Papers

Vision-language-conditioned robot policies integrate perception, language understanding, and control for general-purpose manipulation. However, existing evaluations often focus on task success, isolated physical constraints, semantic refusal, or realized physical damage, providing limited insight into where safety fails during closed-loop manipulation. We introduce SafeStage, a lifecycle-structured benchmark for evaluating manipulation safety before, during, and after task execution. SafeStage contains 97 purpose-built risk scenarios organized into three stages. Initial-State Hazards captures safety-relevant relations that must be resolved before manipulating the target. Execution-Time Safety evaluates unsafe contacts, trajectories, region entries, and object interactions during execution. Final-State Hazards capture unstable or otherwise unsafe conditions remaining after nominal task completion. The benchmark evaluates realized interactions using event-based and state-based checks and reports native task success independently from stage-specific safety outcomes. We evaluate representative direct-action Vision-Language-Action (VLA) policies and policies with world-model-based policies under a common closed-loop protocol. Our results demonstrate that nominal task completion frequently coexists with safety violations and that different policies exhibit distinct failure profiles across the three stages. By separating task success from safety and localizing when violations occur, SafeStage provides a unified diagnostic testbed for evaluating and improving vision-language-conditioned robot manipulation policies.

Security analysts can become overwhelmed with monitoring real-time security information that is important to help them defend their network. They also tend to focus on a limited portion of the alerts, and therefore risk missing important events and links between them. At the heart of the problem is the system that analysts use to detect, explore, and respond to cyber-attacks. Developers of security analysis systems face the challenge of developing a system that can present different sources of information at multiple levels of abstraction, while also creating a system that is intuitive to use. In this article, we examine the complementary nature of exploratory analysis and automated analysis by testing the development of a system that monitors real-time Border Gateway Protocol (BGP) traffic for anomalies that might indicate security threats. BGP is an essential component for supporting the infrastructure of the Internet; however, it is also highly vulnerable and can be hijacked by attackers to propagate spam or launch denial-of-service attacks. Some of the attack scenarios on the BGP infrastructure can be quite elaborate, and it is difficult, if not impossible, to fully automate the detection of such attacks. This article makes two contributions: i) it describes a prototype platform for computing indicators and threat alerts in real time and for visualizing the context of an alert, and ii) it discusses the interaction of exploratory analysis (visualization) and automated analysis. This article is relevant to students, security researchers, and developers who are interested in the development or use of real-time security monitoring systems. They will gain insights into the complementary aspects of automated analysis and exploratory analysis through the development of a real-time streaming system.

Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rules. Conventional methods convert perception into discrete symbolic facts and then plan, discarding perceptual uncertainty and severing task-level feedback to perception. We introduce a generic, fully differentiable neuro-soft-symbolic framework that connects visual perception and task planning within a single computational graph. The framework maintains a continuous soft symbolic state, lifts domain rules into a differentiable soft-$T_P$ transition operator, and optimizes action logits over a short planning horizon. Gradients from the planning objective can also update the perception parameters, allowing task-relevant perceptual representations to be refined during planning. On Blocksworld, our method solves 40/40 LatPlan-40 tasks and 596/600 PlanBench-600 tasks, compared with 33/40 for LatPlan and 587/600 for the reasoning-model baseline, while requiring substantially less computation and time. In the perceptual-uncertainty ablation, our method improves the success rate from 59% with frozen perception to 83%. We further conduct task-and-motion simulations on Blocksworld scenes, providing an execution-level validation of the compatibility between decoded task plans and downstream robotic motion execution.

Generative robot policies can represent diverse, multimodal behaviors, but adapting pretrained policies to deployment-time constraints such as collision avoidance and orientation maintenance remains challenging. Existing inference-time steering methods typically apply gradient guidance through iterative diffusion or flow processes, which can be computationally expensive for real-time control. We propose INSPO, which formulates inference-time steering of one-step generative policies as trajectory optimization in the policy's input noise space. By optimizing the input noise while evaluating constraints on the induced state trajectory, INSPO searches the policy-induced behavior space without directly modifying generated actions. The optimization includes a regularization term that encourages solutions to remain consistent with the policy's input distribution and is solved online using population-based particle optimization. We evaluate INSPO on state- and image-based task-specific policies and generalist vision-language-action policies across Push-T, Can pick-and-place, and LIBERO-Spatial. INSPO improves task success and constraint satisfaction over best-of-N sampling and action projection, while comparing favorably with gradient-guided generation at lower runtime.

Robot localization is an ongoing challenge that demands mapping and positioning systems that are tolerant to viewpoint change. Event cameras are attracting increasing interest and adoption in robotics; however, dealing with viewpoint variance is an under-investigated problem in existing event-based localizers. In addition, event-based datasets that emphasize viewpoint variance for challenging localization situations are scarce. Here, we introduce an event-based visual place recognition (VPR) system that performs robustly under viewpoint changes. We converted five large-scale geo-tagged datasets, conventionally used to train frame-based localization systems, into synthetic event streams using Image-to-Event (I2E) conversion, and used them to fine-tune a pre-trained event-based vision transformer backbone with a multi-loss function, yielding a system we call MegaEvent that learns viewpoint-robust features for place recognition. We achieved an average Recall@1 of 82% across three existing event-based localization datasets, leading the next best event-based method by 20 recall points, and frame-based VPR models applied directly to event frames by 8 to 26 recall points. We introduce a new, challenging dataset - Springfield-Event-VPR - which features a 3.7km walking route recorded in three camera orientations for a total of 11.1km, which MegaEvent outperforms the strongest baseline by 9 recall points. The code for MegaEvent is available at https://github.com/AdamDHines/megaevent.

Developers of cybersecurity software often include and rely upon open source software packages in their commercial software products. Before open source code is absorbed into a proprietary product, developers must check the package license to see if the project is permissively licensed, thereby allowing for commercial-friendly inheritance and redistribution. However, there is a risk that the open source package license could be inaccurate due to being silently contaminated with restrictively licensed open source code that may prohibit the sale or confidentiality of commercial derivative work. Contamination of commercial products could lead to expensive remediation costs, damage to the company's reputation, and costly legal fees. In this article, we report on our preliminary analysis of more than 200 open source cybersecurity projects to identify the most frequently used license types and languages and to look for evidence of permissively licensed open source projects that are likely contaminated by restrictive licensed material (i.e., containing commercial-unfriendly code). Our analysis identified restrictive license contamination cases occurring in permissively licensed open source projects. Furthermore, we found a high proportion of code that lacked copyright attribution. We expect that the results of this study will: i) provide managers and developers with an understanding of how contamination can occur, ii) provide open source communities with an understanding on how they can better protect their intellectual property by including licenses and copyright information in their code, and iii) provide entrepreneurs with an understanding of the open source cybersecurity domain in terms of licensing and contamination and how they affect decisions about cybersecurity software architectures.

Automotive Ethernet carries heterogeneous multi-protocol traffic in modern in-vehicle networks, where labeled attack data are rarely available and the strongest prior unsupervised detector still relies on handcrafted traffic features. This article presents X-SPUR, an explainable, surprisal-based, protocol-aware unsupervised reasoning framework that instead represents raw packet fields as token sequences, learns benign traffic patterns through causal language modeling, and detects anomalies from per-token cross-entropy surprisal. To incorporate temporal context, we introduce a bimodal fusion architecture that combines payload-token embeddings with inter-packet timing through additive fusion and a Hadamard interaction. To handle the heterogeneous score distributions of different protocol families, we further propose a dual top-$k$% per-protocol $Z$-score calibration that jointly captures moderately distributed and sparse anomaly signatures. On the TOW-IDS dataset, X-SPUR achieves an AUC of 0.9987. This is marginally higher than the 0.9969 reported for AERO. X-SPUR also eliminates handcrafted feature engineering. We train a separate CarDS model using the same architecture and training hyperparameters. This model retains strong performance on the second automotive Ethernet dataset. Beyond detection, per-token surprisal provides fine-grained explainability by attributing anomaly scores to specific protocol fields, supporting interpretable security analysis in heterogeneous in-vehicle networks.

Vision-language-action (VLA) policies based on flow matching generate action chunks through repeated evaluations of an action expert. Increasing the number of integration steps raises inference cost, but does not necessarily improve closed-loop success. We propose Coda, which reallocates part of this integration budget to a single learned endpoint correction. A frozen policy first completes a few-step noise-to-action trajectory; a lightweight Transformer then predicts a demonstration-supervised residual using the candidate action, source noise, and shared observation-prefix cache. Only the corrector is trained. On 50 RoboTwin Easy tasks, five-step Coda improves success from 71.64% to 74.68% over the matched five-step baseline, while reducing forward latency by 30.2% relative to the default ten-step policy. A two-step configuration achieves 71.88% success with a 2.12$\times$ speedup. An independent 13-task control shows a 5.69-percentage-point gain at nearly equal latency, supporting correction as an effective alternative to additional integration. The same design also improves frozen official SmolVLA, raising two-step success from 60.8% to 69.4%. These results show that endpoint correction improves the quality-latency trade-off of frozen flow-matching policies.

The repeated averages process is a stochastic averaging process on graphs whose mixing time is known for several structured families, but no general sharp expression is known for all connected graphs. It was conjectured that the $L^2\!\to\!L^1$ mixing time is of order $|E|\log n/\lambda_2$. We disprove this conjecture using the graph $G_n$ obtained by attaching one leaf to the complete graph $K_n$. We prove that $\lambda_2(G_n)=1$ and that \[ t_{\varepsilon,2\to1}(G_n)=\Theta_{\varepsilon}(\gamma(G_n))=\Theta_{\varepsilon}(n^2), \] with no additional $\log n$ factor. The example has a strongly localized Fiedler eigenvector: most of its squared $L^2$ mass lies on the leaf, while the balancing mass is spread across the clique.

Cognitive diagnosis infers students' concept mastery from response logs. However, students' responses are not determined by mastery alone: non-cognitive factors such as emotion, engagement, and fatigue can also affect performance. Affective cognitive diagnosis therefore extends conventional cognitive diagnosis by incorporating affective states. Existing methods often assume that the cognitive diagnosis backbone has already explained ability, item, and concept effects, so the remaining errors can be attributed mainly to affect. We argue that this assumption can be insufficient in real educational data: item calibration bias, systematic concept bias, personalized student-concept deviations, and latent student-item matching can form stable cognitive residuals. Without an explicit modeling pathway, these residuals may leak into affective representations, producing affect contamination. To address this problem, we propose an ability-residual decoupled framework for affective cognitive diagnosis. The model first captures unmodeled cognitive residuals through student, item, concept, student-concept, and low-rank student-item components, and then uses an affective module to modulate guess/slip effects. A Q-matrix-constrained concept residual attention mechanism adaptively aggregates only item-relevant concept residuals. Experiments on ASSIST2017, ASSIST2012, ASSIST2009, and Junyi with six cognitive diagnosis backbones show response-prediction gains across the reported comparisons and generally improved affect alignment when affect labels are available. Ablation studies, leakage probes, principal component analysis visualization, long-tail analysis, and case studies further indicate that ability residuals absorb stable cognitive bias, reduce cognitive contamination in the affective branch, and enhance the robustness and predictive accuracy of cognitive diagnosis models.

We give explicit annular normal forms and classify Frobenius structures for $p$-adic Schwarzian equations defined by developing differentials. For a unit of the Robba ring, reduction of order expresses the associated module as a quadratic rank-one twist of a unipotent extension determined by the residue. Frobenius existence is characterized by a square-class condition. At odd primes, there are exactly four differential-module types, and a uniform dominant-monomial hypothesis gives a Frobenius formula in analytic families across the zero-residue locus. For rational nonintegral annular powers, we obtain a diagonal normal form and a congruence criterion at odd primes; both results hold at every prime when the unit factor is an explicit square. Applied to the reducible modular equations $\theta^2y-\ell^2E_4y/144=0$, with $\gcd(\ell,6)=1$, this gives exactly two annular types at every prime and determines the least $s\geq1$ for which Frobenius under $q\mapsto q^{p^s}$ exists. The subfamily $\ell=12n+1$ has a single annular type. Heine–Stieltjes residue cancellation and nondegenerate Jacobi configurations provide explicit examples. We also prove an obstruction to constant projective Frobenius equivariance of Robba-ring developing maps.

Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when it was seen, making it difficult to reuse experience from earlier traversals of an environment. Systems that do reuse such experience usually construct an explicit representation, such as a map or a topological graph, and plan on it. We propose VNT-PA (Visual Navigation Transformer with Pose Attention), a transformer planner whose context is a set of depth keyframes indexed by camera pose. With camera poses as positional encoding, attention depends on the pose differences between keyframes rather than on their temporal order. VNT-PA is trained to imitate a shortest-path planner operating on the ground-truth scene mesh, predicting actions by querying the spatial context with only its current pose and the goal position. On point-goal navigation in HM3D validation scenes, VNT-PA reaches 93.3% success and 90.4% success weighted by path length (SPL), outperforming baselines that encode the same context as a temporal sequence or treat pose as an input feature, in both navigation performance and training efficiency. Because the spatial context is a pose-indexed set, frames from different trajectories can be fused at test time. The planner also degrades more gracefully under localization noise than a conventional baseline which plans on explicit maps. These results show that pose-stamped experience can serve directly as the environment representation for a learned planner, and that making attention depend on pose differences, rather than on temporal order, speeds up training and improves long-horizon navigation.

Collision-free motion planning requires reliable collision models from sensed environments and validation of states along a continuous trajectory. To make this tractable, most planners check for collision at discrete states along continuous trajectories against a single determinized model of the environment, introducing a trade-off between safety and computational efficiency. While continuous collision checking approaches that approximate the swept volume of the robot exist, they are computationally expensive or overly conservative. Data-driven approaches can learn the swept volume; however, these neural models are susceptible to approximation errors and are therefore often limited to serving as coarse filters for downstream collision checkers. In this work, we propose to learn a signed distance function of the swept volume as a probabilistic field, enabling quantification of epistemic uncertainty, incorporation of perception noise, and eventual integration into a chance-constrained trajectory optimization framework. We demonstrate our approach on challenging high-dimensional manipulation problems with significant sensor noise, both in simulation and on real hardware.

In this paper, we completely resolve the two total positivity problems raised by Li [J. High Energy Phys., 2023(7):Paper No. 167, 44 pp., 2023], thereby determining the precise scope of this positivity structure in the one-dimensional conformal bootstrap. First, the Gauss hypergeometric kernel $\mathcal{F}(\Delta,z) = {}_2F_1(\Delta,\Delta;2\Delta;z)$ is proved to be strictly totally positive of order infinity for $\Delta > 0$ and $z \in (0,1)$. Second, the sharp lower $\Delta$-parameter threshold for the associated one-dimensional $SL(2,\mathbb{R})$ conformal block $G_{\Delta}(z) = z^{\Delta}\mathcal{F}(\Delta,z)$ is shown to be $1/2$: the conformal-block kernel $G_{\Delta}(z)$ is strictly totally positive of order infinity for $\Delta \geq 1/2$. For every $\tau \in (0,1/2)$, there exists a strictly negative odd-order minor of $G_{\Delta}(z)$ such that all its $\Delta$-values are in $(\tau,1/2)$ and all its $z$-values can be chosen arbitrarily close to one. Consequently, no restriction $z > z_0$ with $z_0 < 1$ can restore total positivity of order infinity over all $\Delta > 0$.

High-dimensional bipartite entanglement depends on how probability is distributed across the Schmidt spectrum, whereas a single reference-state fidelity resolves only one spectral scale. We develop multiscale Schmidt-spectrum bounds that connect geometric measures with quantitative Schmidt-number witnesses. For any partition of a pure-state Schmidt spectrum, several nested Vidal tails determine block masses. We derive the sharp upper boundary of the associated normalized nuclear-norm coordinate and show that equality holds if and only if the spectrum is uniform within each block. Refining the partition gives a monotone hierarchy of tighter bounds whenever the added tail data distinguish unequal block means. We also solve a relaxed weighted multiscale optimization globally: one scalar parameter specifies its unique full-support optimizer and explicit value on the nontrivial branch. Using the established single-tail fidelity–resource curve as a baseline, we obtain exact-fidelity equality refinements, convex-roof lower bounds for mixed states, and quantitative calibrations of Schmidt-number witnesses. A higher-tail relation further bounds convex-roof extended negativity in terms of Vidal tails and identifies the pure-state equality spectra. Leakage-aware and joint-confidence formulations state how these bounds can be used with incomplete data. Multistep tails require block-resolved or independently certified spectral information; they are not determined by one projector expectation.

Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but they suffer from two coupled pathologies: permissiveness collapse, where pass-rate rewards are maximised by trivial, non-discriminative tests, and concentration bias, where i.i.d. sampled tests cluster on modal inputs and inflate estimator variance. We introduce CoVer (Co-trained Coder and Verifier), a single-policy GRPO framework that addresses both failure modes. First, an information-gain (IG) reward scores each self-generated test by the mutual information between its pass/fail vector and a graded, ground-truth-anchored correctness signal y [0, 1] m, gated by the sign of their covariance so that only positively discriminative tests receive reward. Second, a three-stage diversity-aware selection step prunes a candidate pool to a behaviourally non-redundant suite (invalidity, input-string, execution-profile filtering), raising the effective sample size of the IG estimator at fixed execution budget. On five benchmarks (LiveBench, MBPP, LiveCodeBench, CodeContests, Code-Forces), CoVer raises one-shot pass@1 by +5.8 points at 7B and +7.1 points at 14B over the Qwen2.5-Instruct backbone, and achieves the highest macro-average among all compared methods at both scales. As a drop-in backbone inside the CodeT ranking pipeline, CoVer-7B adds +3.5 points, demonstrating the dual benefit of co-training for both generation and selection.

Procedural anomaly detection in bimanual assembly requires judging each hand action against the execution so far. A corrective action may look unusual in isolation, while a visually plausible action can violate the order of the procedure. We present HACT, a transition model over predicted per-hand events. A role-preserving history keeps the concurrent responsibilities of both hands, and a marked temporal point process assigns each observed transition a semantic and temporal surprisal. A supervised evidence head and a two-state filter convert these surprisals into per-hand anomaly posteriors. A recovery-aware protocol on predicted events and participant-disjoint folds reports the recovery false-positive rate at an operating point selected on validation participants. On two bimanual power-tool procedures HACT has the highest AUPRC and F1 among the compared methods and the fewest recovery alarms. Applied without retraining to a different assembly order of the same product, it retains the highest AUPRC and F1. The source code is available at https://github.com/Kratos-Wen/HACT.

Cooperative and connected automated vehicles (CAVs) rely on Signal Phase and Timing (SPaT) messages to cross signalized intersections; a denial-of-service (DoS) flood that blocks SPaT forces CAVs into a fail-safe mode. Because human-driven vehicles share the intersection, the safety consequence depends not only on the attack and the CAV fail-safe policy, but on how the surrounding human drivers behave. We investigate this human-factors dimension with a coupled OMNeT++/INET (5G NR-V2X) and SUMO microsimulation of a signalized corridor, sweeping CAV market penetration (10-90%), four calibrated driver temperaments (cautious to aggressive) and two standards-based fail-safe policies, a minimal-risk maneuver (MRM) and an adaptive cruise control (ACC) keep-driving fallback, with each attack arm differenced against its policy-matched no-attack baseline. Temperament's effect on the attack is specific and modest rather than a blanket amplification. Aggressive surroundings worsen one metric, the hard-braking a keep-driving fail-safe forces on nearby drivers (p = 0.03), rising from near zero to +8 episodes/1000 veh-s. They appear to dampen rear-end conflicts, but only because the flood clears the queues aggressive drivers build, so the gain is in flow, not safety. On the attack's primary signatures, CAV red-light running and crossing conflicts, temperament has no detectable effect. It instead dominates baseline risk, producing a 13- to 18-fold cautious-to-aggressive gradient far larger than the attack itself, which acts through a channel already congested by CAV adoption. Human driver populations determine how dangerous the intersection is but do not systematically amplify this attack, so fail-safe design cannot assume a cautious test population bounds the risk.

Pulse interventions represent a highly effective measure for infection control, as they influence disease transmission through short-term actions. In addition, the habitat ranges of dengue vectors and hosts exhibit periodic variations driven by environmental and climatic factors. To investigate the effects of impulsive interventions and domain evolution on disease transmission, we propose a dengue fever reaction-diffusion model that incorporates impulsive perturbations in a periodically varying domain. By applying the Poincar$\acute{e}$ map and the Krein-Rutman theorem, we establish the existence of the principal eigenvalue for the periodic eigenvalue problem with impulses, thereby extending previous studies on reaction-diffusion equations in fixed domains without impulsive effects. Sufficient conditions governing the long-term dynamics of periodic solutions are derived using the comparison principle and monotone iteration theory. Numerical simulations corroborate the theoretical findings and elucidate the effects of impulsive-intervention intensity and periodic domain evolution on disease transmission patterns. Our results indicate that increasing the intensity of pulse interventions suppresses disease transmission, whereas a larger magnitude of domain variation impedes disease control.

Soft materials linked by reversible covalent or supramolecular bonds form a diverse class of assemblies with promising applications from nanoscience to medicine. Experiments typically probe bulk phase behavior and rheology, but it remains difficult to measure how microscopic bonding kinetics and the mechanics of the constituent elements give rise to bulk properties. Coarse-grained molecular dynamics (MD) simulations can bridge these scales, but most simulation approaches do not control individual bond kinetics, and those that do were mostly developed for bespoke applications that do not readily generalize. Here we present pySNAP (Simulation and Network Assembly Pipelines), a modular open source Python platform that integrates tunable dynamic bonding with a workflow, template, and analysis setup, so that users can study a wide range of systems with only small changes to input files. The platform is built on the GPU-accelerated HOOMD-blue MD engine and integrates DyBond, a GPU-accelerated plugin that forms and breaks bonds consistent with an equilibrium distribution and supports bonding between multiple types of partner species. Around this core, the snap_simulate package compiles a directory of parameter files into a HOOMD-blue simulation, and the snap_workflow package orchestrates the resulting parameter sweeps across workstations and high-performance computing schedulers. We describe the theory behind simulated dynamic bonding and how to use the package, from setting up a parameter sweep to analyzing its results, and demonstrate the framework on a diverse range of dynamically bonded systems, showing that it accommodates distinct interaction mechanisms, geometries, and physical scenarios within a unified workflow, while enabling both reproduction of existing models and rapid construction of more complex composite systems.

Code edits that preserve program behaviour can shift frozen code embeddings across classifier decision boundaries, causing correctly detected vulnerabilities to be predicted as benign. Such instability is problematic because semantically neutral changes, including comment removal, insertion of unreachable code, variable renaming, and loop rewriting, should not alter a model's security judgment. We investigate this issue using 15,000 C/C++ functions organized as 7,500 vulnerable-patched pairs from the Big-Vul dataset. Four mutation tracks are applied to both vulnerable and benign samples: comment removal, unreachable code insertion, variable renaming, loop rewriting, and a combined setting that applies all transformations. Using frozen microsoft/codebert-base embeddings with six downstream classifiers, we evaluate the robustness of vulnerability predictions and introduce a train-only defence that projects clean and mutated representations closer together while preserving vulnerability-class information. Under combined mutations, the baseline Vulnerable Flip Rate (VFR) ranges from 35.55% to 42.15%. The proposed defence reduces the mean common-set VFR from 22.60% to 11.32% and improves mean mutated accuracy from 55.33% to 57.10%. For Logistic Regression, VFR decreases by 17.29 percentage points, although benign-to-vulnerable flips increase by 11.95 percentage points. These results indicate that the defence improves robustness to semantics-preserving code transformations but introduces a false-positive trade-off and does not fully eliminate prediction instability.

We present a neural network (NN) basis-selection method for large-scale relativistic configuration interaction (RCI) calculations in GRASPG. The method employs configuration state function generators (CSFGs), each of which generates a set of configuration state functions (CSFs) with the same spin-angular couplings, as the basic selection units for the NN. A constant-orbital feature-elimination strategy removes feature channels whose values remain unchanged across the CSFG pool. The CSFG representation reduces the number of learning units processed by the NN by more than one order of magnitude, while constant-orbital feature elimination further reduces the dimensionality of the NN input. Combined with the high-performance GRASPG framework, the method improves the efficiency of both NN selection and subsequent RCI calculations, maintaining a balance between accuracy and computational cost. In a moderate Ni(12+) benchmark, where the corresponding full-space RCI calculation is still feasible, the CSFs generated by the retained CSFG sets reproduce the full-space RCI results at the few inverse-centimeter level for the target states. For the representative J = 0, even-parity block, the complete workflow reduces the wall time by 75.6 percent, and the peak memory required by a single RCI calculation is reduced by a factor of 10.1. In a larger-scale calculation with a full CSF expansion containing 1.27 x 10^9 CSFs, the method retains only 1.1-1.9 percent of the full-space CSFs and yields energy levels in good agreement with experimental data and other resource-intensive theoretical calculations.

Phase-field models provide a versatile framework for simulating fracture nucleation and propagation without explicit crack tracking. Their principal computational challenge is the need to resolve a small regularization length with a sufficiently fine finite element mesh. This requirement can render uniform-mesh simulations prohibitively expensive, particularly for three-dimensional problems, problems involving distributed crack nucleation, and soft nearly incompressible materials. Adaptive mesh refinement offers a natural means of reducing this cost, but existing approaches often rely on heuristic refinement indicators, are primarily designed for problems containing pre-existing cracks, and retain increasingly large refined regions as cracks grow in size. This work presents an adaptive mesh coarsening framework along with adaptive mesh refinement for phase-field fracture. The coarsening strategy replaces the fractured region in the crack wake with a coarse crack band that preserves the essential mechanical behavior of a crack, making it necessary to have a refined mesh only in a small region near the tip of the growing crack. The method introduces a physics-based refinement indicator derived from the violation of the material strength surface, which is a necessary condition for fracture evolution. The indicator therefore robustly identifies regions where crack nucleation or propagation is imminent and can be applied across arbitrary materials, geometries, and loading conditions. The framework is implemented in parallel within FEniCSx; the supporting finite element codes are made available. Its generality and substantial computational benefit are demonstrated through benchmark problems involving crack propagation and nucleation under quasi-static and dynamic loading, for soft and hard materials, and for thermomechanical fracture.

We determine the generalized and local derivations of the mirror Heisenberg-Virasoro algebra. As a by-product, we give a complete characterization of $\delta$-(bi)derivations.

Manga is a comic drawn by black and white paints gaining popularity around the world. Onomatopoeia in Manga specifically appeals to the audience with its unique visual styles, which convey sound, motion, and emotion. Visual onomatopoeia translation requires the clean replacement of Japanese onomatopoeia with onomatopoeia in the other language while preserving their visual style. Existing approaches often produce residual artifacts or style inconsistency when removing the Japanese onomatopoeia and rendering stylized English onomatopoeia. To approach these problems, we present OnomatoBridge, a filtering pipeline for visual onomatopoeia translation. We evaluate OnomatoBridge from Japanese to English on the Manga109 onomatopoeia dataset and compare it with baseline image editing models. Experimental results show that the filtered outputs by the proposed method outperform those of conventional methods. OnomatoBridge improves English text correctness by roughly 10 to 25 points and reduces residual Japanese text by about 20 to 50% in relative terms.

Chirality-induced spin selectivity (CISS) is usually associated with molecular handedness. The possible contribution of chiral phonons is less established. We study a helical tight-binding model in which local phonon angular momentum modulates spin-dependent nearest-neighbor hopping. Fewest-switches surface hopping calculations give the transmitted spin polarization $\mathrm{SP}=aC+b\mathrm{PH}$. Here $C$ is the molecular chirality and $\mathrm{PH}$ is the phonon chirality. A mirror symmetry reverses $C$, $\mathrm{PH}$, and $\mathrm{SP}$ simultaneously. This symmetry excludes both a chirality-independent offset and a $C\cdot\mathrm{PH}$ term. The phonon contribution can therefore enhance, cancel, or reverse the molecular CISS signal.

Sparse longitudinal CT follow-up limits lesion-size forecasting when only a few prior observations are available. We constructed a five-visit DLT-derived same-lesion trajectory benchmark from DeepLesion and Deep Lesion Tracker (DLT), yielding 205 trajectories from 129 patients. We compared an exploratory conventional sparse-to-final analysis with a primary fixed visit-index horizon design predicting the common log change from T3 to T4 while progressively adding earlier observations, evaluating predictive accuracy, uncertainty reliability, post-hoc conformal interval calibration, subgroup performance, and Gompertz-inspired trajectory regularization. The evaluated methods showed partially overlapping point-prediction accuracy but distinct uncertainty behavior. Mean held-out RMSE across ten training seeds was 0.4726, 0.4305, 0.4499, and 0.4513 for m = 1, 2, 3, 4, indicating the lowest mean RMSE at m = 2; additional history did not improve RMSE. At m = 4, raw Cohort-Level Feature GP coverage was near the 95% nominal level, whereas MC Dropout, Deep Ensemble, and residual-scale intervals were conservative. Patient-level conformal calibration generally produced near-nominal or conservative coverage at the cost of wider intervals. Patient-grouped development cross-validation selected lambda* = 0 for the Gompertz-inspired term. A global population reference frequently opposed lesion-level change directions, and prediction difficulty varied across anatomical subgroups. Overall, additional historical observations provided limited predictive benefit once the prediction horizon was controlled, while predictive accuracy, uncertainty reliability, and trajectory consistency did not necessarily improve together, and should be evaluated jointly in sparse longitudinal imaging.

The scotogenic model offers an attractive framework that explains light neutrino masses while accommodating a viable dark matter candidate. In this work, we study the phenomenology of singlet fermion dark matter, $N_1$, produced via the freeze-in mechanism characterized by an instantaneous low reheating temperature, $T_{\text{rh}}$. We explore the model's viable parameter space, incorporating current bounds from lepton flavor violation ($\mu \to e \gamma$) and direct detection limits. We show that low-reheating scenarios significantly reshape the viable region for $N_1$ dark matter, improving prospects for testing the scotogenic model in the FIMP scenario while keeping it consistent with current lepton flavor violation and cosmological bounds.

Let $S(Q,M,N,(a_n))=\sum_{q\le Q}\sum_{a\bmod q^2,(a,q)=1}|\sum_{M<n\le M+N}a_ne(an/q^2)|^2$ be Zhao's large sieve sum with square moduli. Zhao conjectured that $S\ll(QN)^\epsilon(Q^3+N)\sum|a_n|^2$. The bound of Baier and Zhao (2008) exceeds this conjecture by a factor which reaches $Q^{1/2}$ at the critical point $N=Q^3$, and there the exponent $1/2$ has not been lowered since. We prove that, under Hooley's Hypothesis $R^*$ for short Salié sums, $S\ll(QN)^\epsilon(Q^3+N+Q^{4/3}N^{2/3})\sum|a_n|^2$. This replaces the excess over Zhao's conjecture by its $2/3$-th power throughout the range $Q^{5/2}<N<Q^4$; at $N=Q^3$ it gives $S\ll Q^{1/2-1/6+\epsilon}N\sum|a_n|^2$. The proof is short. Following Zhao's original treatment, we approximate the point under consideration by fractions $b/r$ with denominators up to $Q^{2/3}N^{1/3}$, which for $N<Q^4$ is beyond the customary $\sqrt{N}$. If the approximation is poor, an elementary count suffices. If it is good, the analytic part of the problem disappears: after Poisson summation in both variables the count is expressed through quadratic Gauss sums, and their exact evaluation at every modulus turns the sum over the dual variable into short Kloosterman and Salié sums, to which Hypothesis $R^*$ applies and gives the square root of the elementary count. At odd moduli the hypothesis is needed only in the form of Conjecture (C*) of Friedlander and Iwaniec. The Gauss-sum evaluations, including even moduli and coefficients sharing a factor with the modulus, are proved in full. This version supersedes earlier versions, which obtained the exponent $1/2-1/28$ at $N=Q^3$ by a much longer route through sums of modular square roots. The paper was prepared in collaboration with Claude (Anthropic).

Generative AI can improve students' programming performance, but successful task completion may not reflect what they retain. We examined performance, retention, cognitive load, and ownership in a controlled between-subjects experiment with 59 undergraduate computer science students, 55 were retained for analysis. Participants completed three introductory C programming tasks with access to ChatGPT-4.5 or conventional web search without generative AI. We measured task performance, self-reported mental effort and difficulty, pupillary responses, heart rate variability, and ownership, and assessed cued recall immediately and 48 hours later. ChatGPT-assisted students achieved higher coding scores (89% vs. 69%) but lower recall scores immediately (41% vs. 53%) and after 48 hours (39% vs. 52%). There was no significant difference in the loss of recall information over 48 hours between the groups. Self-reported mental effort increased less across tasks in the ChatGPT condition (Holm-adjusted p = .047), and students attributed less of the submitted code to themselves (45% vs. 81%). Confirmatory physiological tests did not detect significant differences in trajectories between conditions; substantial data loss limits their interpretation. These findings reveal a gap between assisted task performance and subsequent recall and sense of ownership in this setting. They motivate the need for assessment practices and AI learning tools that require students to explain, retrieve, and contribute to the work they submit as active participants in their education.