Papers

The Asset Administration Shell (AAS) is a cornerstone of Industry 4.0 and the Digital Product Passport, providing standardized digital representations of industrial assets. While manufacturers already maintain extensive technical product documentation, generating AAS instances from existing product datasheets remains a labor-intensive task because technical information is extracted from heterogeneous document structures and often involves company-specific terminology and conventions. In this work, we present AAS-RAIL, a retrieval-augmented information extraction (IE) approach that automatically generates Asset Administration Shells from PDF product datasheets using large language models (LLMs). Instead of relying on a fixed set of few-shot examples, the proposed retrieval-augmented in-context learning (RAIL) approach retrieves LLM-generated extraction helpers from similar Asset Administration Shells to provide instance-specific in-context learning (ICL). This enables the model to adapt its extraction behavior to company-specific naming conventions and formatting styles without fine-tuning. Our core contribution is the dynamic selection of company-specific AAS examples for each datasheet, replacing static prompting with an extraction pipeline that adapts to instances and combines semantic retrieval and structured information extraction. The proposed approach is evaluated on a collection of industrial product datasheets using a selection of open- and closed-weight LLMs. Experimental results show that RAIL consistently improves extraction quality over conventional few-shot prompting, yielding relative improvements of 30.4-52.4%. These results demonstrate that our approach provides an effective improvement for company-specific AAS generation.

Part I of this paper presented a decentralised framework for certifying small-signal stability in AC grids using frequency-domain quadratic constraints on individual grid subsystems. Part II extends the framework to a broader class of networks that contain unstable subsystems. In particular, we show that such unstable subsystems arise in many common scenarios, even when the aggregate system is stable and well behaved. Such subsystems must be stabilised by the closed-loop network interconnection, which complicates decentralised stability analysis. A stable hybrid representation resembling the power (PQ) model at low frequencies and the impedance (IV) model at high frequencies is then defined, to which the stability framework of Part I can be applied, allowing plug-and-play compatible conditions to be formulated. Furthermore, we show that at low frequencies, the characteristic loci in the Nyquist plot of the return ratio in this hybrid representation decouple into unbounded and bounded branches along the classical $P$-$\delta$ / $Q$-$V$ separation, and give sufficient conditions on each branch for ensuring system stability. The results are validated on the Kundur two-area system, where stability is certified, with a decentralised, plug-and-play compatible grid code covering the frequency ranges in which electromagnetic interactions arise.

Local pedestrian-vehicle forecasting spans heterogeneous physical scales: pedestrians combine root locomotion with articulated motion, whereas vehicles are rigid bodies described by kinematic state and oriented extent. Existing road-agent forecasters typically omit pedestrian articulation, while pose forecasters leave vehicle futures outside the learned rollout. We introduce PV-WM, a history-only world model over structured post-perception tracks. It recurrently advances pedestrian root motion, 15-joint articulation, and learned vehicle states within a synchronized heterogeneous state. The generated pedestrian and vehicle chunks supply the next recurrent boundary; vehicle boxes are reconstructed from predicted center and heading with observed extent, and P-V geometry is recomputed after every transition. Relative to a matched one-shot complete-state predictor, recurrent execution reduces Root ADE by 12.7% and MPJPE by 14.8%. Feedback interventions show that later predictions depend on the content, temporal order, and pedestrian identity of generated articulation. Across 824 aligned Waymo contexts, with 797 providing valid future vehicle support, PV-WM reduces Root ADE by 5.2%, MPJPE by 7.6%, P-V distance error by 11.9%, and oriented-box closest-approach error by 5.8% relative to a validation-selected Modular Specialist. The single-network model uses 57.1% fewer parameters, 96.5% lower average FLOPs per local scene, and 25.5% lower measured p95 latency. PV-WM unifies this heterogeneous future state while preserving type-specific pedestrian and vehicle dynamics.

In computational fluid dynamics, the numerical simulation of free-surface flows using interface capturing approaches (level set, pseudo-concentration) requires accurate resolution of a transport equation. In the present work, this equation is solved using a new formulation of the Lesaint–Raviart discontinuous Galerkin method, which is particularly suitable for problems without inflow boundaries. The motion is described by the incompressible Navier–Stokes equations with surface tension, discretized using the standard $P2-P1$ Taylor–Hood finite element method in space. Surface tension effects are represented using the so-called Continuum Surface Force model. Finally, the proposed approach is implemented and tested on several benchmarks, including the single rising bubble and the Rayleigh–Taylor instability.

Healthcare Internet of Things (HIoT) technology is revolutionising the healthcare industry by enabling real-time data collection and analysis for personalised patient care. However, the rapid expansion of HIoT technology introduces challenges such as increased latency and higher energy consumption in fog computing environments, particularly when managing battery-operated devices. To address these issues, this work proposes a novel scheduling strategy that optimises both power consumption and latency through task-oriented scheduling for HIoT tasks. The proposed strategy, named PLATOS (Power and Latency Aware Task Oriented Scheduling), is implemented in four sequential phases. In the first phase, HIoT tasks are categorised into three groups: priority-oriented, storage-oriented, and computational-oriented. The second phase focuses on latency optimisation by identifying the fog computing resources that yield the lowest execution delay for each task category. In the third phase, power optimisation is achieved by selecting the resources that minimise energy consumption. Finally, in the decision-making phase, high-performance fog resources are allocated to high-priority tasks while the remaining tasks are scheduled based on a mapped list derived from the latency and power optimisation phases. Simulation experiments conducted in iFogSim2 demonstrate that PLATOS reduces energy consumption by 18.72% and latency by 8.65% when compared to the state-of-the-art. These improvements enhance the efficiency and responsiveness of HIoT systems and contribute to more effective patient care and proactive healthcare service delivery.

Due to the proliferation of vehicle trajectory data enabled by advanced sensing technologies, path representation learning has become a pivotal task in intelligent transportation systems. Although existing self-supervised approaches have achieved promising performance, their dependence on deterministic contrastive learning paradigms and handcrafted view augmentation strategies inherently restricts their cross-scenario generalization capabilities. To address these limitations, we present DGCPath, an innovative Distribution-aware Generative Contrastive learning framework for Path representation. This framework establishes a synergistic connection between generative modeling and distributional contrastive learning, enabling the acquisition of robust and transferable feature embeddings. Specifically, our framework incorporates: (1) a diffusion-based view generator that autonomously produces semantically coherent yet diverse trajectory views from Gaussian noise; (2) a variational contrastive mechanism that enforces latent feature alignment at the distribution level, transcending conventional instance-wise consistency; and (3) a novel generative cross-supervision module that reinforces view-level consistency through cross-view reconstruction learning. Comprehensive evaluations on three real-world trajectory datasets demonstrate that DGCPath outperforms state-of-the-art baselines on two distinct downstream tasks, validating its enhanced generalization capability and representation effectiveness.

The rise of renewable generation in AC power systems calls for small-signal stability assessment methods that do not rely on centralised, system-wide models. In this two-part paper, we present a decentralised stability framework based on frequency-domain conditions imposed on local subsystems (many admitting equivalent graphical interpretations) which collectively imply the stability of the entire grid. The framework generalises many previously reported results, with added flexibility and plug-and-play compatibility provided by the additional degrees of freedom of the imposed conditions, the ability to mix conditions across frequency ranges, conditions on extended subsystems that couple buses to their connecting lines and loads, and a method to incorporate unstable subsystems. Detailed, heterogeneous device and line models are accommodated in the frequency domain using impedance, admittance, and power-flow models, making the framework suitable as a foundation for grid codes that enable plug-and-play functionality in inverter-dominated grids. Part I focuses on stable impedance and admittance representations and Part II extends the results to unstable subsystems, which are shown to be fundamentally present in many grid models. The results of Part I are validated on a modified 9-bus case study, demonstrating the reduced conservatism and significance of the proposed approach.

Rotary position embedding (RoPE) uses each token's integer position to determine the rotation applied inside attention. This works well for local token order, but increasing context length creates a positional train-test mismatch: RoPE produces relative rotations at offsets not seen during training. Methods that rescale, interpolate, randomize, or bias positions specify how attention handles those offsets, but still derive positional information from a growing token counter. We instead divide a token stream into units, retain ordinary RoPE positions within each unit, and assign every completed unit an address computed from its content. Adding units then applies the same learned map to new content rather than extending a positional range or an identifier table. We prove that this construction preserves local RoPE exactly, leaves the attention comparison between two fixed tokens unchanged when other units are inserted or reordered, and does not create new relative rotations merely because more units are added. In a character-level Tiny Shakespeare diagnostic, all-token validation perplexity remains approximately constant from contexts of 256 to 4096 characters. A second diagnostic shows that content-based addressing can retrieve and use information from multiple serialized facts. These are controlled shallow experiments, not scale benchmarks, but they support a direct prescription: use position to address locally and content to address across units.

Segmentation of complex structures in X-ray tomographic data is a fundamental task in biomedical research, but it often requires large amounts of precisely annotated data, making fully supervised approaches costly and difficult to scale. In this study, weakly supervised deep learning is investigated as a strategy to reduce annotation effort while maintaining accurate segmentation. A two-dimensional convolutional neural network based on the nnU-Net framework was adapted to a weak supervision setting using sparse dot-based annotations, complemented by a limited number of fully segmented images. The approach was evaluated on high-resolution microCT slices of rat kidneys, targeting the segmentation of renal glomeruli, which are small, low-contrast anatomical structures. Results indicate that weak supervision provides a meaningful learning signal, enabling reliable localization of glomeruli even in the absence of dense labels. Incorporating a small set of high-quality annotations substantially improves segmentation performance, approaching that of a fully supervised model. These findings highlight the potential of weakly supervised learning as an annotation-efficient strategy for the analysis of complex structures in X-ray tomographic data, and suggest that alternative loss formulations tailored to sparse annotations may further enhance performance.

This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine attacks via robust neighborhood direction estimation and history-based update trend prediction, rather than purely aggregating client models as in the existing work. In R-DPFL, each client first computes the current-round model update by aggregating the received neighborhood update vectors. It then predicts what this update should be based on its historical values and local model changes. Finally, R-DPFL computes the difference between these two quantities, adaptively clips this difference, and adds it to the local update. We prove convergence of the learning process through rigorous analysis and show that honest clients maintain stable personalized descent dynamics under Byzantine neighbor perturbations without requiring consensus among neighboring models. Extensive experiments on CIFAR-10 demonstrate that RDPFL consistently outperforms state-of-the-art decentralized and personalized federated learning baselines under heterogeneous and adversarial settings.

Searching large video collections is typically an interactive process in which users play two roles. First, they hold the search intent: the underlying goal that determines what content they seek and why. Second, users must operationalize this intent through an iterative search loop. Users translate their intent into queries, browse the retrieved candidates, and refine their queries based on the results. In this paper, we investigate the capabilities of modern Vision Language Models (VLM) and agentic approaches to reach search goals interactively and fully autonomously. Specifically, we study whether a provided initial specification of a search goal might be sufficient to solve traditionally interactive search tasks with an agentic system. Provided that the involved VLMs are not aware of the whole large video dataset in advance, the key challenge lies in the effective combination of an existing interactive video search system and a smart VLM agent controlling the system. While the search system provides indexing and efficient querying, the VLM-based agents analyze top-ranked items and make decisions about next actions. Our results show that modern agents can autonomously operate interactive video retrieval systems to solve many search tasks from an initial intent description, achieving performance competitive with strong historical expert-operated systems in several settings.

Robustness evaluation of large language models (LLMs) remains a critical challenge, particularly in assessing their sensitivity to perturbations in input data. In this work, we systematically evaluate LLM robustness across multiple dimensions, including word error rate, character repetition and duplication, modifications in choices, and variability in instruction following. To facilitate this evaluation, we construct a synthetic and augmented dataset encompassing a diverse set of LLM benchmarks, specifically targeting multiple-choice question (MCQ) datasets and instruction-following tasks. We conduct extensive experiments on LLMs of varying scales-small, medium, and large-as well as across base and instruction-tuned variants. Our analysis quantifies the variability in model responses under perturbed conditions and highlights discrepancies relative to baseline models. The findings provide insights into the stability of LLMs across different evaluation scenarios contributing to the development of more robust and reliable language models as well as robust evaluation methodologies.

Taxonomy induction aims to organize concept sets into coherent hierarchical structures. Recent LLM-based methods can induce taxonomies directly from flat term lists, avoiding the need for corpora, but degrade sharply as concept sets scale up. We argue that this degradation stems not only from context length limitations, but also from structural failures in hierarchical reasoning. To address this, we adopt a divide-and-merge paradigm that partitions concepts into smaller subsets, induces local taxonomies, and merges them into a global hierarchy. However, we identify two structural failure modes inherent to this paradigm: Structural Fragmentation, where partitioning weakens local hierarchical signals, and Parent Displacement, where locally plausible relations are misplaced in the global hierarchy. To address both, we propose SPARROW, a scalable taxonomy induction framework that combines structure-preserving spectral partitioning to retain hierarchical connectivity within each block, and constraint-guided incremental fusion that treats block-level relations as structural constraints rather than ground truth for global placement. Experiments on large-scale benchmarks show that SPARROW consistently achieves the strongest global structural quality across backbones. The code is available at https://github.com/rebeccazyr/SPARROW.

Dynamic sparse attention reduces long-context prefill cost by routing each query chunk to a small set of key chunks at every Transformer layer. The sparse attention kernel avoids most token interactions, but the router still rebuilds a chunk–chunk score matrix layer after layer, even when the selected routes change little. We introduce RouteRelay, a router-agnostic method that reuses only route metadata across depth while continuing to compute attention with the current layer's queries, keys, and values. Anchor layers perform full routing. Intermediate layers rescore the previous top-$k$ route and a compact sentinel set of near-miss and randomly probed chunks. A query row is rerouted only when a sentinel challenges its weakest selected chunk. We give a top-$k$ stability condition, a probabilistic bound on missed challengers, and a row-selective GPU execution design. In a reproducible empirical evaluation, RouteRelay retains at least 99.99% route recall while rerouting 25.0%, 55.4%, and 78.2% of rows under low, moderate, and high cross-layer drift, respectively. Across routing scales, RouteRelay retains 100.0% recall while evaluating 38.4–51.6% of full-routing score pairs as the key-chunk count grows from 128 to 1024. Its unfused CPU execution remains slower than dense matrix multiplication, exposing row compaction and ledger updates as the main kernel-engineering targets.

Demographic synthetic survey panels are often validated by matching aggregate answers to published surveys. We test what that certificate establishes across six multiselect batteries from four survey organisations in three countries. The headline analysis is restricted to three instruments whose synthetic cohort and human target share the stated population frame; three other batteries remain sensitivity analyses. The response contract dominates measured fidelity. In the aligned instruments, committed sets leave 66 of 128 model-battery option slots empty in panels of up to 500 respondents, versus 0 of 128 under per-option probability elicitation. Across eight uncapped model-instrument comparisons, probabilities reduce option-marginal MAE by 4.53 to 7.30 points. The capped instrument reverses on two models until the vectors are projected onto its stated maximum. These are measurement effects: human targets are realised check-all responses, whereas the vectors are latent inclusion propensities. Published marginal agreement also fails to discriminate respondent simulation from direct population estimation. On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons. Constraint-aware probability vectors average 5.34 and beat the query on four of nine, so the baseline challenges the validation criterion rather than proving direct estimation uniformly best. On three unpublished demographic cells, neither approach beats reciting the national distribution. Population-marginal agreement is therefore evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.

The independent set polytope, or stable set polytope, of a graph $G$ is the 0/1-polytope defined by the convex hull of the characteristic vectors of all independent sets of $G$. We present a simple algorithm for computing a Hamilton path on the independent set polytope of a given $n$-vertex graph $G$ with amortized delay $\mathcal{O}(n)$. The independent sets are listed such that two consecutive sets differ either in removing a vertex, or adding a vertex and removing its neighbors from the independent set, i.e., the symmetric difference between two consecutive independent sets induces a star in $G$. As applications of this result, we obtain an algorithm to compute a Hamilton path on the matching polytope of an $m$-edge graph $G$ with worst-case delay $\mathcal{O}(m)$, which lists all matchings of $G$ in such a way that the symmetric difference between two consecutive matchings is a path on at most three edges. Furthermore, we obtain an algorithm to compute a Hamilton path on the chain polytope and order polytope of an $n$-element poset $P$ with amortized delay $\mathcal{O}(n)$, which lists all antichains of $P$ or all ideals of $P$, respectively, by star exchanges. Our algorithms are derived from the generic framework proposed by Merino and Mütze (FOCS'23+SICOMP'24) for computing Hamilton paths on arbitrary 0/1-polytopes, which uses a linear optimization procedure as a black box. Our algorithms bypass solving the computationally intractable maximum weight independent set problem by a simple and purely combinatorial greedy rule.

Current paradigms for training language models via reinforcement learning rely heavily on sparse outcome rewards. However, as we pursue tasks that require longer and more complicated trajectories, such strategies result in slow learning. Prior work has attempted to address this problem by rewarding partial progress; however, naive formulations are often biased and converge to suboptimal policies. We show that a simple and unbiased dense reward formulation, which we term progressive point matching, scales exponentially more efficiently to long-horizon tasks by rewarding partial progress on a segment level, both theoretically and empirically via synthetic environments. We then show how progressive point matching can be practically instantiated using a single reference trajectory per task. On extremely hard math reasoning problems, sparse outcome rewards cannot make any progress, whereas segment-level rewards enable improvements at larger test-time token budgets when measured by success rate or pass@k.

Battery cell design must balance energy density, fast charging, and degradation, yet these metrics evolve over different time scales and are costly to optimize jointly. We develop a timescale-aware surrogate-assisted framework that evaluates beginning-of-life volumetric energy density and 10–80% charging time together with state-of-health (SOH) loss over 200 cycles. Physics-based simulations of 1501 cell designs generate 1427 quality-controlled samples across 12 manufacturing-relevant parameters. Objective-specific surrogates support total-order Sobol analysis, which reveals distinct parameter rankings across the three metrics. A cross-objective rank-union strategy then retains variables influential to at least one objective before evolutionary Pareto optimization. Re-evaluation of the optimized candidates using the original physics-based models confirms designs that outperform the reference cell in all three metrics. Among these jointly improving candidates, the objective-wise best solutions, attained by different designs, can reduce SOH loss by 99.31%, increase volumetric energy density by 12.49%, and shorten charging time by 28.73%. The framework makes Pareto exploration across disparate electrochemical timescales computationally tractable, thereby enabling systematic multi-objective optimization of battery cell design.

Ground-penetrating radar (GPR) B-scan image synthesis is important for data augmentation, algorithm validation, and simulation acceleration, yet generating radargrams with both visual realism and physical consistency remains challenging. Existing learning-based generative models often emphasize visual appearance but provide limited control over response geometry. In this paper, we propose PCFlow, a physics-conditioned flow matching framework for fast GPR B-scan image synthesis. The core of PCFlow is a Maxwell-informed dense physical condition field constructed from the parameterized physical model used for electromagnetic simulation, including material properties, target geometry, propagation cues, and response-domain priors. This condition field provides an interpretable interface between physical scene parameters and radar response geometry, and guides conditional flow matching in the VAE latent space toward physically feasible generation paths. We evaluate PCFlow on a gprMax-based buried-pipeline dataset with both in-distribution and out-of-distribution test cases. Experimental results show that PCFlow generates images with more accurate response geometry and high visual fidelity, demonstrating its effectiveness for controllable and physically faithful radar image synthesis.

Learned world models typically assume that observations arrive synchronously, an abstraction inherited from simulators that return a complete state vector at each environment step. Physical sensing instead operates at heterogeneous rates, leaving most observation channels stale at any given instant. Interpolating stale channels introduces measurements that were never observed, while downsampling to the slowest sensor discards valid measurements. A natural alternative is to zero-order-hold the most recent reading and provide the known sampling schedule to the model through two features, staleness and time-to-refresh. We test this prediction using transformer world models across three regimes of increasing causal coupling: open-loop rollouts in continuous-control locomotion, closed-loop model-predictive planning in which each learned model serves as the planner dynamics, and a linear latched-actuator system in which refresh events apply a zero-order-held command to the plant. Our findings show that the effectiveness of time-to-refresh depends on the causal role of the sampling schedule, specifically when refresh events affect the system rather than merely report its state. These results establish when sampling schedules provide useful information for predictive world models operating under asynchronous physical observations.

3D reconstruction typically strives for geometric fidelity or visual plausibility. Radio frequency digital twins (RFDT) are instead judged by whether communication channels behave in them as they do in the real world. RFDTs promise site-specific channel prediction but current practice forces a choice between coarse automated scenes and hand-built, measurement-calibrated models that take weeks to construct per-site. We present KODAMA, an automated pipeline that reconstructs ray tracing-ready RFDTs at city scale from off-the-shelf geospatial data alone: aerial imagery, LiDAR, and photogrammetry yield terrain and watertight building meshes, while exposure-weighted multi-view fusion of street-level imagery recovers façade relief, electromagnetic materials, and clutter—all without site visits or calibration. Across three sites spanning 3.6 to 28 GHz, KODAMA's uncalibrated predictions achieve single-digit RMSE, reducing point-to-point error by up to 5.35 dB over automated baselines and coming within 0.22 dB of a measurement-calibrated, hand-built RFDT.

Ethical evaluation of Large Language Models (LLMs) often characterizes model values as static and monolithic. In contrast, we argue that LLM value expression is better understood as a structured yet dynamic phenomenon. To investigate this, we introduce Conflict-driven Value Probing, a controlled framework that places LLMs in value conflicts and implements four types of interventions that perturb these conflicts to probe LLM value expression. Applying this framework to ten LLMs, we identify three recurring patterns. (1) Expression duality: models shift from broad idealistic orientations in abstract assessment toward more pragmatic priorities in concrete conflicts. (2) Functional steerability: models readily reconfigure their expressed value profiles toward task-defined value objectives. (3) Bounded plasticity: such reconfiguration is not without constraints, i.e. pressure induces a security- and goal-oriented priority shift while negative framing distinguishes protected values from those more amenable to redirection. Together, these findings characterize both the structure and dynamics of LLM value expression: context flexibly reconfigures expressed priorities, yet within behavioral boundaries. This behavioral account provides a foundation for understanding controllability, alignment, and safety in LLMs. Code and data are available at https://github.com/ZeroGen-Lab/CFProbe.

Data-driven constitutive models for path-dependent plasticity are commonly formulated using nonlinear recurrent neural networks, whose sequential state evolution limits parallel training and whose predictions may depend on the discretization of the applied strain path. We introduce a Constitutive State Space (CSS) model that reformulates structured state-space dynamics as an incremental constitutive operator. The strain increment is decomposed into magnitude and direction: the loading direction drives the latent state-space system, while the increment magnitude enters the zero-order-hold discretization of its continuous-time linear recurrence. This mechanics-tailored construction guarantees stationarity under zero increments, strongly reduces sensitivity to strain-path resolution, and retains the parallel-scan structure of S5 for efficient training on long constitutive histories. The CSS and Minimal State Cell (MSC) architectures are compared for four multiaxial path-dependent material models including isotropic J2 plasticity, pressure-sensitive foam plasticity, and combined isotropic-kinematic hardening. CSS matches or exceeds the prediction accuracy of the MSC, including one order of magnitude lower validation losses for the plastically incompressible materials. Importantly, CSS maintains low errors across large changes in strain-path discretization, whereas the MSC error increases substantially when evaluated at coarser resolutions than used for training. CSS trains substantially faster and requires fewer strain-stress pairs to attain comparable or better accuracy. Analysis of the learned state further reveals latent structure consistent with the dimensionality of the underlying physical constitutive models. These results establish mechanics-tailored structured state-space dynamics as a computational framework for efficient and discretization-robust data-driven constitutive modeling.

Supplier selection affects not only operating performance but also the payable network entered by a new obligation. This paper develops the Compensability Capacity Assessment (CCA), an ex ante buyer-supplier measure of expected gross payable relief and its likely timing. CPM provides the bounded structural kernel; concave CCA variants add bilateral invoice capacity. The measure is tested on 749,952 analytical invoices issued during 2012-2023, using frozen nine-month histories and future weekly, monthly, quarterly, semester, and annual windows. Cycle-restricted and path-enabled clearing are independent outcome-generating environments used to validate the measure, not technologies compared by this study. Across seven fully observed quarters in 2022-2023, log-CCA has a median Spearman correlation of 0.638 with future integrated relief; persistent relations carry 93.5% of relief, and the highest-scoring relation captures 92.5% of buyer-specific best relief. Predictability remains positive from week to year, with quarterly recalibration providing the best operating balance between signal, coverage, and timeliness. A timing analysis shows that, across the two validation environments, 89-91% of attributed relief occurs within seven days of invoice issue and 94-96% within thirty days, on average about sixteen days before contractual maturity. Log-CCA correlates 0.564 with thirty-day relief and 0.566 with relief-days. Its highest quartile has a 96.5% median probability of thirty-day compensation, compared with 57.6% in the lowest quartile. Conditional waiting-time prediction is weaker, so CCA should rank timely compensation opportunity rather than forecast an exact payment date. The findings link supplier placement, financial circularity, and working-capital exposure while motivating deployment, causal testing, and quarterly drift monitoring.

The rapid digital transformation of manufacturing, often referred to as Industry 4.0, relies on seamless interoperability between physical and software assets. A central enabler is the Asset Administration Shell (AAS), a standardized digital representation of such assets. Recent advances in large language models (LLMs) enable the generation of AAS submodels from unstructured sources such as product datasheets but raise challenges for quality assurance. In particular, unexpected errors, the lack of ground truth references, and the absence of standardized quality metrics hinder reliable adoption. In this work, we evaluate quality metrics for AI-generated AAS using a perturbation-based evaluation framework. By systematically degrading AAS generation along multiple dimensions, we assess how well different metrics reflect quality changes. Based on a dataset of 200 products from multiple manufacturers, we generate 6,400 AAS instances using GPT-4o-mini, Qwen3, and DeepSeek-R1. Our results show that metrics based on exact matching of property names and similarity-based soft matching of property values, in particular value-based recall and name-based F1 score, provide the most reliable indicators of quality degradation. Furthermore, we quantify the impact of different perturbation types and analyze differences across model families and product segments. These findings support the selection of suitable metrics, the tuning of LLM-based pipelines, and the integration of AI-generated AAS into industrial applications.

Large Language Models (LLMs) are increasingly employed to orchestrate robot behavior through natural-language interfaces, yet no benchmark exists to evaluate their reliability as safety-aware decision makers in human-humanoid collaboration. Unlike deterministic safety systems that enforce binary allow/deny decisions, LLM-based orchestrators exhibit a compliance spectrum ranging from overcompliance (refusing safe actions) to full safety violations. This paper introduces the first safety benchmarking environment for LLM orchestrators in human-humanoid collaboration, built on a Model Context Protocol (MCP)-based architecture with safety invariants grounded in ISO 10218-2:2025 protective measures. The benchmark defines five testable safety invariants, a four-level compliance taxonomy (correct compliance, overcompliance, undercompliance, full violation), and a three-layer evaluation pipeline (text prompting, simulated sensor-actuator loops, and physical validation on a Unitree G1 EDU humanoid). We report Layer-1 results: three cloud backends (Claude Haiku 4.5, GPT-4o-mini, Gemini 2.5 Flash) and a local open-weights baseline (qwen3:8b) across 40 100-turn sessions under full-context and sliding-window budget conditions, while the simulation and physical layers remain ongoing. We find that (1) model family determines the safety floor, as Claude and Gemini remain at or near zero violations while GPT-4o-mini commits up to 13 per session, (2) context management dissociates two failure axes, reducing mean behavioral issues by 42-57% for every cloud backend while nearly doubling GPT-4o-mini's violations (3.8 to 7.2 per session), and (3) proportional compliance, clamping movement speed to the rule-specified maximum rather than refusing, emerges consistently only in Gemini; the preliminary simulation layer reproduces the model ranking and the GPT-4o-mini failure-mode inversion.

Large audio-language models (LALMs) can hallucinate audio objects, answering "yes" to absent sound events, thus undermining reliability in audio question answering. We propose Token-Adaptive Decoding (TAD), a training-free strategy for hallucination mitigation that grounds the initial yes/no decision by contrasting logits under real audio with a matched silent reference. TAD introduces a token-adaptive, confidence-guided gate that is decision-critical at the first decoding step and class-conditional on affirmative tokens, using the audio-silent margin to avoid overcorrection when evidence is weak or already sufficient. Experiments on AudioCaps-Hallucination show that, relative to Audio-Aware Decoding (AAD), a contrastive baseline with fixed contrast strength, TAD improves F1 for Qwen2 by 0.059 to 0.117 across Popular, Adversarial, and Random splits, and for Gemma by 0.025 to 0.064, while on Clotho-AQA it raises F1 from 0.810 to 0.816 on Qwen2 and remains comparable to AAD on Gemma.

Methods for streaming language models are often discussed alongside long-context and memory systems, although they solve different problems. An attention sink can stabilize autoregressive generation over an indefinitely long stream while the model remains unable to use content that has left its recent-token cache. We argue that this distinction should be explicit in system claims and evaluation. We introduce three horizons: the stability horizon, over which predictive behavior remains well behaved; the access horizon, over which past content can still causally affect the output; and the utility horizon, over which a task retains acceptable performance. We show constructively that the stability horizon can be infinite while the access and utility horizons are finite. We then propose ThreeH, an evaluation contract that measures all three horizons under a common state and compute budget. Applying the framework to attention-sink streaming clarifies its strength, constant-memory, stable generation, without treating anchor tokens as semantic memory. The framework exposes roles for cache policies, recurrent state, retrieval, and external memory. Experiments on 128K-token streams, delayed binding recall, and delayed decisions show that attention sinks preserve local modeling but not content beyond the active cache; recurrent and retrieval state extend the semantic horizon.

Modern cybersecurity operations rely on CTI collected from heterogeneous sources, including semi-structured threat representations, IoCs, and narrative technical reports. However, these artifacts are often insufficient in isolation to reconstruct how an attack unfolds, under which conditions each step is feasible, and which traces it leaves behind. In practice, analysts must manually correlate partial evidence scattered across multiple and only partially structured sources, delaying the design of effective prevention, detection, and response actions. To address this gap, we propose an automated pipeline that derives an actionable representation of a cyberattack from heterogeneous CTI sources. The pipeline combines a RAG architecture with a locally deployable SLM, used to consolidate such evidence and infer missing operational details. Starting from a semi-structured threat representation and auxiliary CTI documents, the pipeline produces an enriched Attack Graph that captures a coarse, tactic-aligned progression of the attack and annotates each step with explicit pre-conditions and post-conditions, and an enriched description. This representation supports prevention by exposing execution requirements, detection by highlighting observable traces, and response by clarifying the temporal progression of the attack. Then, due to the lack of validated datasets with ground-truth information on the temporal evolution of real-world attacks, we test the complete pipeline on 10 real-world case studies spanning multiple threat types, including backdoors and staged downloaders delivered via phishing. A manual assessment across 10 real-world case studies provides initial evidence that the generated graphs are consistent with expected attack progressions, indicating that the proposed approach can support analysts by consolidating dispersed CTI evidence into a structured and actionable view of attacks.

Retrieval-augmented generation (RAG) depends on dense retrieval: each document is stored as a learned vector, and queries are answered by nearest-neighbor search. Keeping one full-precision vector per document dominates index cost at corpus scale, so systems replace each vector with a short code of a few bytes (quantization). Standard quantizers such as product quantization (PQ) pick the code that best reconstructs the original vector, but reconstruction is only a proxy for retrieval: at a few bytes per document, a model-aware code trained on the retriever's ranking signal uses the budget better. A single code is even more useful if its short prefixes are each directly searchable, letting a deployment set its efficiency-quality operating point without re-encoding the corpus. But training all prefixes under one objective makes the early bits a compromise across budgets: short codes improve while the full-width code degrades. Binary codes sharpen the conflict, since a gradient step either flips a stored bit or leaves it unchanged. We introduce Matryoshka Hash Representations (MHR), a two-stage procedure that separates full-width training from prefix organization. MHR first learns a longer binary code, then freezes the model and trains zero-initialized residual code adaptors for directly searchable prefixes. Documents are stored at one bit per coordinate, queries keep continuous logits as in PQ, and search runs on FAISS FastScan. Trained on MS MARCO and zero-shot transferred to seven BEIR datasets, one MHR code reaches 0.502 NDCG@10 at 16 bytes and 0.556 at 32 bytes, against 0.404 and 0.524 for the best compact baselines; the gains hold across training seeds, on all 13 public BEIR datasets, and against off-the-shelf binary Matryoshka embeddings with stronger backbones. The same code also helps shortlist candidates for reranking and prune low-storage graph indexes such as LEANN.