arXiv:2607.11646v1 Announce Type: new
Abstract: Intelligent Transportation Systems deployed on highways predominantly rely on conventional RGB cameras for traffic perception and vehicle tracking. However, highway environments present unique challenges: the absence of artificial lighting infrastructure, combined with high vehicle velocities, results in severely degraded perception performance under low-light conditions. Specifically, nighttime scenarios suffer from motion blur, insufficient exposure, and poor signal-to-noise ratios, which catastrophically impair the reliability of RGB-based sensing systems. To address these limitations, we propose a novel Joint Event-RGB Adaptive Tracking (JEAT) framework. Unlike existing multi-sensor trackers constrained by rigid, hard-coded prioritization, JEAT merges asynchronous event streams and RGB frames into a unified joint data association optimization. By employing an Adaptive Extended Kalman Filter to continuously estimate measurement noise via NIS statistics, the framework dynamically weights and fuses both modalities, optimally harnessing event streams during dark or high-speed motion while leveraging RGB frames under bright or static conditions. Furthermore, given the absence of publicly available datasets tailored for event-based highway perception with diverse environmental conditions, we present SEHN, a large-scale synthetic dataset generated using the CARLA simulator. Our dataset encompasses diverse environmental conditions (daytime, nighttime, nighttime with out artificial lighting) and varying traffic densities, providing synchronized RGB imagery and event streams to facilitate multi-modal fusion research. Our code and datasets will be available at https://github.com/haidongwang96/SEHN.
Science Journals
arXiv:2607.11657v1 Announce Type: new
Abstract: We propose an algorithm and its implementation for trajectory planning and certification for 3-DOF robot manipulators. The method uses Real Quantifier Elimination (QE) based on Comprehensive Gr\"obner Systems (CGS), also known as the CGS-QE method. The main advantage of the proposed method is its efficiency in trajectory planning and solution certification. This efficiency comes from the effective use of the CGS. First, for trajectory planning, we solve the inverse kinematics problem at each point along the trajectory via Gr\"obner basis computation. This usually requires recalculating the Gr\"obner basis at every point, which is time-consuming. We avoid this by computing the CGS for a parametric system. Here, the end-effector coordinates are parameters. This approach streamlines the algorithm. Second, for solution certification, the CGS-QE method certifies that an inverse kinematics solution exists at any point along the end-effector's trajectory. Our method also certifies solutions for trajectories composed of line segments and cubic natural splines. The algorithm is implemented within the computer algebra system Risa/Asir.
arXiv:2607.11530v1 Announce Type: new
Abstract: Decoding continuous three-dimensional (3D) motor imagery (MI) using non-invasive electroencephalography (EEG)-based brain--computer interfaces (BCIs) remains challenging due to signal variability and residual decoding errors. Deep learning architectures such as convolutional neural network--long short-term memory (CNN--LSTM) models can capture spatial and temporal dynamics for continuous kinematic decoding; however, systematic residual errors persist in predicted trajectories. We propose a two-stage decoding framework that applies reinforcement learning (RL) to perform residual kinematic correction on the outputs of a CNN--LSTM decoder (CNN--LSTM--RL). The RL agent is trained offline without direct EEG input and instead operates on predicted kinematic trajectories to optimize movement accuracy relative to target trajectories. Decoding performance was quantified using Pearson correlation coefficients ($r$) and Root Mean Square Errors (RMSE) along the $x, y$, and $z$ axes. Compared to CNN--LSTM applied alone, CNN--LSTM--RL improved the mean correlation from $0.5076$ to $0.7181$ ($p = 0.0005$) in 2D and from $0.6420$ to $0.7780$ ($p = 0.0059$) in VR, with relative gains of $41.5\%$ and $21.2\%$, respectively. Correspondingly, RMSE was reduced from $0.0890$ to $0.0532$ (2D, $p < 0.0001$) and from $0.0714$ to $0.0441$ (VR, $p < 0.0001$), representing relative reductions of $40.2\%$ and $38.2\%$. These findings demonstrate that this scalable framework enhances 3D BCI MI decoding by correcting kinematic errors via offline residual RL without extra neural data, advancing neurorehabilitation, prosthetics, and virtual interaction.
arXiv:2607.11665v1 Announce Type: new
Abstract: Runtime assertions are a promising mechanism for testing and debugging quantum programs. But unlike the classical world, checking a quantum program that contains multiple assertions often requires using additional space or running the program additional times. For example, on current quantum hardware where mid-circuit measurement is restricted or costly, an assertion's pass/fail outcome cannot be revealed immediately. Instead, it is routed into an ancilla qubit during execution and read out by a terminal measurement. For a program with $n$ assertions, a naive strategy uses $n$ ancillas to learn all $n$ outcomes, while an alternative uses one ancilla but repeats program execution over $n$ rounds, checking one assertion per round. Both satisfy $S \cdot T = O(n)$, where $S$ is the number of ancillas and $T$ the number of executions: a fundamental time-space trade-off.
Can one do asymptotically better? We reveal that the answer depends sharply on the information to be learned. Reporting the outcomes of all assertions requires linear complexity, but two partial-information tasks of detecting whether any assertion fails, and of identifying the first failing assertion, require only logarithmic complexity -- an asymptotic improvement. Moreover, the checking strategies for these tasks can trade time for space in useful ways. In this work, we formalize the complexity of checking multiple assertions in a quantum program. Using this definition, we establish its landscape of asymptotic lower bounds and constructive upper bounds. We confirm via a case study on Grover's algorithm that the resource costs of constructed strategies match theoretical predictions, illustrating the practical design space for quantum programmers.
arXiv:2607.04597v2 Announce Type: replace
Abstract: In this paper, we study the universal approximation property of residual neural networks, and obtain some new results. For input and output dimensions $d_x$ and $d_y$, and LeakyReLU, ReLU, ReLU-like activation functions, the upper and lower bounds of the minimum block width are established. To achieve $L^p$ approximation $(1\leq p <+\infty)$ on any compact domain, we show that the exact minimum block width is $\max\{d_x,d_y\}$ when each residual branch has inner width 1. Furthermore, we show that residual neural networks with block width $\min\{d_x+d_y, \max\{2d_x+1,d_y\}\}$ can achieve uniform approximation on any compact domain under the constraint that each residual branch has inner width 1. Besides, for any activation function family, we prove that there exist functions that cannot be approximated by residual neural networks with block width less than $\max\{d_x, d_y\}$, both in the $L^p$ sense and the uniform sense, regardless of inner width.
arXiv:2606.07796v2 Announce Type: replace
Abstract: The Internet of Vehicles (IoV) creates a partially observable and adversarial V2X communication environment in which malicious vehicles may evade defensive mechanisms. Existing IoV intrusion-detection methods provide limited support for sequential mitigation under adaptive attacker behavior. This paper formulates IoV cyber defense as a partially observable sequential decision problem and proposes Quantum Belief-Integrated Reinforcement Defense (Q-BIRD), an amplitude-belief reinforcement learning framework. Q-BIRD represents uncertainty over hidden attacker intent through a normalized complex-valued belief state and converts amplitudes into intent probabilities. The resulting belief features are used by a Proximal Policy Optimization defender to select cost-aware mitigation actions. Experiments are conducted in a SUMO-OMNeT++ and Veins V2X co-simulation environment. Q-BIRD reduces mean cumulative damage from 36.0 +- 5.5 to 28.0 +- 3.0 and damage variance from 12.0 +- 2.8 to 6.0 +- 1.5 compared with PPO using classical Bayesian belief. The attack success rate decreases to 0.05 +- 0.02, while survival probability increases to 0.96 +- 0.02. Communication-level results show that Q-BIRD maintains a packet delivery ratio of 0.94 +- 0.02, latency of 45 +- 6 ms, throughput of 3.60 +- 0.15 Mbps, and service availability of 0.95 +- 0.02. Explainability analysis using SHAP, LIME, and Grad-CAM suggests that belief-related features contribute strongly to mitigation decisions. These results indicate that amplitude-based belief modeling can improve both cyber-defense stability and V2X communication reliability under partial observability.
arXiv:2607.04910v2 Announce Type: replace
Abstract: In our earlier work, we modeled the stochastic initiation of HIV rebound by treating latent-cell reactivation as a Poisson-driven process during antiretroviral-therapy (ART) washout, immune modulation, and therapeutic perturbation~\cite{Taye2025CM}. That framework characterized activation survival, cumulative hazards, waiting-time laws, and expected viral-load trajectories. However, the endpoint observed in analytical treatment interruption (ATI) studies is not the hidden time of first successful reactivation. It is the first time at which plasma virus exceeds an assay-defined detection threshold. Here we reformulate post-treatment rebound as a stochastic first-passage problem, with $T_{\rm reb}=\inf\{t\ge t_w:V(t)\ge V_{\rm det}\}$. Successful reactivation events arrive with a time-dependent intensity, and each event seeds an exponentially expanding viral lineage. The total plasma viral load is therefore a Poisson shot-noise process, and rebound corresponds to its first threshold crossing. In the rare-reactivation regime, this crossing is dominated by the earliest successful lineage. Rebound timing then separates into two components: a stochastic waiting time for reservoir reactivation and a deterministic growth delay to detectability. This separation gives a shifted-hazard survival law and yields closed-form rebound-time distributions for constant activation, ART-washout-dependent activation, immune-periodic activation, Cox-process activation, and heterogeneous-reservoir activation. The same formulation also provides a likelihood suitable for the interval-censored sampling structure of ATI trials.
arXiv:2607.02087v2 Announce Type: replace
Abstract: Hierarchical state-space models (HSSMs) offer a promising approach to long-horizon prediction by segmenting sequences into temporal chunks. However, their performance hinges on how chunk boundaries are determined. While prior HSSMs typically rely on fixed-length chunking or similarity-based boundary detection, these methods often misalign with the intrinsic temporal structure of the data. We argue that chunking should instead be driven by prediction errors, which more directly indicate when longer-range context becomes necessary. Nevertheless, integrating surprise-based chunking into HSSMs introduces critical challenges, including hierarchical collapse during end-to-end training and the absence of surprise signals during open-loop prediction. To address these issues, we propose Surprise-based Nested Temporal Abstraction (SUNTA), a method that employs a decoupled training strategy to preserve surprise signals and uses internal inconsistency as a top-down surprise metric to determine chunk boundaries within imagined rollouts. Experiments on video prediction tasks in 2D and 3D environments demonstrate that SUNTA outperforms baselines, uniquely maintaining accurate predictions over 250 timesteps, whereas all baselines degrade within the first 10 timesteps.
arXiv:2607.10278v1 Announce Type: new
Abstract: Accurate cervical cytology image classification is a key component of automated cervical cancer screening, where reliable recognition of normal, precancerous, and cancer-associated cellular patterns from Pap smear images can improve screening efficiency and diagnostic consistency. However, this task remains challenging because cervical cells exhibit complex morphology, subtle intra-class variations, and strong inter-class similarities. Existing convolution-based models capture local texture well but have limited ability to model long-range relationships, whereas attention-based models provide broader context but often lack explicit structural guidance. To address these limitations, we propose a geometry-aware classification framework for cervical cancer screening-oriented cytology image analysis, incorporating semantic abstraction and structural priors learned from pre-trained vision-language features. The method uses Gaussian expert modules to generate axis-wise priors from global semantic information, capturing structural regularities such as nuclear alignment and cellular spatial organization. These priors are embedded into an axial self-attention module to modulate similarity computation along horizontal and vertical directions, improving long-range dependency modeling and structure-sensitive feature interaction. Experiments on the Mendeley liquid-based cytology and SIPaKMeD datasets show that the proposed method achieves 99.48% accuracy on the former and 96.08% on the latter, with balanced gains in recall, precision, and overall classification performance. Visual analysis further shows that the learned priors highlight diagnostically relevant cellular regions, demonstrating the potential of the proposed framework as a screening-oriented decision-support tool for cervical cytology.
arXiv:2607.10113v1 Announce Type: new
Abstract: Large language model agents increasingly store reusable procedures outside the model. These reusable procedures are often called \emph{skills}: they may be code functions, natural-language instructions, SKILL.md packages, workflow graphs, or learned adapters that a future agent can retrieve and invoke. This taxonomy-driven survey asks how such skill libraries change over time. Across a $124$-paper $2023$--$2026$ audit set, we synthesize dynamic skill systems as \emph{lifecycle-managed, verified, evolving artifact stores}: agents collect evidence from interaction, propose skill updates, verify and admit candidates, organize them for retrieval and composition, repair or prune stale entries, and govern sharing through provenance and rollback. We organize the literature around three survey tools. First, a $\text{six}$-sense taxonomy distinguishes the structurally different artifacts called ``skills'' in current papers. Second, an $\text{eight}$-stage lifecycle architecture identifies the recurring design decisions behind evidence acquisition, proposal, verification/admission, storage, retrieval/composition, maintenance, distillation/portability, and governance. Third, a lightweight skill-record schema and $\text{ten}$-operator vocabulary provide common terms for comparing library updates without elevating them into a separate method contribution. Using this structure, we synthesize evidence-graded patterns with explicit caveats: admission and repair are repeatedly important, verifier quality materially affects skill-aware RL, flat retrieval can degrade as libraries grow, and current benchmarks still under-report library trajectories, usage--utility gaps, and safety surfaces. We close with concrete reporting standards and open problems for evaluating dynamic skills as changing libraries rather than static prompt or tool collections.
arXiv:2607.11301v1 Announce Type: new
Abstract: We introduce a unified framework for classical search and routing problems, including pathwise search, expanding search, the minimum spanning tree problem, and the traveling salesperson problem. The framework is based on two parameters. The first is a discount factor $\alpha \in [0,1]$: the first traversal of an edge incurs its full cost, whereas each subsequent traversal incurs only an $\alpha$-fraction of this cost. For a path starting at a designated root vertex, the $\alpha$-latency of a vertex is the discounted cost accumulated until the vertex is first visited. The second parameter is a norm parameter $p\geq 1$. The objective is to find a root-starting path that visits all vertices and minimizes the $p$-norm of the resulting vector of $\alpha$-latencies.
The model interpolates between several well-studied objectives. For $p=1$ and $\alpha=1$, it recovers pathwise search; for $p=1$ and $\alpha=0$, it recovers expanding search. As $p$ tends to infinity, the objective converges to a makespan-type criterion. At the endpoints $\alpha=1$ and $\alpha=0$, this limiting objective corresponds to TSP-type and MST-type behavior, respectively. For $p=1$, we give polynomial-time constant-factor approximation algorithms for all $\alpha\in[0,1]$, matching the best known guarantees for expanding search at $\alpha=0$ and pathwise search at $\alpha=1$. For general $p\geq 1$, we obtain a randomized constant-factor approximation algorithm and a derandomized pseudo-polynomial-time algorithm with the same guarantee.
arXiv:2607.06372v2 Announce Type: replace
Abstract: A standard way to control expression swell in computer algebra is to use multi-modular or evaluation-interpolation methods. In computations involving Gr\"obner bases, these techniques typically require repeatedly computing Gr\"obner bases of specializations of the same ideal. These repeated computations can be accelerated through precomputation, notably using Traverso's tracing. We present Groebner$.$jl (https://github.com/sumiya11/Groebner.jl), a Julia implementation of the F4 algorithm that exposes Traverso's tracing through a reusable public interface. The implementation supports SIMD-friendly coefficient types, such as tuples of machine integers, which Julia compiles to efficient code with little manual intervention. This lets other Julia software leverage tracing to obtain speedups in applications such as structural identifiability of ordinary differential equation models and polynomial system solving.
arXiv:2607.06894v2 Announce Type: replace
Abstract: We study the task of disambiguation of finite state automata, namely, converting an automaton into an equivalent, unambiguous one. We do this by developing a novel and simple algorithmic framework that generalizes the subset construction for determinization, and that satisfies some desirable properties: (1) it preserves the original automaton if it was already unambiguous, (2) it computes the successor states on-the-fly and (3) computes each new state in polynomial time--this last point is crucial as it guarantees that the running time is polynomial in the size of the output automaton. Then, we show how to apply this framework for partial disambiguation: by changing the criterion that builds the new states, we develop algorithms for different levels of ambiguity, namely, finitely ambiguous, and polynomially ambiguous automata. These algorithms also satisfy condition (1) for their respective levels, and also (2) and (3). Finally, we show that the disambiguation framework can easily be extended to other models of automata like weighted automata.
arXiv:2602.02905v2 Announce Type: replace
Abstract: Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a trade-off: they either heavily rely on LLM-as-judge evaluations of automatically generated research outputs or optimize convenient yet isolated performance metrics that provide coarse proxies for scientific insight. To address this gap, we introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery of established findings from recent, high-impact machine learning research. Agents are given only a high-level research question extracted from a published, verified study and must autonomously explore ideas, design experiments, implement code, execute their plans, and derive conclusions supported by empirical evidence. We evaluate a range of state-of-the-art agents with frontier LLMs backbones like gpt-5 on FIRE-Bench. Our results show that full-cycle scientific research remains challenging for current agent systems: even the strongest agents achieve limited rediscovery success (<50 F1), exhibit high variance across runs, and display recurring failure modes in experimental design, execution, and evidence-based reasoning. FIRE-Bench provides a rigorous and diagnostic framework for measuring progress toward reliable agent-driven scientific discovery.
arXiv:2602.03435v2 Announce Type: replace
Abstract: Continuum soft robots are inherently underactuated and subject to intrinsic input constraints, making dynamic control particularly challenging, especially in hybrid rigid-soft robots. While most existing methods focus on quasi-static behaviors, dynamic tasks such as swing-up require accurate exploitation of continuum dynamics. This has led to studies on simple low-order template systems that often fail to capture the complexity of real continuum deformations. Model-based optimal control offers a systematic solution; however, its application to rigid-soft robots is often limited by the computational cost and inaccuracy of numerical differentiation for high-dimensional models. Building on recent advances in the Geometric Variable Strain model that enable analytical derivatives, this work investigates three optimal control strategies for underactuated soft systems -- Direct Collocation, Differential Dynamic Programming, and Nonlinear Model Predictive Control -- to perform dynamic swing-up tasks. To address stiff continuum dynamics and constrained actuation, implicit integration schemes and warm-start strategies are employed to improve numerical robustness and computational efficiency. The methods are evaluated in simulation on three Rigid-Soft and high-order soft benchmark systems -- the Soft Cart-Pole, the Soft Pendubot, and the Soft Furuta Pendulum -- highlighting their performance and computational trade-offs.
arXiv:2607.11357v1 Announce Type: new
Abstract: Failure diagnosis in modern software systems requires iterative evidence acquisition and hypothesis reasoning guided by operational experience. Existing LLM-based methods improve diagnosis through agentic reasoning or knowledge augmentation, but they often lack a mechanism to coordinate the evolving diagnostic state with operational experience during iterative diagnosis. We propose OpsMem, a dual-memory framework that maintains a short-term memory for the current diagnostic state and a long-term memory for reusable operational experience. OpsMem uses cross-memory resonance to activate state-relevant long-term memory, conditions multi-agent diagnosis on the short-term and activated long-term memories, and consolidates reusable experience from solved incidents back into long-term memory. Experiments on a real-world Huawei microservice failure diagnosis dataset show that OpsMem outperforms representative agentic-reasoning and knowledge-augmented baselines, improving Match and Relevant by up to 46.88% and 18.39% over the strongest baseline, respectively.
arXiv:2607.11538v1 Announce Type: new
Abstract: Self-supervised learning (SSL) models are widely used as feature extractors for state-of-the-art audio deepfake detection, but it remains unclear how to directly and quantitatively connect what SSL models capture to detection decisions. To address this gap, we propose Evidence Subspace Projection, a method that represents both evidence factors (e.g., attack category, codec, gender, transmission) and authenticity labels in a shared space constructed from SSL models' neuron activation patterns. By projecting the decision vector onto each evidence subspace, we obtain a scalar ratio that quantifies the explanatory power of each evidence type. We evaluate SSL models in raw, fine-tuned, and post-trained settings on multiple datasets. The results confirm findings from established studies, validating the proposed method, and reveal new insights into model behavior.
arXiv:2607.11540v1 Announce Type: new
Abstract: We study tropical circuits with scalar multiplication gates, that is, algebraic circuits whose gates implement $\max$, $+$, or multiplication with a positive constant. For such circuits, we prove exponential size lower bounds for computing maximum weight directed spanning trees and maximum weight bipartite perfect matchings. As a corollary, we obtain an exponential size separation between monotone and non-monotone maxout neural networks, which generalize the popularly used ReLU neural networks. One conclusion from this is that neural network models with enforced convexity constraints, such as input-convex neural networks (ICNNs), sometimes need to be exponentially larger than their unrestricted counterparts in order to express the same functions.
arXiv:2607.10729v1 Announce Type: new
Abstract: Molecular property models are commonly evaluated by holding out Bemis--Murcko scaffolds, yet a scaffold identifier is only one notion of chemical unfamiliarity. We introduce a label-free structural-frontier split that reserves the sparsest and most physicochemically remote scaffold groups, and evaluate it on six public experimental or curated ADMET tasks. Against a 70/10/20 scaffold control with identical acyclic grouping, the frontier inflates equally weighted primary error with a taskwise median of 87.0\% and a skew-sensitive mean of 130.3\% (descriptive task/seed bootstrap interval, 52.1--246.0\%). The mean falls to 75.9\% once BBB is removed; that endpoint is the one whose score ranking inverts at the frontier. A message-passing graph-network control still shows a large gap (mean 82.8\% over four tasks) and does not invert, so a low-capacity head does not explain the effect. We also test Multi-View Frontier Risk Extrapolation (\method), a count-adjusted tail-risk penalty over four molecular views, and treat it as a falsifiable probe. It changes normalized frontier error by only 0.16\% relative to empirical risk minimization for the perceptron head (interval, $-0.43$--0.84\%) and by $-1.9$\% for the graph network; three fixed robust-penalty controls are likewise inconclusive. Against the published Lo-Hi and DataSAIL splitters the frontier inflates error more on average, though no split is uniformly hardest. An audit of 31,561 marine natural products further shows that OOD status and agreement with legacy ADMET predictions depend on the molecular view, endpoint and teacher coverage. Split construction and label provenance are important evaluation constraints in their own right, and the tested training penalties do not resolve the frontier failures we observe.
arXiv:2607.11257v1 Announce Type: new
Abstract: Pathology Foundation Models (PFMs) offer powerful Whole Slide Image (WSI) representations but suffer from massive computational costs. While Knowledge Distillation (KD) can create efficient student models, existing multi-teacher methods often use suboptimal uniform weighting that ignores tissue heterogeneity. We propose LaGuadia (Language-Guided Adaptive DistillAtion), a framework that develops a compact pathology image encoder by dynamically integrating expertise from multiple PFMs under clinical linguistic guidance. Our approach utilizes a multi-stage pipeline: first, extracting visually observable clinical keywords from pathology reports; second, aligning visual features with these keywords via a Vision-Language meta-teacher (MedSigLIP) to provide dense semantic guidance; and finally, performing adaptive KD where teacher contributions are weighted based on their semantic alignment with the clinical narrative. Experiments on WSI captioning, visual question answering, and slide-level classification tasks demonstrate that an 87M parameter LaGuadia student model matches or exceeds foundation-scale models such as GigaPath and UNI, achieving strong factual consistency and robust generalization. These results highlight clinical language as an effective semantic anchor for building efficient and reliable digital pathology systems. Code is available at https://github.com/hvcl/LaGuadia.
arXiv:2607.11269v1 Announce Type: new
Abstract: Decision support systems (DSS) increasingly run retention what-if analysis on synthetic customer populations, because privacy constraints preclude unrestricted use of real data. Such a system is trustworthy only if the synthetic data lead managers to the same decisions as the real data would; yet prevailing criteria certify distributional similarity, not decision alignment, so a synthetic population can match every marginal distribution while still steering a marketing team toward the wrong campaigns. We close this decision-alignment gap with three contributions: strategy simulation fidelity (SSF), a criterion measuring how often the synthetic population yields the same go/no-go campaign decision as the real population; PolicySynth, a DSS framework whose generator is conditioned on the production churn scorer to align decision-relevant structure; and a three-axis reporting standard of decision alignment, membership-inference resistance, and novel-record rate as the minimum deployment quality gate. On a telecommunications churn corpus and a banking acquisition corpus, PolicySynth attains a mean SSF of 0.923 and 0.960, with seed-to-seed variance roughly ten times tighter than CTGAN on telecommunications and 2.5 times on banking. This stability is the deployable property: go/no-go recommendations shift by at most 1.2 percentage points between monthly retraining cycles, against 11.5 for CTGAN, a reversed recommendation on one campaign in nine. A bootstrap baseline matches PolicySynth on SSF yet copies real records verbatim and fails membership inference, evidence that no single axis suffices. PolicySynth reliably supports directional go/no-go screening; its ROI estimates diverge from real outcomes by 70 to 78% and require the volume correction we document.
arXiv:2607.10736v1 Announce Type: new
Abstract: Artificial intelligence agents increasingly perform journalism tasks autonomously, searching for sources, evaluating credibility, and producing news content with minimal human oversight. Yet research has largely treated AI as a monolithic category, leaving the effects of architectural design unexamined. Drawing on gatekeeping theory, this study presents the first systematic comparison of four agent architectures, monolithic (Claude), chain-based (LangChain), multi-agent collaborative (CrewAI), and autonomous iterative (AutoGPT), across 200 controlled experiments spanning 50 journalism tasks of graduated difficulty. All architectures used the same underlying language model and identical tools, isolating architectural effects. Results revealed significant effects on task duration (F(3, 196) = 24.54, p < .001, eta-squared = .27) and computational strategy (F(3, 196) = 305.63, p < .001, eta-squared = .82), with architecture explaining 82% of the variance in processing behavior. Multi-agent collaboration achieved the highest accuracy (84.7%) at roughly twice the time cost of other designs. Multistage analysis of the monolithic architecture documented a 71.7% source rejection rate, a quantitative parallel to classic human gatekeeping, while framework-based systems obscured their filtering inside abstraction layers. Transparency emerged as an architectural choice: framework designs excelled at structured attribution, whereas monolithic and iterative designs produced superior methodological documentation. Findings position architecture as a new structural level of gatekeeping and offer evidence-based guidance for newsrooms: chain-based designs for speed, multi-agent for accuracy, monolithic for versatility, and iterative for auditability.
arXiv:2607.11379v1 Announce Type: new
Abstract: Network theoreticians hypothesize that the structure of real-world networks has a geometric origin. Especially, hyperbolic geometry was proven insightful in representing and modeling of scale-free networks. Embedders are algorithms used to find a geometric representation of a network. In this study, we introduce a fast lossless graph compression algorithm based on modern hyperbolic embedders. Experimental validation on real-world and generated networks shows that our algorithm beats state-of-the-art by up to 42% on real-world graphs.
arXiv:2607.09948v1 Announce Type: new
Abstract: Cardiac amyloidosis (CA) is increasingly recognized but remains substantially underdiagnosed, because its clinical and imaging phenotype overlaps with more common cardiomyopathies. Definitive subtype assignment and management further require integration of multimodal evidence to distinguish transthyretin from light chain disease. Machine learning and deep learning have been applied across the diagnostic and management pathway. These applications span ECG, echocardiography, and health record-based case finding, as well as CMR and nuclear interpretation, including SPECT/CT biomarker quantification, prognostic modeling, and treatment response assessment. This narrative review synthesizes these studies by clinical tasks, namely screening, detection, quantification, prognosis, and treatment response monitoring, rather than by input modality. This task-based organization clarifies why apparently similar AI models require different cohorts, reference standards, evaluation metrics, and implementation thresholds. The evidence reveals a maturity gradient. Binary detection and AI assisted quantification on bone scintigraphy and SPECT/CT are closest to clinical translation. Detection is supported by large externally validated cohorts, and quantification by interpretable, outcome linked measurement of myocardial tracer burden. By contrast, subtype aware classification, prognostic risk stratification, and treatment response monitoring remain at an early stage. These tasks are limited by small cohorts, enriched retrospective designs, heterogeneous labels, incomplete external validation, and uncertain calibration in realistic prevalence settings. Across tasks, high discrimination alone is insufficient.
arXiv:2607.09962v1 Announce Type: new
Abstract: Automation in industries such as retail, warehousing and logistics presents opportunities for greater throughput, cost reduction and mitigation of disruptions from labour shortages. Previously, such efforts have focused on back-room operations involving packing and sorting in relatively structured environments. With advances in robotic mobile manipulation hardware and foundation models, automation can now be applied to more variable and human-centric environments such as retail store shelves. In this work, we present a task-planning approach using Large Language Models (LLMs) and Vision-Language Models (VLMs) to address the restocking problem in retail scenarios such as supermarkets. We demonstrate this system on a custom omnidirectional mobile manipulation platform, with user-driven prompts and a feedback-based iterative re-planning approach for error correction. The end-to-end system is validated in a PyBullet simulation environment for pick-and-place tasks.