Grid-scale battery degradation unfolds over multi-year timescales under coupled electrochemical, thermal, and operational feedbacks difficult to capture using laboratory data or proprietary field datasets. This scarcity limits the development of degradation-aware algorithms and digital twins that require long-horizon, physically consistent ground truth. Here we present SAGE (Synthetic Aging for a Grid Environment), an open-source, physics-informed simulation framework that generates hour-resolved, multi-decade operating histories and degradation trajectories for heterogeneous battery energy storage system (BESS) fleets. The framework couples stochastic environmental drivers, market-based dispatch, electro-thermal behavior, aging kinetics, and asset-level heterogeneity within a transparent, externally parameterized architecture. We validate physical consistency through hierarchical tests, including Arrhenius temperature acceleration, thermal stratification, and emergent wear-out statistics. Simulations demonstrate how intrinsic heterogeneity in thermal environments and manufacturing naturally produces dispersion in state-of-health trajectories without imposed statistical failure ass
Agentic LLMs must continuously decide whether newly extracted facts should be added, merged with existing memories, or ignored, yet prior work has focused more on retrieval and storage than on principled write-side control. We frame memory evolution as a novelty-detection problem and propose SAGE, a Spherical Adaptive Gate for memory Evolution that scores candidate facts with a von Mises-Fisher-based density estimator over memory embeddings and routes them with an adaptive threshold that tracks memory-store geometry. SAGE resolves clearly novel facts as ADD, clearly redundant facts as NOOP, and sends only uncertain cases to an LLM merge step, reducing expensive write-time reasoning. On LoCoMo, SAGE achieves the best average token-F1 against Mem0 on all seven open-weight backbone comparisons, while on GPT-4o-mini it reduces add-phase API cost by 3.4$\times$ and add-phase latency by 2.5$\times$ with only a small average judge-score gap. As a drop-in binary gate for A-Mem, SAGE skips roughly 16-18% of LLM calls across five models with minimal quality change on open-weight backbones. These results suggest that novelty-aware write control is a practical lever for improving both memory q
Simulating prospective magnetic resonance imaging (MRI) scans from a given individual brain image is challenging, as it requires accounting for canonical changes in aging and/or disease progression while also considering the individual brain's current status and unique characteristics. While current deep generative models can produce high-resolution anatomically accurate templates for population-wide studies, their ability to predict future aging trajectories for individuals remains limited, particularly in capturing subject-specific neuroanatomical variations over time. In this study, we introduce Individualized Brain Synthesis (InBrainSyn), a framework for synthesizing high-resolution subject-specific longitudinal MRI scans that simulate neurodegeneration in both Alzheimer's disease (AD) and normal aging. InBrainSyn uses a parallel transport algorithm to adapt the population-level aging trajectories learned by a generative deep template network, enabling individualized aging synthesis. As InBrainSyn uses diffeomorphic transformations to simulate aging, the synthesized images are topologically consistent with the original anatomy by design. We evaluated InBrainSyn both quantitativ
We investigate the effects of aging in the noisy voter model considering that the probability to change states decays algebraically with age $τ$, defined as the time elapsed since adopting the current state. We study the complete aging scenario, which incorporates aging to both mechanisms of interaction: herding and idiosyncratic behavior, and compare it with the partial aging case, where aging affects only the herding mechanism. Analytical mean-field equations are derived, finding excellent agreement with agent-based simulations on a complete graph. We observe that complete aging enhances consensus formation, shifting the critical point to higher values compared to the partial aging case. However, when the aging probability decays asymptotically to zero for large $τ$, a steady state is not always attained for complete aging.
The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static computation graphs with fixed routing. This leads to extra computation and makes it harder to adapt to changes in input. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures via a dual-path design with hierarchical gating and a Shape-Adapting Hub (SA-Hub) that harmonizes feature representations across convolutional and transformer modules. Embodied as SAGE with ConvNeXt and Vision Transformer UNet (SAGE-ConvNeXt+ViT-UNet), our model achieves a Dice score of 95.23% on EBHI, DSC scores of 92.78% and 91.42% on GlaS Test A and Test B, respectively, and 91.26% DSC at the WSI level on DigestPath, while exhibiting robust generalization under distribution shifts by adaptively balancing local refinement and global context. SAGE establishes a scalable foundation for dynamic expert routing
As humans, we are natural any-horizon reasoners, i.e., we can decide whether to iteratively skim long videos or watch short ones in full when necessary for a given task. With this in mind, one would expect video reasoning models to reason flexibly across different durations. However, SOTA models are still trained to predict answers in a single turn while processing a large number of frames, akin to watching an entire long video, requiring significant resources. This raises the question: Is it possible to develop performant any-horizon video reasoning systems? Inspired by human behavior, we first propose SAGE, an agent system that performs multi-turn reasoning on long videos while handling simpler problems in a single turn. Secondly, we introduce an easy synthetic data generation pipeline using Gemini-2.5-Flash to train the orchestrator, SAGE-MM, which lies at the core of SAGE. We further propose an effective RL post-training recipe essential for instilling any-horizon reasoning ability in SAGE-MM. Thirdly, we curate SAGE-Bench with an average duration of greater than 700 seconds for evaluating video reasoning ability in real-world entertainment use cases. Lastly, we empirically val
Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines, yielding artifacts and physically invalid scenes. We present SAGE, an agentic framework that, given a user-specified embodied task (e.g., "pick up a bowl and place it on the table"), understands the intent and automatically generates simulation-ready environments at scale. The agent couples multiple generators for layout and object composition with critics that evaluate semantic plausibility, visual realism, and physical stability. Through iterative reasoning and adaptive tool selection, it self-refines the scenes until meeting user intent and physical validity. The resulting environments are realistic, diverse, and directly deployable in modern simulators for policy training. Policies trained purely on this data exhibit clear scaling trends and generalize to unseen objects and layouts, demonstrating the promise of simulation-driven scaling for embodied AI. Code, demos, and the SAGE-10k dataset can be found on the project page here: https://resea
Automatically generated software, especially code produced by Large Language Models (LLMs), is increasingly adopted to accelerate development and reduce manual effort. However, little is known about the long-term reliability of such systems under sustained execution. In this paper, we experimentally investigate the phenomenon of software aging in applications generated by LLM-based tools. Using the Bolt platform and standardized prompts from Baxbench, we generated four service-oriented applications and subjected them to 50-hour load tests. Resource usage, response time, and throughput were continuously monitored to detect degradation patterns. The results reveal significant evidence of software aging, including progressive memory growth, increased response time, and performance instability across all applications. Statistical analyzes confirm these trends and highlight variability in the severity of aging according to the type of application. Our findings show the need to consider aging in automatically generated software and provide a foundation for future studies on mitigation strategies and long-term reliability evaluation.
This chapter demonstrates how computational social science (CSS) tools are extending and expanding research on aging. The depth and context from traditionally qualitative methods such as participant observation, in-depth interviews, and historical documents are increasingly employed alongside scalable data management, computational text analysis, and open-science practices. Machine learning (ML) and natural language processing (NLP), provide resources to aggregate and systematically index large volumes of qualitative data, identify patterns, and maintain clear links to in-depth accounts. Drawing on case studies of projects that examine later life--including examples with original data from the DISCERN study (a team-based ethnography of life with dementia) and secondary analyses of the American Voices Project (nationally representative interview)--the chapter highlights both uses and challenges of bringing CSS tools into more meaningful dialogue with qualitative aging research. The chapter argues such work has potential for (1) streamlining and augmenting existing workflows, (2) scaling up samples and projects, and (3) generating multi-method approaches to address important question
This paper examines the state of Open Data in Latvia at the middle of 2014. The study is divided into two parts: (i) a survey of open data situation and (ii) an overview of available open data sets. The first part examines the general open data climate in Latvia according to the guidelines of the OKFN Open Data Index making the results comparable to those of other participants of this index. The second part examines datasets made available on the Latvia Open Data community catalogue, the only open data catalogue available in Latvia at the moment. We conclude that Latvia public sector open data mostly fulfil the basic criteria (e.g., data is available) of the Open Data Index but fail on more advanced criteria: the majority of data considered in the study are not published in machine-readable form, are not available for bulk download and none of the data sources have open license statements.
A long term operation of Multi-Strip Multi-Gap Resistive Plate Chambers (MSMGRPC) with gas mixtures based on C2H2F4 and SF6 leads to aging effects, observed as depositions on the surface of the resistive electrodes. Moreover, enhanced depositions and higher noise rates were evidenced around the nylon spacers used for defining the gas gaps between the resistive electrodes. The aging effects are reflected in an increase of the dark current and dark counting rate, with negative impact on the long term performance of the chamber and data volume in a free running readout mode operation. MSMGRPC prototypes designed with a direct gas flow through the gas gaps and minimization of the number of spacers in the active area were developed as mitigation solution. Prototypes with this new design and different granularities were assembled using fishing line as spacers and investigated for aging effects. Although a significant reduction in the dark current and dark counting rate was evidenced, dark counting rate localized around the fishing line spacers remains. In this paper, a new generation of direct flow chambers based on discrete spacers is presented. The results of their aging investigations
The role of additives such as FEC in extending the calendar life of silicon anodes beyond the cycling benefits is still not fully understood. Herein, the calendar life of high-loading Si (80 wt%) using baseline 1.2 M LiPF6 in EC-EMC electrolyte versus adding 10 wt% FEC is investigated over months. Over 8 days of aging, FEC leads to a 13-fold reduction in irreversible capacity loss in Si-LiFePO4 full cells. Cells without FEC are projected to fall below 80% of their initial capacity within approx. 22 days versus approx. 279 days with FEC. Symmetric Si-Si cells from harvested electrodes show greater increase in interphase resistance without FEC, whereby an increase of 10.81 Ohms is measured for 0 wt% FEC vs. only 3.37 Ohms for 10 wt% FEC over 2 months. Power law modeling of this long-term interphase resistance finds mixed transport-reaction growth behavior in FEC-free cells, suggesting significant dissolution, whereas cells with 10 wt% FEC added display a diffusion-controlled impedance growth behavior, suggesting a robust surface passivation film. Post-mortem FTIR and XPS confirm polycarbonate enrichment of the SEI, which was discovered to predominantly emerge from FEC self-polymeriza
To investigate in more details of Stellar Abundance and Galactic Evolution (SAGE) and in a huge sample, we are performing a northern sky photometric survey named SAGES with the SAGE photometric system, which consists of 8 filters: Strömgren-$u$, SAGE-$v$, SDSS $g$, $r$, $i$, DDO-$51$, $Hα_{wide}$, and $Hα_{narrow}$, including three Sloan broadband filters, three intermediate-band filters and two narrow-band filters, and one newly-designed narrow-band filter. SAGES covers $\sim$12,000 square degrees of the northern sky with $δ> -5 ^{\circ}$, excluding the Galactic disk ($|b|<10^{\circ}$) and the sky area of 12 hr $<$ R.A. $<$ 18\,hr. The photometric detection limit depth at signal-to-noise ratio $5σ$ can be as deep as $V\sim$20\,mag. The SAGES will produce a depth-uniformed photometric catalogue for $\sim$500 million stars with atmospheric parameters including effective temperature $T_{\rm eff}$, surface gravity log\,g, and metallicity [Fe/H], as well as interstellar extinction to each individual target. In this work, we will briefly introduce the SAGE photometric system, the SAGE survey, and a preliminary test field of the open cluster NGC\,6791 and around.
The Shapley Additive Global Importance (SAGE) value is a theoretically appealing interpretability method that fairly attributes global importance to a model's features. However, its exact calculation requires the computation of the feature's surplus performance contributions over an exponential number of feature sets. This is computationally expensive, particularly because estimating the surplus contributions requires sampling from conditional distributions. Thus, SAGE approximation algorithms only take a fraction of the feature sets into account. We propose $d$-SAGE, a method that accelerates SAGE approximation. $d$-SAGE is motivated by the observation that conditional independencies (CIs) between a feature and the model target imply zero surplus contributions, such that their computation can be skipped. To identify CIs, we leverage causal structure learning (CSL) to infer a graph that encodes (conditional) independencies in the data as $d$-separations. This is computationally more efficient because the expense of the one-time graph inference and the $d$-separation queries is negligible compared to the expense of surplus contribution evaluations. Empirically we demonstrate that $d
The classes of sums of arithmetic-geometric exponentials (SAGE) and of sums of nonnegative circuit polynomials (SONC) provide nonnegativity certificates which are based on the inequality of the arithmetic and geometric means. We study the cones of symmetric SAGE and SONC forms and their relations to the underlying symmetric nonnegative cone. As main results, we provide several symmetric cases where the SAGE or SONC property coincides with nonnegativity and we present quantitative results on the differences in various situations. The results rely on characterizations of the zeroes and the minimizers for symmetric SAGE and SONC forms, which we develop. Finally, we also study symmetric monomial mean inequalities and apply SONC certificates to establish a generalized version of Muirhead's inequality.
Cloud computing has brought a fundamental transformation in how organizations operate their applications, enabling them to achieve affordable high availability of services. Kubernetes has emerged as the preferred choice for container orchestration and service management across many Cloud computing platforms. The scheduler in Kubernetes plays a crucial role in determining the placement of newly deployed service containers. However, the default scheduler, while fast, often lacks optimization, leading to inefficient service placement or even deployment failures. This paper introduces SAGE, a tool for optimal solutions in Kubernetes clusters that can also assist the Kubernetes default scheduler and any other custom scheduler in application deployment. SAGE computes an optimal deployment plan based on the constraints of the application to be deployed and the available Cloud resources. We show the potential benefits of using SAGE by considering test cases with various characteristics. It turns out that SAGE surpasses other schedulers by comprehensively analyzing the application demand and cluster image. This ability allows it to better understand the needs of the pods, resulting in consi
The common sense reasoning abilities and vast general knowledge of Large Language Models (LLMs) make them a natural fit for interpreting user requests in a Smart Home assistant context. LLMs, however, lack specific knowledge about the user and their home limit their potential impact. SAGE (Smart Home Agent with Grounded Execution), overcomes these and other limitations by using a scheme in which a user request triggers an LLM-controlled sequence of discrete actions. These actions can be used to retrieve information, interact with the user, or manipulate device states. SAGE controls this process through a dynamically constructed tree of LLM prompts, which help it decide which action to take next, whether an action was successful, and when to terminate the process. The SAGE action set augments an LLM's capabilities to support some of the most critical requirements for a Smart Home assistant. These include: flexible and scalable user preference management ("is my team playing tonight?"), access to any smart device's full functionality without device-specific code via API reading "turn down the screen brightness on my dryer", persistent device state monitoring ("remind me to throw out
It is well known that the state operator of an open quantum system can be generically represented as the solution of a time-local equation -- a quantum master equation. Unraveling in quantum trajectories offers a picture of open system dynamics dual to solving master equations. In the unraveling picture, physical indicators are computed as Monte-Carlo averages over a stochastic process valued in the Hilbert space of the system. This approach is particularly adapted to simulate systems in large Hilbert spaces. We show that the dynamics of an open quantum system generically admits an unraveling in the Hilbert space of the system described by a Markov process generated by ordinary stochastic differential equations for which rigorous concentration estimates are available. The unraveling can be equivalently formulated in terms of norm-preserving state vectors or in terms of linear ``ostensible" processes trace preserving only on average. We illustrate the results in the case of a two level system in a simple boson environment. Next, we derive the state-of-the-art form of the Diosi-Gisin-Strunz Gaussian random ostensible state equation in the context of a model problem. This equation pro
Extrusion-based 3D printing has become one of the most common additive manufacturing methods and is widely used in engineering. This contribution presents the results of flexural creep experiments on 3D printed PLA specimens, focusing on changes in creep behavior due to physical aging. It is shown experimentally that the creep curves obtained on aged specimens are shifted to each other on the logarithmic time scale in a way that the theory of physical aging can explain. The reason for the physical aging of 3D printed thermoplastics is assumed to be the special heat treatment that the polymer undergoes during extrusion. Additionally, results of a long-term flexural creep experiment are shown, demonstrating that non-negligible creep over long periods can be observed even at temperatures well below the glass transition temperature. Such creep effects should be considered for designing components made of 3D printed thermoplastics.
Data augmentation is a key element for training accurate models by reducing overfitting and improving generalization. For image classification, the most popular data augmentation techniques range from simple photometric and geometrical transformations, to more complex methods that use visual saliency to craft new training examples. As augmentation methods get more complex, their ability to increase the test accuracy improves, yet, such methods become cumbersome, inefficient and lead to poor out-of-domain generalization, as we show in this paper. This motivates a new augmentation technique that allows for high accuracy gains while being simple, efficient (i.e., minimal computation overhead) and generalizable. To this end, we introduce Saliency-Guided Mixup with Optimal Rearrangements (SAGE), which creates new training examples by rearranging and mixing image pairs using visual saliency as guidance. By explicitly leveraging saliency, SAGE promotes discriminative foreground objects and produces informative new images useful for training. We demonstrate on CIFAR-10 and CIFAR-100 that SAGE achieves better or comparable performance to the state of the art while being more efficient. Addi