Distributed Computing
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Tuesday 18 August
Environmental simulation models support scenario analysis, calibration, and decision-making, but repeated execution can incur significant energy costs. Microservices offer modularity and scalability, yet their low-carbon impact remains unclear because decomposition introduces orchestration, communication, persistence, and idle-service overheads. This paper evaluates four environmental models as containerised microservice workflows, comparing monolithic execution with polling-based and event-driven orchestration. Results show that microservices increase energy consumption for smaller or tightly coupled models, where coordination overhead dominates. For a larger workflow, event-driven orchestration reduces energy use despite longer runtime, while selective downstream re-execution achieves a 41% reduction during repeated parameter exploration.
Machine Learning · Cross-listed from stat.ML
Inference and Uncertainty Quantification for Streaming $r$-PCA
We address two open questions in streaming PCA via Oja's algorithm: sharp operator-norm convergence for general rank under sub-Gaussian data, and distributional inference for the resulting subspace estimator. Existing convergence analyses, even in the rank-one case, either assume bounded data or leave non-vanishing remainder terms that prevent adaptation to a polynomially vanishing tail spectrum, while existing distributional results are confined to the rank-one case. Our convergence theory removes these remainder terms and yields a sharp rate. In the dense-tail spiked covariance regime, this rate matches the minimax rate up to logarithmic factors. More generally, we prove a matching lower bound, up to logarithmic factors, across both dense-tail and sparse-tail regimes under a mild nondegeneracy condition. The analysis yields a linearization of Oja's iterates, which in turn enables a high-dimensional Gaussian approximation for the general-rank subspace estimation error with an explicit limiting covariance. We also establish a row-wise Gaussian approximation over convex sets for the aligned difference, recovering prior rank-one results as special cases. For practical inference, we develop an online multiplier bootstrap algorithm and prove its consistency. Beyond streaming PCA, our techniques contribute to Gaussian approximation and bootstrap inference for nonconvex stochastic approximation.
Read the full abstract
Computers and Society
The Fabricated Front: Generative AI and the Opacity of Workplace Performance
Generative AI (GenAI) has become a fixture of workplace life. Current research asks chiefly what this implies for jobs and outputs, measured in productivity, displacement, or bias. What remains underexamined are the interactional reconfigurations that GenAI produces at work. The emerging concept of effort opacity has begun to fill this gap by highlighting the systematic decoupling of observable output from human engagement. When GenAI makes interactional cues less diagnostic, it weakens the reciprocal exchange that sustains collaborative trust. Extending this account of effort opacity, we examine the interactional mechanics that produce opacity in everyday workplace encounters. Drawing on Erving Goffman's dramaturgical framework and 1,250 interview transcripts from Anthropic's AI Interviewer dataset, we identify five opacity mechanisms through which workplace fronts are reorganized: voice (whose stance the words index), provenance (who can stand behind the artifact), vulnerability (whether the worker is uncertain), attention (whether the worker is engaged), and investment (how much labor the output reflects). We show that professionals defend the identity mechanisms while freely producing opacity around the labor mechanisms, and trace this asymmetry to the output-centered organization of contemporary work, where deliverables already stand in for the labor process that produced them. The governance task, accordingly, is one of involvement management: specifying which forms of human involvement (attention, effort, judgment) must remain inspectable, and to whom. Workplace AI policies built on universal disclosure will systematically misrecognize a social field in which inspectability is already audience-relative.
Read the full abstract
Computer Vision · Cross-listed from eess.IV
Optic Disc Segmentation in Fundus Images: From Classical Image Processing and Deformable Models to Modern AI
Accurate localization and segmentation of the optic disc (OD) are important for retinal image analysis and glaucoma assessment, yet remain challenging due to variations in illumination, pathology, vascular interference, and poorly defined boundaries. This structured methodological review examines the evolution of OD segmentation from classical image-processing and deformable models to contemporary artificial intelligence (AI)-based approaches. A structured literature search and study-selection process was used to identify representative studies spanning major methodological developments. The review first summarizes commonly used fundus-image datasets, then organizes classical methods by principal mechanisms, including intensity and thresholding, histogram and entropy analysis, morphology, geometric and Hough-transform methods, filtering and feature operators, texture- and region-based approaches, and active-contour and level-set models. This paper pays particular attention to the assumptions, strengths, limitations, and complementary roles of these methods in OD localization and boundary delineation. Representative AI approaches are subsequently examined to illustrate the transition from handcrafted features and explicitly defined priors to learned representations, Transformer-based segmentation, boundary- and shape-aware learning, promptable segmentation, and retinal foundation models. Across these methodological generations, several core segmentation principles persist, including region-of-interest localization, multiscale representation, geometric and anatomical constraints, and boundary regularization, although their implementation has shifted from predefined operators to learned modules, losses, prompts, and pretrained representations. The review further identifies boundary ambiguity, anatomical variability, domain shift, and cross-dataset generalization as continuing challenges.
Read the full abstract
Hardware Architecture
MAGMA: Mixture-Model Adaptive Gaussian Model Acceleration
Conventional FPGA-based Gaussian Mixture Model (GMM) accelerators use offline-trained, fixed parameters, limiting their ability to adapt to evolving scene statistics in long-lived edge systems. We present MAGMA, a fully synthesizable fixed-point FPGA architecture that performs concurrent GMM inference and online Expectation-Maximization (EM) parameter adaptation from a streaming RGB pixel input. MAGMA combines a pipelined inference datapath with a background update engine using hardware-friendly transcendental approximations—a range-reduced Chebyshev exponential, a CLZ-based logarithm, and a shift-and-subtract divider—alongside guards against variance collapse and cluster death that stabilize online fixed-point EM. Implemented on an AMD Spartan-7 XC7S50 with $K=4$ clusters, MAGMA runs at 74.49~MHz using 7,779 LUTs, 91 DSPs, and no block RAM, consuming 274~mW. It achieves an $11.8\times$ inference speedup and an $81\times$ M-step speedup over software, while spatial subsampling reduces per-update pixel volume by $40\times$ with minimal impact on EM convergence. Under a synthetic non-stationary scene, MAGMA's online adaptation improves mean pixel accuracy over a static baseline (81.5% vs.\ 79.7%), demonstrating that full online GMM learning is achievable on a commodity edge FPGA.
Read the full abstract
Numerical Analysis
Posterior Convergence without Force Convergence: Resolution-Stable Sampling for Rough Bayesian Inverse Problems
Bayesian targets may converge under model refinement even when the exact sensitivities used by gradient-based samplers do not. We study this probability–sensitivity mismatch and its consequences for Metropolized Hamiltonian proposals. A vanishing-amplitude wiggly-energy model first gives the basic analytic obstruction: the potential perturbation tends to zero while its classical derivative is of order $r_\varepsilon/\varepsilon$. We then show that the same scaling arises naturally in a periodic elliptic inverse problem, where homogenization makes the forward map and Gaussian likelihood converge while differentiation with respect to a microscopic scale parameter retains an $O(1)$ oscillatory contribution. This provides a PDE origin for the single-scale wiggly mechanism. The main construction concerns a more demanding nested Weierstrass hierarchy, interpreted as an analytically tractable prototype for repeated corrector contributions across geometrically separated scales. There all previously resolved scales persist, adjacent classical-force increments grow geometrically like $(ab)^N$, and the limiting rough component may fail to possess a classical derivative. In this self-similar setting the matched Jackson quotient is structurally adapted to the refinement through dilation covariance and exact finite closure. Uniform negative-log-likelihood approximation yields explicit total-variation, Hellinger, and bounded quantity-of-interest bounds. Measurable kick–drift–kick maps remain exact after Metropolis correction, local field convergence propagates to fixed-length proposals and kernels, and the first classical HMC half-kick can have no fixed-step refinement limit. Numerical experiments on scale-structured inverse problems test the resulting resolution-stability mechanism across one- and two-dimensional inverse problems.
Read the full abstract
Robotics
A Task-Agnostic Control Strategy for Dynamic Assistance with Pneumatically Actuated Soft Exosuits
Pneumatic artificial muscles have provided new opportunities to develop upper-extremity soft exosuits for reha- bilitation, augmentation, and assisted daily living. However, the complex dynamics and limited bandwidth of these actuators has made providing responsive assistance based on user intention a longstanding challenge. In this work, we present an inverse-plant control strategy for pneumatically actuated soft exosuits that only relies on kinematic sensing for task-agnostic and dynamic assistance during daily living. We model the human-robot system using a Hammerstein dynamic model, consisting of a Preisach hysteresis model and a linear time-invariant filter, to capture the static and dynamic behavior of the system. We personalize our model to each user using 140 s of data and approximate an inverse to integrate into our control loop. When evaluated on a test rig that emulated a soft assistive exosuit for the wrist, our controller reduced the interaction torque by up to 73% and the activation of key flexor and extensor muscles by up to 47% relative to the condition with no assistance for speeds ranging from 8{\deg}/s to 120{\deg}/s. Overall, this work presents a control strategy that can provide task-agnostic, dynamic assistance with pneumatically actuated soft exosuits without the need for physiological or force sensors to interpret user intention.
Read the full abstract
Computation and Language
Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning
Figurative language is deeply culturally embedded; fluent use requires not just linguistic competence but cultural immersion. We ask whether LLMs can learn this link: does fine-tuning on cultural data improve figurative language understanding, and vice versa? We conduct a systematic study across four models (ALLaM-7B, Fanar-1-9B, Qwen3-8B, Llama-3.1-8B) and six Arabic datasets spanning cultural commonsense, proverbs, and poetry across diverse dialects and regions. Fine-tuning on poetry improves idiom comprehension (+2.33%, p<0.05), a gain our ArabicMMLU control does not reproduce, indicating that it stems from figurative content rather than Arabic language adaptation and pointing to a sensitivity to non-literal meaning that transfers across figurative types. Cultural fine-tuning, by contrast, lowers proverb-interpretation accuracy in both Arabic-centric models. Transfer between the two domains is otherwise indistinguishable from noise, with Arabic models frequently regressing after fine-tuning, suggesting prior saturation of relevant knowledge, while multilingual models show greater adaptation headroom. Error analysis further reveals that fine-tuning reinforces experiential cultural knowledge while destabilizing historically grounded factual knowledge. Our findings suggest that the relationship between culture and figurative language, though conceptually natural, is not straightforwardly captured through fine-tuning alone.
Read the full abstract
Software Engineering
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
Agentic AI systems take consequential actions governed by more than one pre-action control at once: authority, resource, and evidence gates that can admit, degrade, or remediate an action before it executes. This paper's central object is remediation-induced control coupling: a remediation applied by one control can change the action, evidence, or context another control evaluates, invalidating that control's earlier judgment. We formalize this coupling and give a remediate-and-regate protocol that restores per-action soundness in the current bounded, idempotent setting under its stated assumptions. We further show that the two implemented remediation operators (evidence substitution and resource-budget downroute) do not commute – a finite-model checker finds concrete counterexample instances – making remediation order part of the control-plane semantics rather than an implementation detail. A governed evidence buffer that trusts its own most recent admitted write is a further instance of the same problem at the level of state – current admissibility does not imply future reference trustworthiness – and is vulnerable to poisoning from declared-uncovered defect classes; two mitigations reduce, not eliminate, that exposure. Supporting results establish the exact condition under which positive-weight linear aggregation of gate outcomes can compensate a member veto, a unified cross-control Evidence Set, and that composition manufactures no new detection coverage, reported honestly. Empirically, on a deterministic open-data artifact composing three published engines unmodified, CH1-CH5 meet their registered decision rules across all 30 pre-registered seeds; CH6 does so under W1 but not under the smaller W2 workflow, reported as such. This is a mechanism demonstration on open payload data with a synthetic metadata layer, not a claim about production prevalence.
Read the full abstract
Cryptography and Security
0xPass: A Secure Protocol for Universal Cross-Chain Accounts
Universal accounts allow users to manage assets and execute operations across heterogeneous blockchain ecosystems through a single interface, but they introduce security and trust challenges involving authentication, authorization, transaction signing, key custody, recovery, and decentralization. This paper presents 0xPass, a modular protocol architecture for universal cross-chain accounts. 0xPass separates request orchestration, transaction solving, and transaction signing into interoperable layers. User-approved requests are bound to authenticated identities and authorized across layers, while threshold signatures prevent any single transaction node from holding a complete signing key. The design also supports constrained authorization delegation, transaction policies, account recovery, distributed key management, and auditable communication among independently operated sub-networks. We describe a staged deployment path from a centrally operated service to a permissioned network and ultimately to a permissionless network with third-party modules, collateral-backed onboarding, and rotating key-management committees. The resulting architecture provides a practical framework for extending cross-chain account functionality while progressively reducing centralized trust and preserving user control over transaction authorization.
Read the full abstract
Computers and Society
Capability-Based Planning for AI Crisis Preparedness
Capability-based planning drives preparedness in defense and homeland security, but has yet to be applied seriously to AI. Government AI preparations follow a predict-then-act paradigm: rank risks by likelihood and impact, then prepare for the highest expected harm. AI resists prediction: expert timelines disagree by orders of magnitude, and official reviews concede that likelihood-based risk assessment fails for exactly this class of risk. Drawing on principles of decision making under deep uncertainty, we propose a methodological framework in three parts: a scenario library sampled systematically across declared axes; a rating procedure that assesses each government capability against each scenario on coarse, gated criteria; and a prioritization step that maps the resulting matrix onto decision rules a government might adopt. Through a pilot across the four most severe AI-enabled threat classes, we illustrate the kind of insight the instrument yields and provide a proof of concept for capability-based planning as a practical tool for AI crisis preparedness.
Read the full abstract
Systems and Control
Model Predictive Supervisory Control for Hierarchical and Distributed UAS Traffic Management
This work proposes a hierarchical Model Predictive Supervisory Control (MPSC) framework for multi-agent systems with shared resources. MPSC integrates receding-horizon cost-optimal control with Supervisory control theory (SCT) based supervision that enforces safety, nonblockingness, and resource exclusivity. Scalability arises from hierarchical and scalable supervisor and automaton templates, enabling distributed execution without monolithic synthesis. Using this framework, this work develops an urban Unmanned aircraft system Traffic Management (UTM) model. The model supports pickup-and-delivery missions under time-varying demand efficiently.
Read the full abstract
Information Retrieval
AI in Search Reduces Publisher Referrals Without Improving User Experience: Experimental Evidence
The integration of generative AI into web search delivers synthesized answers to user queries, changing how people navigate and assess information, while raising concerns about the downstream impacts on publishers who supply the underlying content. We conduct a preregistered field experiment (N=1,100) on Google Search, the dominant online search platform, to estimate the causal effects of AI Overviews and AI Mode on user behavior, perceptions, and publisher traffic. We show that removing AI Overviews and AI Mode increases click-through rates to publishers, while an AI Mode-only experience reduces click-through rates and erodes user experience and trust in information found on Google. These findings show that integrating generative AI into web search reshapes online attention, with economic consequences for the online publishers that sustain both search platforms and the overall information ecosystem.
Read the full abstract
Cryptography and Security
Task-Conditioned Least-Privilege Learning for Executable Terminal and MCP Agents
Tool-using large language-model agents can complete a task while exercising authority that the user did not grant or the task does not need, causing excess-authority errors. Traditional permission gating systems alone for validating agent environments are insufficient. We study whether post-training can teach a 4B-parameter model to choose task-conditioned authority in executable terminal and Model Context Protocol (MCP) environments to complement those measures. We propose a framework where each action is audited before execution and again from observed effects along six dimensions of risk. This auditing is conducted using deterministic verifiers that score completion, evidence, exact state, prohibited attempts, and safe success. In conjunction with predefined task-specific sufficient-authority envelopes, we determine task-specific excess privilege values for trajectories, which are then optimized for in post-training. We find that after training using this framework on Qwen3.5-4B over 1,500 tasks, the selected seed reaches 98.48% safe success across 2,896 evaluation episodes spanning all 500 held-out tasks, compared with 64.36% for the base policy, and reduces excess-authority error events from 4.56% to 0.79%. Furthermore, external tests show capability retention and prompt-directed improvement. A 400 task continuation study also found evidence of generalization, reducing excess-authority events by 6.99 percentage points while maintaining previous capabilities. We conclude learned restraint through least-privilege aware post-training is therefore useful as an additional control layer for tool-using agents in executable terminal and MCP environments, but it does not replace permission gates and sandboxing.
Read the full abstract
Cryptography and Security
XNET: Intelligent Dynamic Sampling for High-Speed Network Security Monitoring
Growing network speeds, with 100GbE line rates becoming common in modern enterprise networks, pose challenges to operators and security applications, as they struggle to scale their operational efficiency accordingly, without relying on costly hardware, excessive sampling, or complex distributed deployments. Unintentional loss due to stochastic packet sampling often produces low-quality traffic, further risking missed detection of critical security incidents, particularly those hidden in typically low-rate traffic, such as APT/malware command-and-control communications. In this paper, we introduce XNET, a system that monitors traffic at line rate using commodity hardware and applies dynamic sampling to amplify the visibility of high security value traffic. XNET leverages Linux's XDP technology to process packets efficiently, classify them based on their security value, and sample them as per configured policies. The outcome is a reduced packet stream in which the security-relevant portion of the traffic is amplified at the expense of less interesting traffic segments. XNET is a highly flexible, scalable and dynamic system that can be adapted based on a network's needs. We deployed XNET in a large real-world network using only commodity hardware, where our results show that XNET can achieve up to 84% traffic reduction with no packet loss while increasing the visibility of otherwise negligible traffic fivefold. With controlled stress tests, we further demonstrate XNET's scalability up to 100Gbps. Additionally, we show that XNET sampling led to a detection rate of 99.6% in an IDS application.
Read the full abstract
Artificial Intelligence · Cross-listed from physics.chem-ph
Coupled-cluster molecular properties across the main group that extrapolate beyond training size
Coupled-cluster theory defines the accuracy standard for molecular electronic-structure properties but scales too steeply for routine application, whereas density-functional theory is affordable yet systematically biased. We resolve this trade-off with a single equivariant network, HARP (Hamiltonian Read-out for Properties), that predicts an effective one-electron Hamiltonian from one inexpensive B3LYP/def2-SVP calculation and derives a broad suite of properties from it (energy, optical gap, dipole, quadrupole, polarizability, Mulliken atomic charges, and Mayer bond orders) at coupled-cluster accuracy across nine main-group elements, including the under-served phosphorus, sulfur, and chlorine chemistries. The model is trained on a new in-house dataset of multi-property labels computed at the CCSD(T) level for all nine elements. On a held-out test set, it reduces the error of every property by a factor of 3.8 to 270 relative to semi-local, hybrid, and double-hybrid DFT (referenced to composite CCSD(T)/cc-pVTZ), while adding only ~0.1 s wall time per molecule, delivering coupled-cluster-quality predictions at the cost of a single DFT calculation. Critically, deriving every property from a predicted Hamiltonian rather than pooling per-atom features builds the correct size-scaling into the model architecture: on pi-conjugated oligothiophenes it matches finite-field CCSD polarizability to ~1% and the EOM-CCSD optical gap to ~3% at the largest sizes where those references remain affordable (44 and 37 atoms, where a single CCSD field point already costs ~500x the model's entire inference) and extrapolates the corrected trends to 58-atom chains, a regime where pooling-based architectures fail by construction. Accurate extrapolation is therefore set by the model's inductive bias rather than by the training data.
Read the full abstract
Neural and Evolutionary Computing
Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring
Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deployment complexity. We demonstrate autoencoder-based acoustic anomaly detection on an Intel Loihi 2 neuromorphic processor under clean and noisy conditions. Log-mel features are computed off chip; normalization, autoencoder inference, L1 reconstruction scoring, and thresholding run on chip. In a clean, microphone-position-invariant ToyADMOS ToyCar benchmark, the on-chip model achieves 0.9959 AUC and 0.9785 standardized pAUC at maximum false-positive rate 0.1. In the DCASE 2026 Task 2 ToyCar noisy benchmark, the model achieves source AUC 0.7990, target AUC 0.6466, and pAUC 0.6426, exceeding reported baseline metrics. Power profiling on a 16-chip Loihi 2 VPX system shows real-time throughput with 0.0406$\unicode{x2013}$0.0426 mJ dynamic energy per sample, two orders of magnitude lower than both a CPU and GPU. These results support neuromorphic acoustic anomaly detection as a practical candidate for low-power, persistent machine monitoring.
Read the full abstract
Computer Vision
From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model
Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference. Although significant efforts are devoted to adapting VLMs at test time, they rely heavily on noisy pseudo-labels predicted directly from raw embedding similarities during inference, which are unreliable under distribution shift and mislead the adaptation. To avoid noise amplification, existing works craft coarse-grained surrogate objectives during adaptation, which fail to explicitly model sample-level relationships across different modalities, creating objective mismatch with inference, thus leading to marginal performance improvement. In this work, we aim to bridge the detached objectives of inference and adaptation for VLMs, and propose a principled VLM TTA method called \algname. For VLM inference, we formulate the zero-shot image classification task as a cross-modal alignment problem encoded via a Wasserstein OT formulation, providing robust pseudo-labels at the sample-level to effectively adapt VLMs. For VLM adaptation, we adopt a soft-label InfoNCE loss to adapt VLMs based on the OT-induced pseudo-labels, leveraging fine-grained supervisions to explicitly model relationships of individual image-text pairs via contrastive learning, which empowers accurate inference at the same granularity. Moreover, we theoretically reveal that the InfoNCE loss can be neatly reformulated as a Wasserstein OT formulation, thereby unifying the objectives of the inference and adaptation of VLMs to achieve their mutual benefits. Extensive experiments demonstrate the effectiveness and efficiency of our methods, outperforming the best-performing methods by up to 7% with state-of-the-art efficiency.
Read the full abstract
Artificial Intelligence
Measuring the Partial-Credit Gap: A Strict Benchmark on Vietnam's 2025 Convex Marking Scheme
When evaluating language models on human exams, benchmarks typically score each response as right or wrong and report the overall accuracy. This approach assumes that partial knowledge is worth proportional credit, an assumption that fails when an examination uses a non-additive grading scheme. The 2025 reform of Vietnam's National High School Graduation Examination demonstrates the cost of this substitution. In Part II of the exam, candidates evaluate four true/false statements per question. The grading is convex: the number of correct statements earns 0, 0.10, 0.25, 0.50, or 1.00 points. Identifying three statements correctly pays 0.50 points, not the 0.75 points that standard accuracy metrics would award. Because Part II accounts for 4.00 of the exam's 10.00 points, reporting accuracy inflates the score by rewarding partial knowledge that the state explicitly penalizes. We introduce THPT-Ladder, a benchmark of 632 items from 21 official exams across 11 subjects, graded exactly as the ministry grades its students. The ministry publishes the marks of over a million candidates, allowing us to place models directly into the human cohort. Across eight models, the official rubric pays 0.020 to 0.159 points less per Part II question than proportional credit. This shortfall changes a model's apparent competence. For Qwen3.5-27B on the 2025 History exam, a 0.042-point shortfall drops its standing from the 90th to the 77th percentile among 481,293 candidates. A model's accuracy does not predict this penalty. At Claude Sonnet 5's accuracy level, different distributions of errors yield scores varying from 0.869 to 0.932 points per question. Official marks depend on how correct statements are grouped, meaning standard benchmarks report a competence the institution would not certify.
Read the full abstract
Machine Learning
When Does Dynamic Ensembling Pay Off? Diagnosing Regionwise Gains in Regression under Distribution Shift
Whether input-dependent ("dynamic") combination of a regression model pool beats the best static blend depends on the shift and is rarely known before deployment. Can a small labeled target-domain probe tell us when reallocating trust across regions of the input space will pay off? We answer this with $\widehat{D}_{\mathrm{CF5}}$, which estimates from the probe the cross-fitted gain of the regionwise convex combination over the best static convex blend: the realizable value of deciding, region by region, whom to trust. Across a frozen suite of 12 dataset-shift pairs (spatial, temporal, domain, feature-cluster), $\widehat{D}_{\mathrm{CF5}}$ predicts realized regionwise test gains with dataset-level Spearman $+0.98$ (95% CI $[+0.83, +1.00]$; $p=5\times10^{-5}$), including two cases overturning preregistered expectations. The relationship holds in a 16-pair sensitivity analysis (Spearman $+0.83$), whereas alternative probe diagnostics reach at most $+0.66$. This contrast isolates regional trust reallocation: correlation is $+0.98$ for regionwise-convex gain, but $+0.01$ for smooth covariate-dependent stacking after affine correction. A controlled generator shows dynamic gains arise from the interaction of shift heterogeneity and local competence, increase with shift severity, and become realizable between 128 and 256 probe labels in the tested grid. The Probe-Validated Ensemble Selector chooses among a static affine stacker and dynamic realizers, deploying a candidate only when a held-out lower confidence bound clears the static-convex floor. In a preregistered prospective batch, it matched or improved the floor in all 12 runs; two deployments reduced test risk by 11% and 16%, while the gate rejected a candidate whose un-gated deployment incurred $>30\times$ the static loss. We release OpenRegShift, a reproducible evaluation harness for regression ensembles under distribution shift.
Read the full abstract
Software Engineering
Engine-Transfer-Bench: An Evidence-Based Benchmark for Document Compilation Engine Selection
There is no shared framework for selecting among document compilation engines (pdfLaTeX, XeLaTeX, LuaLaTeX, Tectonic, Typst, and pandoc PDF backends). We present Engine-Transfer-Bench (ETB): 1,784 open documents, four tasks covering reliability, latency, text consistency, and failures, a pinned harness, and host-tagged multi-OS results. On GitHub Actions (N=4,211 compiles per host across macOS, Ubuntu, and Windows), Tectonic success is stable within 0.9 percentage points (96.3-97.2%), whereas classic TeX Live-style engines vary by 12-20 percentage points according to distribution policy (Ubuntu apt, MiKTeX auto-install, or macOS BasicTeX). On 702 portable LaTeX documents, the tested engines succeed at 100%, making latency the primary selection factor; failures concentrate in 107 engine-specific templates. Within ETB, failures are architectural, involving fonts, layout, and assets, rather than missing packages on a provisioned host. A 50-pair validation of the S_pdf text-consistency metric achieves 94% precision for real content divergence. We release ETB, ETB-Porta, a recommender and portability gate, and a public cross-OS harness as shared infrastructure.
Read the full abstract
Programming Languages
Compiling WebAssembly Concolic Execution with Staging, Continuations, and Snapshots (Extended Version)
Concolic execution is a variant of symbolic execution that runs a program simultaneously with concrete and symbolic inputs. It records the symbolic constraints encountered along a concrete execution path, then solves those constraints to generate inputs that explore new paths. Existing concolic engines generally follow one of two implementation strategies: Interpreter-based systems are comparatively simple to build but incur substantial interpretation overhead, while instrumentation-based systems avoid this overhead but typically re-execute the program from the beginning for each new input. In this paper, we develop a new approach that achieves the best of both worlds. Starting from the concrete semantics of the target language, we first develop a definitional concolic interpreter and stage it to compile away interpretation overhead while retaining the simplicity of an interpretation-based implementation. By expressing the staged interpreter in continuation-passing style, we can capture execution snapshots at branch points and resume from them when exploring alternative paths, avoiding repeated execution from the program entry. Because snapshot-reuse can itself incur overhead, we further develop a heuristic that favors snapshot-reuse only when it is expected to be beneficial. We instantiate this approach for WebAssembly and implement it in a new concolic-execution compiler GenWasym. Across 184 benchmarks, GenWasym with staging alone achieves a $29.4\times$ average speedup over the interpreter-based WASP; heuristic snapshot-reuse further increases the speedup to $44.9\times$.
Read the full abstract
Artificial Intelligence
Governance Records as Supervision: Verifier-Selected Self-Training for Structured Workflow Repair
Machine-verifiable workflows produce governance records linking a task contract, model attempt, verifier decision, accepted output, and target origin. We test whether verifier-admitted outputs can supervise a bounded model by consolidating occasional or expensive capability into reliable one-shot execution. On fresh, structure-disjoint PlanBench replanning cases, Qwen3-14B thinking produced 24 plans admitted by independently authored VAL. They trained the same checkpoint for non-thinking execution, without oracle targets or a stronger teacher. VAL acceptance rose from 1/80 to 57/80. A prospective replication held targets, model revision, recipe, and evaluation corpus fixed across eight LoRA seeds and three inference realizations per seed. Every seed produced a clear lift: adapters reached 45/80 to 70/80 against 1/80 for every matched base report; the exact seed-level sign-flip test gave p=0.0078125. Target-selection performance was less stable. An initial matched seed gave 102/160 accepted plans after VAL selection versus 69/160 after blinded model self-selection. Across eight prospective seeds, the contrast was seed-dependent, included one clear reverse seed, and did not replicate (p=0.3672). VAL also had a positive descriptive aggregate over schema-only selection but failed its preregistered seed-level reliability gate (p=0.0703). The verifier remains the admission authority; no reliable downstream capability advantage of semantic selection is established. A complementary Phi arm supports stronger-teacher distillation. Earlier synthetic studies bound teachability, cumulative learning, transfer, and stopping. The evidence supports robust consolidation of one fixed, machine-checkable capability, not arbitrary planning, enterprise validity, or unrestricted self-improvement.
Read the full abstract
Information Retrieval
Multimedia Asset Personalization via Multimodal Embeddings at Netflix
Personalized promotional assets, namely artwork images and video preview clips, are critical to content discovery on Netflix. Traditional models for asset selection rely on ID-based interaction history, leaving them blind to asset content and unable to serve newly launched titles and assets. We describe how multimodal embeddings reshaped production systems at Netflix and report transferable lessons for practitioners adopting foundation-model embeddings into recommender systems. First, pretrained image embeddings unlock cross-title, cross-canvas knowledge transfer. Augmenting a two-tower model with CLIP image embeddings lets a single model serve all five Netflix artwork canvas types, replacing five separately trained per-canvas models and substantially improving cold-start performance. A lightweight extension reuses CLIP's joint text-image space to make artwork personalization query-aware in search. Second, multimodality decisively beats any single modality for video preview personalization. We describe MediaFM, our in-house tri-modal foundation model trained on a large-scale corpus of shots from the Netflix show catalog, fusing visual (SeqCLIP), audio (wav2vec 2.0), and timed-text signals; adopted for video preview personalization, it outperforms strong visual-only baselines both offline and in online A/B tests. Third, a simple offline proxy task whose performance correlates with online outcomes can accelerate the experimentation and productization cycle. Predicting the popularity-based winner from embeddings alone ranks embedding models and versions, pruning the choice space before any end-to-end integration or A/B test; it now gates every new MediaFM checkpoint. We also share the production engineering decisions (shared embedding infrastructure, low-latency serving, cheap screening) that made these deployments viable, along with the design tradeoffs and failure modes we encountered.
Read the full abstract
Machine Learning
SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement Learning
Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identify a novel source of plasticity loss due to the growing anisotropy of weight matrices' singular values during training, and analyze this phenomenon both empirically and theoretically. To mitigate this issue, we introduce SingularClip, a procedure that periodically clips the singular values of all weight matrices. We show that SingularClip performs strongly against baselines across a range of tasks in both continual supervised learning and deep reinforcement learning.
Read the full abstract
Systems and Control
A Benchmark Graph Dataset for Transient Stability Assessment of the IEEE 9-Bus System: 20,000 Scenarios with Full Generator Trajectories
Transient stability assessment determines whether a power system retains synchronism after a large disturbance. Machine-learning surrogates can accelerate it, but progress is limited by the lack of open datasets that combine dynamic ground truth, network graph structure, and machine parameters. We release a benchmark of 20,000 three-phase-to-ground fault scenarios on the IEEE 9-bus system. Each scenario couples an AC power-flow operating point with a detailed electromagnetic-transient simulation of the post-fault response. Every record provides the network as an attributed graph (nine buses, eighteen directed branches, ten node and twelve edge features), the full rotor-angle and speed trajectories of the three generators, the static machine constants, the fault description, and a center-of-inertia binary stability label. Wide load and generation scalings across eighteen fault locations yield a near-balanced distribution (48.96% stable, 51.04% unstable). Generation is deterministic and fully reproducible through fixed seeds and public code. The dataset is distributed on IEEE DataPort under a persistent DOI and supports stability classification, trajectory prediction, margin and critical-clearing-time estimation, and the comparison of topology-aware, physics-based, and hybrid learning methods.
Read the full abstract
Computer Vision
Reproducible Multimodal Affordance Prediction
Affordance prediction is the identification of potential actions an agent can perform on a target object from multimodal inputs. Affordance prediction methods are difficult to evaluate and compare due to heterogeneous problem formulations, inconsistent dataset annotations, incomplete reporting of experimental protocols, and limited information about deployment conditions. These limitations challenge fair benchmarking and performance comparison. To promote transparency, we propose the Affordance Sheet, a documentation detailing task formulation with its input modalities, model architectures and training information, datasets, and experimental protocols. Affordance Sheets enable reproducible benchmarking and reliable evaluation of affordance models for real-world scenarios, including generalisation to novel conditions and human safety.
Read the full abstract
Computer Vision
A Configurable Privacy-Preserving MRI Processing Workflow Using Deep Learning-Based Brain Extraction and Adaptive Anatomical Preservation
Structural Magnetic Resonance Imaging (MRI) is widely used in neuroimaging research and clinical practice, but structural MRI volumes may retain facial and cranial anatomical information that raises privacy concerns. Existing deep learning-based brain extraction methods generally produce a single fixed output, limiting flexibility when different applications require different balances between privacy and anatomical preservation. This paper presents a configurable privacy-preserving MRI processing workflow that extends deep learning-based brain extraction through adaptive anatomical preservation, interactive preservation selection, and integrated quality control. The workflow employs SynthStrip for automated brain extraction, followed by morphological mask expansion to generate configurable shell-based preservation levels. An Interactive Preservation Framework enables users to compare preservation configurations and select an appropriate output, while an integrated Quality Control Framework provides multi-plane visualisation and brain-mask overlay verification. The workflow was implemented in Python using open-source neuroimaging libraries within the Renku reproducible research environment and evaluated using structural T1-weighted MRI data from the publicly available IXI dataset. Experimental results demonstrate anatomically plausible brain extraction and configurable preservation outputs, supported by systematic visual verification. The principal contribution is a modular and reproducible MRI preprocessing framework that enhances deep learning-based brain extraction with configurable anatomical preservation, interactive user-guided processing, and integrated quality control. The workflow provides a practical foundation for privacy-oriented neuroimaging research and collaborative medical image analysis.
Read the full abstract
Systems and Control
Real-Time Design of Public Transport Lines: Reconciling Adaptivity and Efficiency
Demand-responsive transport (DRT) is typically routed by solving Dynamic Vehicle Routing Problems (DVRPs), where individual vehicle trajectories are adjusted on incoming requests. This limits demand consolidation and thus efficiency. On the other hand, Conventional Public Transport (CPT) bus systems are based on a network of lines and users find their routes on it, which provides high demand consolidation. However, such a network is built offline and cannot adapt to the demand. We propose a public transport management strategy that reconciles efficiency and adaptivity by dynamically designing a structured network of lines via a receding-horizon optimization approach. Using real-world trip requests, we show that we nearly double the fraction of served requests compared to DVRP-based routing, and we serve more requests than CPT with lower user trip times.
Read the full abstract
Computation and Language
Artifact-centered Claim-aware Observability for Autonomous Scientific Agents
Autonomous scientific agents now increasingly propose ideas, write code, run experiments, analyze results, and even draft papers. Observe and audit those agents are necessary but logging every model call is not enough, scientists also need to inspect the artifacts and claims that the systems produced and their relations. This is driven by the fact that failures in scientific agent systems are often distributed across several objects. A manuscript claim may cite the wrong evidence, a search process may select a degenerate candidate, a laboratory novelty claim may depend on an unstated rule, or a multi-agent plan may change without a visible trigger. Existing tracing, experiment tracking, and archival provenance tools are valuable, but their native objects do not make these scientific audit relations first-class. We argue that autonomous scientific systems should emit portable, claim-aware artifact lineage as a minimum audit layer. We propose a compact observability profile organized around individuals, operators, fitness records, lineage, archives, runs, streams, and steering commands. In this profile, scientific claims are ordinary individuals with explicit evidence bindings and verification records. The profile is intended as a semantic layer that complements current telemetry and provenance standards. Execution details can remain in OpenTelemetry. Final packages can export to PROV-O or RO-Crate standards.