes and sequential tests whose performance are as strong as the ones that have oracle knowledge about which arm generates the most evidence against $\mathscr{P}$. Formally, we generalize notions of log-optimality and expected rejection time optimality to more than one arm, obtaining matching lower and upper bounds for both. A key technical device in this optimality analysis is a modified upper-confidence-bound-like algorithm for unobservable but sufficiently "estimable" rewards. In the design of this algorithm, we derive nonasymptotic concentration inequalities for optimal wealth growth rates in the sense of Kelly [1956]. These may be of independent interest.
arXiv:2509.02971v2 Announce Type: replace-cross
Abstract: Flow-based generative models can face numerical challenges on scientific data with multiscale Fourier spectra, often producing large errors at fine scales. We approach this problem within the flow matching and stochastic interpolants framework, through the principled design of noise distributions and interpolation schedules. Working in function space ensures that the generative model remains well defined as the resolution is refined; the Lipschitz regularity of the drift is important to both this function-space well-posedness and the integration cost at fixed resolution. The central observation is that the noise should be at least as rough as the target distribution -- measured by Fourier-spectrum decay -- in order to keep the Lipschitz constant finite. For Gaussian and near-Gaussian targets whose fine-scale structure is known, matched-spectrum noise improves numerical efficiency over standard white-noise choices. For more complex non-Gaussian targets, matched-spectrum noise may not be sufficient, and we propose scale-adaptive interpolation schedules to mitigate the terminal-time stiffness that arises when the noise is rougher than the data. Numerical experiments on synthetic Gaussian random fields and on invariant measures of the stochastic Allen--Cahn and Navier--Stokes equations illustrate the approach and demonstrate its ability to generate high-fidelity samples at lower computational cost than traditional approaches.
arXiv:2606.05740v1 Announce Type: new
Abstract: Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias. In this work, we identify a complementary optimization-level pathology: inter-class gradient interference within shared representations, where gradients from majority classes suppress minority-class learning. To analyze this phenomenon, we introduce a diagnostic framework based on layer-wise gradient flow analysis and a Gradient Conflict Matrix, which quantifies interference using cosine similarity between class-specific gradients. Using this framework, we study multi-branch convolutional architectures and propose a lightweight modification, Class-Specific Branch Attention (CSBA), that enables branch-specific channel reweighting to reduce gradient coupling. This mechanism promotes implicit feature decoupling across branches while preserving architectural simplicity. Empirically, CSBA improves minority-class performance, increasing the F1 score for the Physical-Damage class from 0.261 to 0.522 under severe imbalance, while maintaining comparable overall accuracy. Validation on CIFAR-10-LT confirms that this behavior generalizes across imbalanced visual recognition settings, with Macro-F1 improving from 0.595 to 0.655. More broadly, our findings highlight the importance of considering optimization dynamics alongside statistical methods when designing architectures for imbalanced learning.
arXiv:2606.05731v1 Announce Type: new
Abstract: In-season crop type mapping is critical for food security in the face of increasingly extreme climate-related threats to crops. Currently, the USDA Cropland Data Layer provides crop type labels at 30m resolution and is available the February after harvest, but no product exists that maps crop types before harvest with satisfactory accuracy that would allow emergency managers to respond to crop threats in near real time. Furthermore, the relative advantages of a wide range of algorithms have not been evaluated in a way that accounts for interannual variability, until this study. Here, Harmonized Landsat-Sentinel surface reflectance imagery time series and crop rotation history information are combined to map corn in Iowa and almonds in California at 30m resolution accurately by early June in unseen years, with robust quantification of uncertainty due to phenology and crop distribution. Thousands of model configurations across ten machine learning algorithms were compared using a year-wise cross-validation and a suite of metrics. Hyperparameter search revealed Support Vector Machines to be the most successful algorithm overall, with a mean F1 score of 0.74 (0.59) across five unseen validation years for almonds by early June in California (corn by early June in Iowa). Interannual variation was a large source of uncertainty, but patterns showed the potential to further improve performance with ensemble approaches or ancillary data. Future work may extend these methods to include multiclass maps of all crop types, CONUS-wide maps, and in-season crop yield forecasting.
arXiv:2606.06171v1 Announce Type: cross
Abstract: Physics-Informed Neural Networks inherently suffer from task interference because they rely on a shared parameter space to satisfy both governing differential equations and boundary conditions. We analyze this structural conflict using the Fisher Information Matrix to quantify the effective degrees of freedom ($d_{eff}$) in a physics-constrained model. Unlike the classical $d_{eff}$ which measures how many parameter directions are informed by data against a statistical prior, our $d_{eff}$ measures the dimension of the parameter directions unconstrained by the differential operator. For operators with finite-dimensional kernel, we show that $d_{eff}$ converges to the kernel dimension exactly, independent of network width, depth, or activation function, recasting it from a fit diagnostic into a structural invariant of the underlying continuous operator. For operators with infinite-dimensional kernel, $d_{eff}$ instead measures the network's finite-dimensional representational bandwidth for that kernel rather than recovering an integer invariant. Importantly, $d_{eff}$ also serves as an a priori structural diagnostic. Driving $d_{eff}$ of a well-posed problem to zero certifies that the physics and boundary constraints have absorbed the network's free directions. Building on this characterization, we introduce subspace projection strategies for boundary adaptation. Rather than retraining from scratch, we project parameter updates into the null space of the pre-trained physics operator so that new boundary conditions are satisfied without disturbing the learned physics. Gradient-based fine-tuning can match or exceed this but needs more wall-clock time and tuning, whereas subspace projection delivers near-equivalent quality in seconds to minutes. We validate on linear and nonlinear operators, demonstrating accurate adaptation to initial and boundary shifts and unencountered constraint types.
arXiv:2606.05571v1 Announce Type: new
Abstract: Sound effects (SFX) datasets and libraries often employ distinct tagging schemes, taxonomies, and metadata structures. This creates challenges for research on SFX classification and generation because incompatible taxonomies lead to siloed datasets that might require individualized approaches, result in non-comparable outcomes, and prevent data merging strategies. We propose a modular dataset relabeling framework that adopts the Universal Category System (UCS), an industry-standard hierarchical taxonomy for sound effects, as a shared structural foundation. This open-source framework enables us (i) to convert tags of existing datasets to UCS with a rule-based multi-stage pipeline and conflict resolution to achieve high automatic conversion rates, (ii) to suggest a stratified dataset split for the new labels, and (iii) to combine multiple datasets. To showcase the practical utility, we introduce the EnvSound-UCS dataset, a publicly available unified UCS-compliant dataset of environmental sounds with 58,057 sound clips from three sources: AudioSet, FSD50K, and ESC-50.
arXiv:2606.05974v1 Announce Type: cross
Abstract: Since the initial disclosure of the extraordinary piezoelectric coefficients of Potassium sodium niobate (KNN) in near-equimolar bulk ceramics, its development trajectory has resembled a rollercoaster, with its integration into microelectronics severely lagging due to thermodynamic stability issues and poor planar process compatibility. In this work, we revisit the bulk-derived phase diagram for the specific case of thin films integrated on silicon. By systematically investigating Mn-doped K1-xNaxNbO3 films grown on 8-inch wafers, we demonstrate that the optimal stoichiometry for thin films fundamentally diverges from the bulk equimolar standard. A Na-rich composition (> 70 at.%) is required to overcome substrate-induced constraints, effectively suppressing pyrochlore formation and chemical phase segregation while promoting dense columnar growth with a complete (001) out-of-plane polar orientation. Consequently, Na-rich films deliver outstanding functional properties, reaching remanent polarizations up to 14 uC cm-2, with piezoelectric coefficients of d33f= 79 pm/V and e31f = 10 C/m2. Supported by Density Functional Theory simulations, we correlate this enhancement with improved stability and a strain-driven structural reorientation toward a lower-symmetry monoclinic phase with tilted polarization. By redefining the phase engineering rules for wafer-scale thin films, our results establish a clear route toward KNN integration in microsystems.
arXiv:2508.19006v2 Announce Type: replace-cross
Abstract: This study investigates the pre-trained RNN attention models with the mainstream attention mechanisms, such as additive attention, Luong's three attentions, global self-attention and sliding window sparse attention, for the empirical asset pricing research on the top 420 large-cap US stocks. This is the first paper on the large-scale state-of-the-art (SOTA) attention mechanisms applied in the asset pricing context. They overcome the limitations of the traditional machine learning-based asset pricing, such as mis-capturing the temporal dependency and short memory. Moreover, the enforced causal masks in the attention mechanisms address the future data leaking issue ignored by the more advanced attention-based models, such as the classic Transformer. The proposed attention models also consider the temporal sparsity characteristic of asset pricing data and mitigate potential overfitting issues by deploying the simplified model structures. This provides some insights for future empirical economic research. All models are examined in three periods, which cover pre-COVID-19, COVID-19 and one year post-COVID-19, for testing the stability of these models under extreme market conditions. The study finds that in value-weighted portfolio back testing, the global self-attention model and the sliding window sparse attention model exhibit excellent capabilities in deriving the absolute returns and hedging downside risks, while they achieve an annualized Sortino ratio of 2.0 and 1.80 respectively in the period with COVID-19 in the static transaction cost scenario. Moreover, the sliding window sparse attention model performs more stably than the global self-attention model from the perspective of absolute portfolio returns with respect to the size of stocks' market capitalization.
arXiv:2606.05844v1 Announce Type: new
Abstract: Rule-based Intrusion Detection and Prevention Systems (IDPS) offer precise attack detection as well as mitigation, however their manually crafted, signature-driven rules limit adaptability to emerging and zero-day threats. Additionally, existing public datasets (e.g., CICIDS2017, UNSW-NB15) focus on traffic classification and provide little structured information to support automatic rule synthesis or prevention logic. To address this gap, we propose Generative Thread Intelligence (GenTI) \footnote{GenTI refers to the proposed framework, and GTI refers to the dataset.} an LLM-driven benchmark for automatic generation of IDPS rules targeting unseen attacks. The dataset (GTI) aggregates over 150k detection and prevention rules from Snort, Suricata, Emerging Threats, as well as 50k YARA, each annotated with protocol behavior, payload signatures, contextual relationships, mappings to Cyber Threat Intelligence (CTI), along with actionable response types (alert, drop, reject). Moreover, on top of this corpus we design an LLM-based pipeline that transforms analyst prompts and representative payloads into deployable rules via structured prompt engineering, Chain-of-Thought (CoT) reasoning, as well as a Chain-of-Verification (CoVe) loop for syntactic, semantic, and security validation. The generated rules are executed in real time on (Snort/Suricata) and evaluated by syntax accuracy, semantic similarity, CTI coverage, security effectiveness as well as unseen attacks detection. Furthermore, our GenTI instantiation achieves a composite rule-quality score of 89.4\%, with 94.8\% CTI coverage, improving unseen attacks detection from 45\% to 87.4\% and reducing the false-positive rate from 8.5\% to 2.3\%. Overall, GenTI establishes the first large-scale benchmark that tightly couples rule-level CTI with LLM-based automation, enabling adaptive, self-evolving IDPS.
arXiv:2506.03232v2 Announce Type: replace-cross
Abstract: Spreadsheet tools are widely accessible to and commonly used by K-12 students and teachers. While spreadsheets are not ideal for many types of statistical analysis, they have an important role in data collection and organization. From a pedagogical standpoint, spreadsheets make data visible and easy to interact with, facilitating student engagement in data exploration, analysis, and computation. Though not suitable for all tasks, spreadsheets can facilitate learning and practicing data and computing skills for K-12 students. This paper 1) demonstrates the potential utility of spreadsheets in K-12; 2) reviews prior frameworks and standards that are relevant for K-12 data tools; and 3) proposes data-driven data skills to help develop data acumen and computational fluency. We provide some example activities, identify challenges and barriers to adoption, suggest pedagogical approaches to ease the learning curve for instructors and students, and discuss the need for professional development to facilitate deeper use of spreadsheets for data science and STEM disciplines.
arXiv:2606.06262v1 Announce Type: new
Abstract: Climate change and extreme weather are increasing the vulnerability of power systems globally, particularly in emerging economies such as Indonesia. Yet, existing studies often assess these impacts in isolation, focusing on individual components or specific hazards, leaving system-level implications under-examined. To address this gap, we develop an integrated, spatially explicit approach to assess an energy system's climate-related vulnerabilities and their impacts, and apply the approach to Indonesia. We quantify climate-based vulnerabilities in generation and transmission infrastructure as well as in demand by distinguishing stressors (temperature rise) and shocks (disruptive hazards due to sea-level rise, flooding, and landslides). Through geospatial data analysis, derating models, and regression analysis, we examine existing and planned assets and demand under historical and future climate conditions. Results indicate that both existing and planned generation are likely to experience stress, which implies a reduction in usable capacity, even as electricity demand increases due to temperature rise, and transmission assets face potential disruption from climate change-induced shocks. Together, these effects erode reserve margins by up to 36 percentage points under the 10-year plan, indicating a substantial reduction in system resilience. The largest system, Jawa-Madura-Bali, experiences a 20.8 percentage point decline, leaving a remaining margin of 26.5%, below the 10-year planning threshold. Importantly, the findings suggest that a growing share of future capacity expansion may be absorbed by climate-induced losses, implying that adaptation-related investments may increasingly be required simply to maintain existing supply levels rather than meet future requirements. We conclude that there is an urgent need to embed climate considerations more explicitly into power sector planning.
arXiv:2606.05274v1 Announce Type: new
Abstract: Electro-Hydrostatic Actuators (EHAs) are widely used in aerospace and industrial systems, where timely detection of sensor anomalies is essential to ensure safe and reliable operation. However, the large volume and high sampling frequency of EHA sensor data pose challenges for accurate and efficient anomaly detection. Conventional statistical and classical machine-learning methods such as Z-score, Interquartile Range (IQR), Median Absolute Deviation (MAD), Isolation Forest, Gaussian Mixture, and k-means often fail to capture the temporal dependencies inherent in EHA signals, resulting in limited detection accuracy and elevated false-alarm rates. Furthermore, systematic evaluations of data-driven anomaly detection approaches for EHA systems remain scarce, particularly under varying operational conditions. This study presents an offline anomaly-detection framework for univariate EHA sensor signals, focusing on temperature and pressure data collected from a controlled test bench. The method employs a reconstruction-based Long Short-Term Memory (LSTM) autoencoder, calibrated and evaluated using validation-set reconstruction-error distributions. Performance is assessed across multiple fault-injection scenarios using accuracy, precision, recall, and F1-score, complemented by sensitivity analyses under varying operating conditions. The LSTM autoencoder achieved an average accuracy of 99.0\%, precision up to 100\%, recall between 90.2\% and 99.6\%, and F1-scores from 93.1\% to 99.8\%, demonstrating high detection sensitivity and a very low false-alarm rate across all evaluated sensors. These results highlight the feasibility of data-driven offline anomaly detection for EHAs. Future work will focus on adapting the developed framework for an online (real-time) environment.