Papers

Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattered-light-free biomedical ground truth is often unavailable; second, scattering is coupled with weak illumination and sensor-induced noise; and third, many learning-based restoration models are computationally expensive for embedded devices in Internet of Medical Things (IoMT) scenarios. To address these issues, this paper proposes PP-Net, a hybrid physical-prior neural network for biomedical scattered light removal. The proposed method consists of three components: DFN-Net suppresses sensor-induced noise, ASAP estimates the scattering map and recovers a physics-based prior map, and GF-Net refines the prior map by fusing it with the denoised observation. To reduce the dependence on paired biomedical ground truth, a progressive synthetic training and cross-domain transfer strategy is developed. Experiments show that the physical-prior branch improves the peak signal-to-noise ratio (PSNR) by up to 1.26 dB on paired synthetic benchmarks. Under joint noise-and-scattering degradation, PP-Net improves PSNR by more than 10.8 dB and the structural similarity index measure (SSIM) by more than 0.62 compared with representative baseline methods. On real W2S biomedical images, the proposed method reduces the average Natural Image Quality Evaluator (NIQE) score by 43.3%. Edge deployment with RKNN conversion and INT8 quantization achieves an average inference latency of approximately 200 ms per $512\times512$ image over 360 test images. These results demonstrate that PP-Net provides an effective and deployable solution for microscopic imaging, endoscopic inspection, and edge-assisted biomedical analysis in IoMT scenarios.

The theory of the basic reproduction ratio $R_0$ is established for the almost periodic non-densely defined Cauchy problems. Firstly, we present some dynamical properties of the linear almost periodic non-densely defined Cauchy problems. Then we define the evolution semigroups on the space of almost periodic functions, investigate their infinitesimal generators and define the basic reproduction ratio $R_0$. Finally, our developed theory is applied to age-structured models and functional differential systems.

Galaxy asymmetry is an efficient way to characterize galaxy morphology in atomic hydrogen 21 cm emission detections. We propose a novel Bayesian approach to calculate the probability of an underlying squared differences asymmetry in a noisy detection. This approach has a number of advantages, including the recovery of low asymmetry values where prior noise corrections failed. More importantly, our approach provides robust uncertainties on the asymmetry, enabling a wide variety of statistical studies of galaxy populations. This method is generalized for convolved noise measures. We validate our method using a convergence test. Finally, we show how, when applied to the untargeted HI survey WALLABY, our method nearly triples the number of reliable measurements relatively to the previous state-of-the-art technique. This Bayesian approach to measure asymmetry will therefore further unlock the statistical power of widefield galaxy surveys.

As an extension of the It^o-Michler theorem to the nonabelian or nonnormal Sylow subgroups, A. Moreto raised the following conjecture: let G be a finite group and P a Sylow p-subgroup of G. Then the number of irreducible characters of G whose degrees are divisible by p is not less than the length of any subgroup chain between N_G(P) and G. In this short note, we give a counterexample to this conjecture.

Ensuring safety and scalability in Collective Perception Service (CPS) remains a key challenge for Cooperative Intelligent Transport Systems (C-ITS). Conventional CPS enhances perception by broadcasting Collective Perception Messages (CPMs). However, its reliance on transmitting a potentially large volume of context-irrelevant information at high frequency leads to network congestion, processing delays, and poor scalability. We propose a Context-Aware Adaptive Filter that dynamically adjusts CPM content and transmission frequency based on contextual relevance and situational criticality. By prioritizing safety-critical objects and interactions, the proposed approach prevents information overload while preserving timely updates for decision-making. An end-to-end SUMO–Artery simulation evaluates safety, decision-making efficiency, and communication cost under different computational capacity tiers and transmission rates. Results show that the proposed adaptive filtering mechanism achieves safety performance comparable to conventional CPMs transmitted at the maximum allowed frequency (10~Hz), while reducing communication volume by over 93% and preventing queue saturation. This demonstrates that context-aware adaptivity enables CPS to remain both scalable and safety-compliant across heterogeneous computing platforms.

Myelin membranes are tightly connected to the axon, forming an electrical route for rapid saltatory conduction of action potentials from node to node. Beneath the myelin, adjacent to the node, lie voltage-gated potassium (K$^+$) channels, whose fundamental role in conduction remains poorly understood. Constrained by biological data, we developed a finite element model of a node of Ranvier encompassing an adaxonal membrane separating oligodendrocyte cytoplasm from the periaxonal space, and solved the full coupled set of physical equations governing electrodiffusion and voltage profiles at the nanoscale. Remarkably, we find that nodal action potentials invert at the inner adaxonal myelin membrane. The hyperpolarization-driven opening of myelinic Kir4.1 channels produces an instantaneous, powerful K$^+$ prebuffering, clamping the periaxonal K$^+$ concentration and enabling high-frequency action potential generation. Together, these findings indicate that the periaxon maintains an electrical feedback loop with the node, and suggest a key evolutionary advantage of juxtaparanodal K$^+$ channel positioning.

A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence calibration metrics target binary or multi-class tasks, while multi-label calibration remains largely underexplored. Multi-label classification tasks, such as assigning medical codes to clinical notes or determining news topics, are usually dominated by a large number of negatives, i.e., labels that do not apply. We show that existing binning schemes to compute label-wise expected calibration error either underestimate the error, simply reflect label frequency, or suffer from many bins with very few instances. To achieve trustworthy label-wise calibration errors, we propose a new binning scheme that gives equal weight to positive and negative label assignments. Our empirical study demonstrates that in contrast to existing binning schemes, our new scheme results in meaningful estimates of calibration error in hierarchical and in extreme multi-label classification. We also show that calibrating confidence scores of large language models for multi-label predictions is an open challenge. Our detailed analysis lays the foundation for further research by providing a solid evaluation metric for measuring calibration in multi-label classification.

Vision-language-action (VLA) models often struggle in the precision-critical phases of multi-stage manipulation tasks. To mitigate this issue, VLA models can be used in conjunction with reinforcement learning (RL) specialists that are specifically trained to handle the precision-critical phases. However, the coordination between the base VLA model and the RL specialists, which dictates when a specialist should take over from the base VLA and vice-versa, remains an open research question. In this paper, we address this gap by introducing RouteRLT, a modular framework that coordinates a generalist VLA, used as the default controller, with designated precision-critical RL specialists. At a high level, our framework trains a phase-aware coordination mechanism that handles handoffs between the generalist and the specialists. We evaluate RouteRLT on the LIBERO and LIBERO-Plus benchmarks, as well as on a physical connector pickup and insertion task. Overall, we find that RouteRLT improves success on LIBERO, and retains net gains on LIBERO-Plus. On the physical task, RouteRLT completes 65.7% of trials, compared with 8.6% for the baseline. Altogether, these results demonstrate that learned coordination builds on generalist VLA capabilities to improve task completion in precision-critical manipulation.

We present a multi-epoch Very Long Baseline Array (VLBA) survey of radio sources in the Orion Nebula Cluster (ONC), updating the detection statistics and investigating inter-epoch variability. The dataset comprises eight C-band (4-8 GHz) epochs targeting 575 radio sources previously identified in deep Very Large Array surveys. VLBA observations result in resolutions of milliarcseconds and are only sensitive to high brightness temperatures meaning only non-thermal emission is observed. We detect 226 unique radio sources corresponding to a detection fraction of 39 per cent. The majority of sources (~83 per cent) are detected only once indicating that non-thermal emission associated with Young Stellar Objects (YSOs) is highly intermittent. To quantify variability, we use per-epoch peak flux densities and the variability factor (VF) defined as the ratio between the maximum and minimum fluxes. We identify 21 sources (~9 per cent of detected sources) that exhibit high variability defined as a change of flux density by at least a factor of five. We crossmatch with the COUP Chandra survey to identify sources as YSOs. We identify COUP counterparts for ~56 per cent of the detected sources. The remaining population cannot be explained solely by variability or background contamination, suggesting a population of radio detected YSOs without X-ray counterparts. We find a clear correlation between radio and X-ray luminosities consistent with the Güdel-Benz relation, the empirical relation between non-thermal radio and thermal X-ray emission for magnetically active stars.

Let $\Gamma$ be a coalgebra over a field. There is a well-known covariant embedding of the category of graded $\Gamma$-comodules into the category of graded modules over the dual algebra $\Gamma^*$. We show that this covariant embedding preserves Ext-groups in a range of motivating cases, including in some cases like Steenrod algebras where the covariant embedding has otherwise bad homological properties and fails to preserve Ext-groups on the underlying ungraded categories. As an application, we prove the old conjecture in stable homotopy theory that there are no nonzero projectives in the category of graded comodules over the dual Steenrod algebra. As another application, we carry out a study of the right adjoint to the extended comodule functor, including a topological interpretation of this right adjoint. This yields generalizations of formulas of Margolis and Lin characterizing maps from Eilenberg-Mac Lane spectra into finite-type bounded-below spectra; our generalizations drop the "finite-type" hypothesis.

Many numerical invariants of a finite group arise as the multiplicity of the trivial character in a naturally associated class function, and the remaining multiplicities carry finer structural information. For the number of conjugacy classes of elements whose order involves only a chosen set of primes, the natural such class function is a generalized character interpolating between the classical conjugating character and the regular character. We prove that it is a character in two important general cases, obtained independently by Robinson, and we rule out a family of groups and characters in which, we argue, a counterexample would be most likely to arise. Furthermore, we characterize when these class functions are compatible with passing to a subgroup and thereby sharpen a theorem of Sangroniz. The analogous class function for real elements is shown to always give a character. Finally, we give a dual construction that, together with the recently proved McKay Conjecture, yields a best-possible criterion for a finite group to have an abelian Sylow $p$-subgroup.

Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and radiomics-only variants, indicating complementary contributions from radiomics and image representations. These findings suggest that radiomics remains relevant for RCC CT classification in the presence of foundation representations, and that its integration with MedVAE is more effective in the 3D setting. More broadly, the study supports a complementary role for radiomics and foundation representations in clinically meaningful imaging decision support.

Driven-dissipative many-body quantum systems can be exploited in quantum enhanced sensing protocols. Here, non-classical correlations may allow one to reach a measurement precision that surpasses the standard quantum limit. The relevant figure of merit for assessing such quantum advantage is the quantum Fisher information (QFI). In a many-body setting its computation is challenging as it requires knowledge of the full system-environment state. Here we make use of a field-theoretical approach, which is particularly well suited for systems with many degrees of freedom. In particular, we exploit that the QFI can be linked to a Keldysh path-integral. This route leads to a semiclassical expression of the QFI, which is obtained through a controlled expansion in the so-called quantum fields. We benchmark the framework on three systems of increasing complexity: the driven-dissipative harmonic oscillator, the boundary time crystal - which becomes semiclassical at large system sizes - and a two-dimensional array of collectively emitting atoms. We assess in which parameter regimes the semiclassical description holds and gives access to system sizes beyond the reach of exact methods.

Pseudorandom number generators (PRNGs) constitute indispensable computational tools across multiple scientific domains, including Monte Carlo simulations, stochastic computing, and artificial intelligence (AI). The reproducibility of such applications critically depends on the ability of PRNG implementations to generate identical sequences across software environments when initialized from the same internal state. These algorithms enable the simulation of stochastic processes while providing deterministic and repeatable behaviour, thereby facilitating reproducible experiments. Modern PRNG implementations may be initialized through either a seed or, more accurately, an initial state that exceeds the capacity of a conventional integer seed. However, reliance on a simple seed alone frequently proves insufficient to ensure consistent program execution traces across different implementations. A natural assumption is that transferring the complete internal state of a generator should guarantee identical outputs regardless of the software library used. This study examines the validity of this assumption by investigating whether complete initial states can ensure cross-library fidelity and portability of PRNG streams. We focus on two widely deployed generators, Mersenne Twister and Philox, and evaluate their implementations across four major Python ecosystems-Random, NumPy, PyTorch, and TensorFlow. We compare the sequences produced by these implementations against those generated by the original reference algorithms under identical initialization conditions. Our results demonstrate that reproducibility cannot be assumed from PRNG state transfer alone, even when implementations claim to follow the same underlying algorithm. While fidelity was successfully achieved for several implementations, significant discrepancies were observed in others. Most notably, the Philox implementation in PyTorch exhibits fundamental incompatibilities with the reference algorithm, preventing exact reproduction of generator outputs across environments. These findings challenge the common expectation that access to a full internal state of a PRNG is sufficient to ensure reproducibility across software stacks. They further highlight that implementation-specific design choices can introduce hidden barriers to experimental replication, particularly in AI workflows that rely on multiple frameworks. This work shows that implementation fidelity of a PRNG is a necessary condition for scientific reproducibility and makes two primary contributions. First, it identifies practical guidelines for achieving reliable PRNG usage and reproducibility within the Python scientific and AI ecosystem. Second, it evaluates the extent to which cross-library portability and fidelity can be recovered through user-level techniques, without requiring modifications to library source code.

Anomaly detection systems are often trained using normal data alone, while model selection and evaluation typically require labeled anomalies. We study whether anomaly detection performance can be predicted without access to anomalous data. For kNN-based detectors, we derive a lower bound on the area under the ROC curve (AUC) that relates detection performance to the separation between inlier and outlier scores and to their respective variances. Under a local scaling model, we use this bound to characterize how density variation, intrinsic-dimensional heterogeneity, and cross-domain mismatch contribute to score variability. We then investigate anomaly-free model selection and show that inlier score variance alone does not reliably predict performance across different representations. To address this limitation, we introduce simple pseudo-anomaly probes that provide a reference for estimating relative score separation. Experiments on the DCASE 2022-2025 benchmarks, spanning four embedding models and 208 candidate systems, show that pseudo-anomaly-based estimators substantially improve anomaly-free model selection. In particular, diverse pseudo-anomalies enable anomaly-free model selection to outperform conventional development-set selection under domain shift. These results show that embedding-space geometry contains predictive information about anomaly detection performance while also highlighting the representation-dependent nature of inlier-only performance estimates.

Gaussian random fields are a versatile tool used in the fields of stochastic PDEs, uncertainty quantification, and geostatistical simulation. One way to obtain them is to use a truncated Karhunen-Loève expansion (KLE). Computing the expansion requires the leading eigenpairs of an $N \times N$ covariance matrix, where $N$ is the total number of grid cells. These are usually computed with a Krylov eigensolver, which relies on the covariance operator only within matrix-vector products. Stored densely, the matrix takes $\mathcal{O}(N^{2})$ memory and each product $\mathcal{O}(N^{2})$ time. For a stationary kernel on an equispaced grid, the covariance matrix becomes (block-) Toeplitz and the product evaluates in $\mathcal{O}(N\log N)$ time using FFT-based circulant embedding, without the need to assemble the dense matrix. In a matched single-threaded comparison, the median speedup of the eigensolve grows from $18 \times$ at $N = 4096$ to $183 \times$ at $N = 2^{15}$. This makes it possible to compute discretized fields that would otherwise be infeasible to compute in the standard formulation. We show that the same construction carries over to non-separable kernels as well as $d$ dimensions, using block-Toeplitz matrices. We extend it to piecewise-constant fields on arbitrary domains given as subsets of a tensor grid. Computational savings grow with problem size, and storage drops from $\mathcal{O}(N^{2})$ to $\mathcal{O}(2^{d}N)$.

We introduce CoDeR, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual observations, our system explicitly constructs an executable world with code and employs video generation models for visual realization. Specifically, we coordinate five complementary roles to translate high-level concepts into structured world rules, executable dynamics, and perceptual observations. This design enables long-term memory, open-ended interactions, autonomous world evolution, and multi-agent scenarios, where multiple entities can act, interact, and evolve persistently beyond the current observation. Extensive experiments demonstrate that our framework substantially extends the capabilities of existing world models, enabling long-term memory, open-ended interactions, autonomous evolution, and persistent multi-agent dynamics, while achieving state-of-the-art performance across multiple evaluation settings. Code and model weights will be made publicly available. Project Page: \href{https://becauseimbatman0.github.io/CoDeR}{CoDeR}.

AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to optimizing inference. A natural next step is to improve the research efficiency of the agents themselves. When an AI research agent's own code is the object of optimization, each accepted rewrite becomes the agent that the next round edits. We refer to this loop as recursive self-improvement. Its significance lies in a long-standing trend, in which increased cumulative spending on R&D yields diminishing returns. Sustained self-improvement offers a way to counter this trend. We present AIDE^2, a system that implements this loop for a frontier AI research agent. It proposes changes to its own code, benchmarks modified versions of itself on a suite of AI R&D tasks, and keeps the changes that perform best on hidden evaluations. In an autonomous 8-day run, AIDE^2 discovered seven successive improvements, ranging from a new search policy to memory mechanisms that compress and manage the agent's growing context. These gains generalize to four held-out benchmarks spanning machine learning engineering, heuristic algorithm engineering, and physics-based weather forecasting, the last of which is out of distribution from the selection tasks. On all four, the strongest discovered agent matches or exceeds a human-engineered production research agent that ranks among the strongest on FML-Bench. On a separate held-out task family, the discovered agents also exhibit reduced reward hacking, a property the loop never explicitly optimized for: the rate falls from 55% to 32% during the run, 7 percentage points below the human-engineered agent. Together, these results show that an AI research agent can improve its own research efficiency through recursive self-improvement, and that these gains transfer to tasks and domains the loop never encountered.

We prove the existence of rogue waves and breathers in nonlinear lattice wave equations including the nonlinear Klein–Gordon and the FPUT lattice (with added local forces). The main feature of our lattice wave equation is that the kinetic part $\frac{\mathrm{d}^2}{\mathrm{d}t^2}$ is multiplied by a non-constant function $\frac{1}{d(t)}$ such that gaps in the spectrum of $\frac{1}{d(t)}\frac{\mathrm{d}^2}{\mathrm{d}t^2}$ open wide enough to include the spectrum of the spatial linear operator. We find solutions as critical points of an indefinite functional using a saddle-point method combined with concentration-compactness arguments. In case of temporally $T$-periodic coefficients and under identical assumptions as for rogue waves, the same variational method also provides existence of breather solutions whose temporal period is an arbitrary prescribed integer multiple of $T$.

In this paper, we prove the optimal diameter estimate for positive Yamabe metrics on a connected, closed manifold. It is a scalar curvature version of both classical Myers' diameter estimate and Cheng's maximal diameter theorem on Ricci curvature.

Seismic velocity model building (VMB) is fundamental for understanding subsurface structures. Traditional methods demand high-quality starting models and, also, remain limited in resolution in coverage and computationally intensive. Recent generative diffusion model-based approaches capture statistical priors to support traditional inversion methods, but these approaches do not account for the top to bottom progression of information (layer stripping) involved in surface recorded data, where deep velocity information depends on the shallow. To address this issue, we propose a depth-progressive diffusion framework that constructs velocity models incrementally from shallow to deep by propagating prior information. Our method trains on paired shallow-deep velocity patches with variable overlap and explicit depth encoding, integrating multiple geophysical constraints including well logs and seismic images (representing structural information). During inference, we synthesize overlapping depth slices using a progressive algorithm and merge them with Gaussian-weighted blending to eliminate boundary artifacts. This approach leverages both learned geological distributions and observed shallow priors while providing uncertainty quantification. Extensive numerical experiments on in-distribution tests and an out-of-distribution test demonstrate excellent VMB accuracy with a strong correlation between predicted uncertainty and actual errors. As a proof of concept, this part I employs idealized structural constraints derived from vertical reflectivity to validate the methodological framework. The companion paper (Part II) extends the approach to realistic structural constraints relying on migrated images with field data applications.

Strong-to-weak spontaneous symmetry breaking (SWSSB) can occur in a maximally mixed charge sector even when ordinary charged correlations vanish. We study this order when a charge sector splits into dynamically disconnected fragments. In a one-dimensional $t$-$J_z$ chain with species-resolved dephasing, each fragment is labeled by a conserved spin word. A charged transfer between separated finite intervals preserves that word only if the intervening spins satisfy a periodicity constraint. In the full-state two-point sense, we use this constraint to prove the absence of long-range fidelity and Rényi-1 order in typical fixed-composition fragments, uniformly over all norm-bounded charged operators in any prescribed finite interval. A fragment with primitive spin-word period $k$ supports a $k$-particle channel with exact long-distance value $\nu^k(1-\nu)^k/k^2$, and no charged operator on fewer than $k$ sites can carry this order. A transverse exchange connects the fragments while preserving the global charges and restores the full-sector steady state at finite size. The conserved spin word therefore selects the local channels that can support mixed-state order.

Suppose that a discrete group $G$ acts smoothly, properly, and effectively on a connected smooth manifold $M$, and let $q:M\to M/G$ be the quotient map. We prove that if $q$ admits a continuous section, then $G$ is generated by reflections. We also establish converse results for dissecting reflections and give applications to Euclidean and lattice actions.

For positive integers \(m,n\), let \[ A_{m,n}=(\{1,\ldots,m\}\times\Z_n)\cup\{0\} \] have flat addition and multiplication truncated at degree \(m\). We prove that \(A_{m,n}\) is finitely based exactly when \(m\le 2\) or \((m,n)=(3,1)\). Explicit finite bases are supplied throughout this region. Outside it, high-girth hypergraphs with a constant-sum rigidity property yield finite countermodels to every bounded-variable fragment of the equational theory. The proof places no divisibility or coprimality restriction on the parameters.

We construct infinitely many pairwise non-diffeomorphic irreducible smooth four-manifolds homeomorphic to ${\mathbb {CP}}^2\# 7{\overline {\mathbb {C}} {\mathbb {P}} } ^2$, each admitting a free, orientation-preserving involution. Their quotients give infinitely many irreducible definite four-manifolds with fundamental group ${\mathbb {Z}}/2 {\mathbb {Z}}$ and $b_2=3$, filling the corresponding gap in the geography of such examples. The construction of infinitely many distinct examples relies on a novel equivariant torus surgery.

We report the first measurements of two-particle transverse momentum correlations for mid-rapidity charged particles in Au+Au collisions at $\sqrt{s_{\rm NN}} =$ 3.0, 3.2, 3.5, 3.9, 4.5, 5.2 and 7.7 GeV recorded by the STAR experiment. The results are compared with previous STAR measurements from the Beam Energy Scan Phase I (BES-I) and with transport model calculations. The measured two-particle $p_{\rm T}$ correlators exhibit an approximate power-law scaling with the number of participating nucleons ($N_{\rm part}$), consistent with expectations from an independent-source scenario. This scaling is least well described at the lowest collision energy, $\sqrt{s_{\rm NN}} = 3.0$~GeV. Furthermore, a non-monotonic energy dependence of the $p_{\rm T}$ correlations is observed in central collisions, representing the first systematic observation of such behavior as a function of collision energy.

Secure multiparty computation (MPC) enables mutually distrustful parties to compute on private digital inputs. We initiate the study of spatiotemporal MPC, extending this paradigm to functionalities whose inputs additionally depend on physical facts such as the parties' locations, times, or trajectories. Such protocols must simultaneously hide spatiotemporal information and ensure its physical consistency: a malicious party should not be able to make the functionality operate on a spatiotemporal input inconsistent with its actual physical state. The main conceptual challenge is to formulate extraction of spatiotemporal information within the simulation-based security framework. We introduce arguments of spatiotemporal knowledge, following the principle "I prove, therefore I am:" rather than defining physical presence directly through a mathematical relation, we define it operationally through the ability to complete a sound spatiotemporal verification protocol. Accordingly, an extractor recovers a spatiotemporal point from a successful prover and certifies its physical validity by using the extracted prover to succeed in an auxiliary spatiotemporal verification protocol. Building on this notion, we define universally composable (UC) security for spatiotemporal MPC, capturing privacy, physical consistency, and composability. We provide constructions achieving this new MPC notion. We first construct UC-secure commit-and-prove of spatiotemporal knowledge: in the CRS model under LWE against quantum provers without pre-shared entanglement, and in the QROM against quantum provers with unbounded pre-shared entanglement. Using these protocols, we obtain UC-secure spatiotemporal MPC from semi-honest post-quantum MPC. We also extend our framework to support quantum functionalities with classical spatiotemporal input.

Young stellar systems provide key insights into the processes governing star/planet formation, often exhibiting complex and evolving photometric variability. In this paper, we present an analysis of the object around NOI 105872, observed by the Next Generation Transit Survey (NGTS) to eclipse a young ($4.1\pm0.4$ Myr) M-type star in the Orion Nebula Cluster. The system displays deep, asymmetric eclipses with a period of $\sim0.69$ days, alongside variability in morphology. We combine photometric observations spanning approximately a decade from multiple ground- and space-based facilities to investigate the nature of this system. We explore a range of physical scenarios to reproduce the eclipse profiles and their evolution. After analysis, our preferred explanation is a circumsecondary disk surrounding a companion in orbit around the M-type primary. We adopt a six-parameter disk model and fit the eclipse profiles independently to each dataset. The best-fitting solution yields a disk radius of $\sim 0.005 \mathrm{au}$ or $0.98 R_{*}$, with broadly consistent orientations across epochs, but with variations that may be attributed to disk precession or intrinsic stellar variability. Constraints from the Hill radius imply a companion mass consistent with a very low-mass stellar companion. These results establish NOI 105872 as a candidate for a circumsecondary disk system in a young stellar environment. Continued photometric monitoring and spectroscopic follow-up will be essential to confirm this interpretation. If confirmed, systems such as NOI 105872 provide valuable benchmarks for understanding disk dynamics, companion formation, and the origin of complex eclipse phenomena in young stars.

When two photonic structures of different topology are joined, an optical mode appears at their junction. Its existence depends only on this topological difference and not on the precise dimensions of either structure. Here we realize the photonic analogue of a Jackiw-Rebbi (JR) state in hexagonal boron nitride (hBN) hosting negatively charged boron vacancies, optically addressable spin defects. Two partially etched gratings, in which the order of the radiating and dark band-edge modes is reversed, are joined side by side. Angle-resolved reflectivity and photoluminescence reveal this reversal and a non-dispersive JR state at the junction. The state proves remarkably tolerant: despite fabrication errors of up to 20 nm, its wavelength lies within a 1 nm of the design, as predicted by a systematic numerical tolerance analysis. JR gratings therefore offer a robust, monolithic platform for controlling the emission of luminescent defects.

This manuscript formalizes the most popular model validation tools used in general insurance actuarial modeling. These include graphical tools like calibration plots, actual-vs-expected plots, lift charts, Murphy diagrams, as well as classical statistical tools such as Bregman losses, deviance losses, elementary losses, Murphy's decomposition and Gini scores. Particular emphasis is placed on whether calibration and discrimination are studied under a policy-weighted or an exposure-weighted population measure. This distinction is crucial in ensuring that premium schemes are calibrated on the correct scale.