Papers

The rapid build-out of hyperscale computing for artificial-intelligence workloads has made data-center noise a recurring source of community concern in the United States, yet calibrated, standards-grade acoustic data remain scarce. This narrative review synthesizes direct measurements, regulatory and legal records, investigative journalism, and relevant engineering literature to assess what is currently known and identify the measurements needed for credible health inference. Available sources report heterogeneous acoustic values at residences, property lines, and near-source positions, with individual readings from 39 to above 70 dB(A). Because location, metric, duration, instrumentation, and provenance differ, these values are not directly comparable community exposures, do not define a pooled distribution, and do not support an aggregate comparison with nighttime limits. Among cases with spectral detail, all but one reported continuous tonal noise associated with complaints, most often low-frequency content near 70-140 Hz, that A-weighted metrics alone may under-represent. Engineering evidence further suggests that cooling architecture may be a major determinant of facility sound emission; the cited 15-30 dB span is an equipment-level sound-power estimate, not a measured facility- or residential-receptor difference, and remains a hypothesis pending comparative field measurements. We propose a standards-based field-measurement and modeling protocol designed to generate frequency-resolved exposure data at named facilities. Such exposure characterization is a necessary foundation for credible assessment of community health effects and environmental justice implications.

To discover and characterize debris disks, one must obtain high-quality photometry in order to accurately fit photosphere models for the host stars. Since the $K$ band always falls on the Rayleigh-Jeans side of a star's spectral energy distribution (SED), its reliability is particularly important for uncovering mid-infrared excess emission from dust. While Two Micron All Sky Survey (2MASS) photometry is the near-infrared benchmark for most stars that host debris disks discovered by Spitzer and the Wide Field Infrared Survey Explorer (WISE), the brightest stars ($K_s < 5$) saturated the 2MASS detectors. To accurately model debris disks that orbit the nearest, brightest stars, we construct new photosphere models by replacing saturated 2MASS data with $JHK$ photometry from the NASA Catalog of Infrared Observations, archival $R_C I_C$ photometry, and saturation-corrected WISE W1 photometry. We estimate the dust temperature and minimum distance from the star by fitting blackbody and modified blackbody models to infrared photometry from WISE, Spitzer, and Herschel. Our models allow us to identify disks that subtend large angles on the sky; these disks are candidates for follow-up with ground-based angular differential imaging, the Space Telescope Imaging Spectrograph (STIS) on the Hubble Space Telescope (HST), and NIRCam on JWST. Finally, we find that the disk surrounding $\gamma$~Tri likely has warm dust that could be resolvable with JWST's MIRI instrument at $23$ or $25.5 \micron$. Multiwavelength observations provide benchmarks for collisional cascade models and may reveal planet–disk interactions.

Amorphous materials are statistical ensembles rather than definitive structures, and conventional density-functional (DFT) and machine-learned-potential simulations sample only a small part of that ensemble. We present an $SE(3)$-equivariant denoising-diffusion model that learns the configurational distribution of amorphous oxides, so the model itself is the structure database. The learning is data efficient. A model trained on $1{,}781$ DFT configurations suffices to reproduce partial radial distribution functions, coordination statistics and bond-angle distributions, and to generate models of over $3\times10^{5}$ atoms at a cost comparable to that of the cheapest classical pair potentials. The trained model can propose amorphous atomic structures for first-principles relaxation to explore the configuration space. For example, it locates an amorphous Zr-Ta-O structure $36$ meV/atom below the previously known minimum. Generation can also extend beyond trained conditions to non-stoichiometric compositions, other mass densities, interfaces, and doping. First-principles verification confirms that generation can be steered to a requested energy, and shows that the denoising training loss does not rank generative quality, because the two measure different things.

Ising machines have emerged as promising hardware accelerators for intractable optimization and sampling problems, yet their practical impact increasingly hinges on the co-design of algorithms and hardware, where algorithmic demands shape new architectures and new hardware capabilities inspire entirely new algorithms. In this Review, we survey probabilistic algorithms designed for portability across diverse Ising platforms, advocating a top-down perspective that prioritizes principled methods with provable guarantees. We cover foundational methods such as simulated annealing and parallel tempering, including two-dimensional extensions that natively encode hard constraints, and examine approaches that expand the scale of solvable problems from cluster mean-field methods to variational samplers. We highlight the Probabilistic Approximate Optimization Algorithm (PAOA), a classical analog of QAOA that emerged directly from probabilistic hardware development, and explore how generative AI and Ising machines might reinforce each other: learned models propose global moves to accelerate optimization, while probabilistic techniques improve inference in large language models. Much as quantum computing has seen algorithms co-evolve with hardware, probabilistic and Ising computing stand at a similar inflection point. We outline a co-design framework for accelerating the capabilities and adoption of next-generation Ising machines.

Automated repair of High-Level Synthesis (HLS) designs using large language models (LLMs) is an emerging but underexplored problem. While LLM-based repair shows strong results on register-transfer level (RTL) Verilog, the only prior systematic study of HLS logic repair reports just 10.5% correction accuracy for GPT-4, with no analysis of why repair fails or what drives difficulty. We present the first comprehensive evaluation of LLM-based HLS repair across four models (GPT-4o, GPT-4o-mini, GPT-5.4, and Claude Opus 4.6) on 125 benchmark instances spanning eight logic bug types across three open-source HLS suites (CHStone, MachSuite, Polybench). We construct the first executable APR-style HLS repair benchmark with suite-specific functional oracles, enabling pass@k evaluation rather than the string-match approximations used in prior work. Design context and scale, rather than bug type alone, dominate repair difficulty: repair rates range from 6-45% on complex cryptographic kernels (CHStone) to 81-93% on compact algorithmic kernels (MachSuite) despite identical bug type distributions. We introduce solution multiplicity, the fraction of distinct patches generated across repeated repair attempts, as an empirical measure of repair underconstraint, and show it strongly predicts repair failure across all four models (Spearman rho = -0.393, p = 6.61 x 10^-20). Frontier models reduce underconstrained instances from 41-46 (GPT-4o, GPT-4o-mini) to just 3 (Claude Opus 4.6), with pass@1 improving from 42-53% to 73-76%. SHFT bugs remain consistently hard across all models, and semantic bug classes such as buffer indexing become reliably repairable only at frontier scale. These findings show that future APR benchmarks must include complex, executable, and weakly identifiable designs that remain challenging after frontier LLM repair.

Space infrastructures play critical roles in modern society, including satellite communications (SATCOM). Like the Internet, space infrastructures are vulnerable to cyber attacks, or space cyber attacks, highlighting the importance of managing cyber risks to space infrastructures, or space cyber risks. However, adequately managing space cyber risks is an open problem. In this paper, we propose the first Space Cyber Risk Management (SCRM) framework to systematically analyze and mitigate space cyber risks. The framework models space infrastructures, space missions, and space cyber attacks, while offering algorithms for space mission risk analysis and hardening. We demonstrate its usefulness by conducting a case study on real-world space cyber attacks against the SATCOM infrastructure implemented in our testbed. Our results show, among other things, that: (i) dealing with space cyber attack cascading effects is essential to space cyber risk management; (ii) the framework can effectively harden space missions; (iii) National Institute of Standards and Technology (NIST) security controls can effectively mitigate space cyber risks.

Software performance optimization requires identifying bottlenecks and improvement opportunities, and empirically evaluating the effects and trade-offs across performance objectives. Autonomous AI coding agents submit performance-oriented pull requests (PRs) to open-source projects, yet it remains unclear whether these changes reflect established optimization practices and adequately substantiate their claimed value. Extending our MSR 2026 Mining Challenge pilot study of 407 performance PRs, we analyze a sample of 1,130 agentic and 1,130 human-authored performance PRs collected through June 2026. We compare adoption outcomes and patch characteristics between the two groups, and examine their optimization practices and validation behaviors. The results show that agentic PRs are merged less often than human-authored PRs (54.4% vs. 73.3%), but the two groups use similar optimization strategies and report validation at comparable rates. Agentic PRs rely more on static reasoning and less on benchmarks (46.1% vs. 57.2%), although benchmark use converges by the end of the study period. Agentic PRs also report validation for code-smell refactorings as often as for resource-targeting changes, whereas human-authored PRs do so less often. Across both groups, about half of validated PRs report no quantitative performance metric, and relevant trade-offs are rarely quantified. Agentic optimization practice has become increasingly similar to human practice, but the supporting evidence remains incomplete. Establishing whether agent-proposed optimizations are supported by rigorous, quantitative, and multidimensional evidence remains an important challenge. These findings motivate evaluation infrastructure and review criteria that measure intended effects and relevant costs rather than treating the presence of validation alone as sufficient.

We develop a theory of orientability for metric manifolds and singular metric spaces using locally integral currents. For topological $n$-manifolds with locally finite Hausdorff measure, we introduce local degree and measure-theoretic conditions under which topological orientations correspond canonically to boundaryless, locally integer rectifiable $n$-currents of multiplicity one on the rectifiable part. We extend these currents to a class of singular spaces whose manifold part is dense and of full measure, and establish constancy and top-dimensional homology results under local uniqueness of orientation. For orientable non-collapsed $\RCD(\kappa,n)$ spaces, we prove a current-theoretic Stokes theorem: the boundary of the orientation current is the induced orientation current of the geometric boundary, with multiplicity one. In particular, its mass measure is precisely the $(n-1)$-dimensional Hausdorff measure on that boundary. For purely $n$-dimensional, locally geodesically complete spaces with local upper curvature bounds, we show that local uniqueness of orientation excludes codimension-one branching and implies a local $1$-Poincaré inequality. The latter result applies beyond homology manifolds and extends the connection between quantitative topology and Poincaré inequalities to this class of singular spaces.

This work considers reconfigurable intelligent surface (RIS) aided multi-way communication systems employing QPSK. The objectives of such system is to allow multiple users to exchange information, exploiting the full-duplex capabilities of RIS. The system under consideration comprises $K$ user terminals and an RIS with $N$ reflective elements. Each user terminal is equipped with one transmit and $M$ receive antennas. To mitigate inter-user interference caused by the full-duplex operation of the RIS, three successive interference cancellation (SIC) techniques are considered. We investigate three SIC ordering methods: $1)$ descending channel variances, $2)$ increasing mean square error, $3)$ optimization approach which maximizes the combined channel gain within the system. The bit error rate (BER) performance of these three SIC methods are evaluated using extensive Monte-Carlo simulations for different numbers of RIS elements, ranging from 4 to 64, and a varying number of transmitting users, ranging from 1 to 5. Additionally, an RIS phase shift optimization method for RIS with reflection elements of varying amplitudes is considered. In this case the previous SIC optimization technique is adapted to address phase-dependent amplitudes in RIS reflection elements. Simulation results indicate that in both ideal and varying amplitude scenarios, when the number of RIS elements is small, SIC with ordering based on increasing mean square error achieves the best BER performance. However, as the number of RIS elements increases, SIC ordering based on the optimization method achieves the best BER performance.

Each run of an AI-driven research system (ADRS) is an expensive search over a vast solution space, and dependable evaluation requires many runs, making run data both costly to produce and valuable to retain for large-scale analysis. Yet this data remains fragmented: teams operate in isolation, ADRS frameworks emit results in different formats, and no shared infrastructure exists to aggregate or compare runs across problems and systems. We present ROAR, a solution for systematically unifying and analyzing heterogeneous ADRS outputs. ROAR addresses two challenges: reconciling heterogeneous ADRS outputs and enabling analytics across runs with different objectives and scoring functions. We achieve this through a relational schema and parsing layer that normalize heterogeneous ADRS outputs while preserving data lineage and temporal structure, and accommodating new systems without requiring schema modifications. From building a corpus of more than 900 runs from multiple ADRS, we show how pooled data can reveal properties of problem landscapes that are difficult to observe. Consistent with prior work, runs with identical configurations may converge to different scores. We find that many runs realize most gains early, and that the effectiveness of different strategies for incorporating prior solutions into the search process varies across problems. We further show that the pooled corpus is actionable and not merely analytical by using ROAR to configure ADRS runs. Together, these results illustrate how pooled ADRS data can expose problem-dependent structure in search behavior that is difficult to detect from any single system, team, or benchmark. Such cross-cutting insights are difficult to obtain while runs remain siloed; ROAR is the first infrastructure designed to unify them.

Coherent microwave-to-optical transduction is essential for hybrid quantum networks. Typical transducers, however, have bandwidths set by fixed device parameters and face efficiency-bandwidth tradeoffs. We propose a cavity-based microwave-to-optical transducer mediated by a collective Rydberg excitation, where external driving fields tune the conversion bandwidth in situ from narrowband, spectrally selective operation to broadband operation without modifying cavity parameters. Under impedance-matching conditions, the system operates as a continuous-wave phase-preserving linear transducer, maintaining both near-unit efficiency and quantum-limited added noise throughout the tunable bandwidth range.

Hybrid radio frequency (RF) and visible light communication (VLC) networks have emerged as a promising solution for high-capacity indoor wireless connectivity in sixth-generation (6G) systems. However, the limited optical coverage and vulnerability of VLC links to line-of-sight (LoS) blockage under user mobility remain fundamental challenges. In this work, a mirror-based intelligent reflecting surface (IRS) is deployed to assist a dynamic indoor hybrid RF/VLC network, where each mobile user is exclusively assigned to either the IRS-enhanced VLC subnetwork or the RF subnetwork through a binary selection decision. A joint optimization problem is then formulated to maximize proportional fairness by jointly optimizing the RF/VLC technology selection, power allocation, and IRS mirror roll and yaw orientation angles. To enable real-time adaptability, the problem is reformulated as a Markov decision process (MDP) and solved using a cooperative multi-agent deep reinforcement learning (DRL) algorithm based on centralized training with decentralized execution. Simulation results demonstrate the superior performance of the optimized hybrid network compared with optimized standalone VLC and RF networks. The results further validate the practicality and effectiveness of the proposed DRL framework compared to widely adopted DRL algorithms as well as conventional model-based optimization approaches.

Calcium homeostasis is maintained by an endocrine network comprising parathyroid hormone (PTH), calcitriol and calcitonin, which defends serum calcium at the expense of skeletal reserves. Serum calcium is therefore an unreliable indicator of nutritional calcium status, and empirical supplementation remains common. This narrative review proposes a clinical–metabolic approach to estimating individual calcium requirements that integrates bone mineral density (BMD), vitamin D status and the compensatory PTH response. We make three contributions. First, we present a sigmoidal phosphate–PTH model in which a glucose-dependent gain term ($\Delta k_{\mathrm{gluc}}$) captures the heightened parathyroid sensitivity associated with dysglycaemia, and we illustrate it with simulated values for healthy adults, women and individuals with gluco-osteoporosis. Second, we translate the model into a four-step decision algorithm that frames the intake gap as a net balance of intestinal absorption, renal excretion and bone turnover. Third, we incorporate the osteocyte–osteoblast bioenergetic axis (sclerostin/Wnt signalling, GLUT1-mediated glucose uptake, aerobic glycolysis and osteocalcin–insulin crosstalk) to explain why calcium supplementation may be ineffective when cellular energy supply or insulin sensitivity is impaired. The framework aims to prevent secondary hyperparathyroidism, avoid over supplementation and preserve skeletal integrity. The model values are simulated and require prospective clinical validation.

The BAIBAICHUCHU team participated in the Social Media Subtask of NTCIR-19 FinArg-3, ranking Chinese investor posts by Maximum Possible Profit (MPP). A three-track ensemble of lexical features, a FinArg-2-pre-finetuned MacBERT ranker, and an LLM judge reaches 0.734 in post-grouped development evaluation, but our best official run scores 0.517. All twelve submitted runs lie between 0.4598 and 0.5402, and our 26 unanimous three-track pairs score 0.500. A post-hoc audit finds that the submitted judge applied a long-only rule to bearish posts although MPP is stance-aware. Correcting it changes 28 of 87 official predictions without changing accuracy, yet lowers development accuracy from 0.680 to 0.622: a regime-specific semantic shortcut improved validation fit. We decompose ranking into directional text, volatility and horizon, and pairwise margin. A running-extremum model predicts $\sigma\sqrt{T}$ scaling, observed ex post in 502 price-aligned posts from a separate July 2026 collection. Pre-posting volatility scaled by the post-specific observation horizon, $\sigma_{\mathrm{pre},20}\sqrt{N_i}$, is associated with a later truncated-horizon MPP proxy (Spearman $\rho=0.320$; ticker-cluster 95% CI [0.133,0.466]) and correctly orders 61.4% of unequal-outcome pairs. Transferred text is nearly uncorrelated with the July outcome ($\rho=0.055$) and adds little conditional on this score and stance. Development reliability rises from about 0.60 to 0.93 as the labeled MPP gap widens. An earlier ERAI result of 0.6207 rules out universal unpredictability as a simple explanation. Evaluation should jointly consider text, market regime, historical volatility, horizon, and pair composition.

Although scattering is inherently non-separable, holographic multiple-input multiple-output channels are commonly modeled using separable scattering across the source and receiver. In this paper, we investigate non-separable scattering in a non-line-of-sight holographic line model based on wavenumber-division multiplexing. We model its power spectral factor (PSF) using a bivariate von Mises-Fisher (vMF) distribution and introduce a non-separability parameter. We prove that the marginal densities flatten and their Kullback–Leibler divergence from the uniform distribution decreases monotonically with non-separability. Using majorization theory, we further establish that an upper bound and an approximation at low signal-to-noise ratio (SNR) of the ergodic spectral efficiency increase monotonically. Numerical results validate the analysis and demonstrate the performance gains of non-separable scattering over its separable counterpart.

Instruction fine-tuning adapts a pretrained language model to follow instructions by training it on instruction–response pairs from a collection of tasks, such as summarization and question answering. Task-level poisoning exploits this task structure to manipulate the fine-tuned model into producing attacker-specified biased content on a particular target task, without requiring an explicit input trigger. Detecting such attacks is challenging because there is no explicit trigger to identify, the target task and biased content are unknown, and benign fine-tuning itself changes model behavior. We introduce Localize-and-Detect, a two-stage black-box auditing method for task-level poisoning that requires only outputs from both the base and fine-tuned models. In the first stage, we localize the target task by identifying candidate tasks on which the fine-tuned and base models have the largest differences in their next-token distributions. In the second stage, we search the shortlisted tasks for biased content that repeatedly appears in the fine-tuned model's responses but not in those of the base model. We evaluate Localize-and-Detect on 216 poisoned models across two model families, varying the target task, poisoning mode, poison budget, and type of biased content. Our evaluation demonstrates that Localize-and-Detect can effectively localize target tasks and detect biased content across a range of poisoning settings and models, with detection that tracks attack success and few false positives on clean models.

Recent world action models (WAMs) reuse pretrained video VAEs whose encoder latents directly condition downstream action policies. Quantization must therefore preserve not only reconstruction fidelity but also the policy-facing latent contract expected by the frozen policy. Direct NVFP4 leaves W4A4 quantization error uncompensated, whereas joint quantization-aware training (QAT) can recover reconstruction by moving this representation. On Wan2.1, joint QAT nearly matches FP32 VBench-7 (0.7403 versus 0.7409), yet LIBERO success collapses from 95.5% to 10.5%. Controlled decoder-only experiments show that activation quantize-dequantize operations alter the reconstruction signal and decoder Jacobian, redirecting the gradient returned to the encoder and inducing persistent latent drift. Based on this mechanism, we introduce LatentQuant, a two-stage NVFP4 QAT framework that first aligns the quantized encoder with its high-precision counterpart, then freezes it while adapting the decoder. Across Wan2.1 and Wan2.2, LatentQuant preserves near-baseline control and high reconstruction quality, achieving 95.75% success on LIBERO and 68.8% on RoboTwin. On NVIDIA B300 GPUs, NVFP4 execution achieves 1.17x-1.26x end-to-end VAE speedups over BF16 cuDNN.

Question answering over spreadsheet collections requires finding the correct workbook and computing over complete tables. We introduce Find-then-Compute (FiCo), which retrieves document summaries, disambiguates similar workbooks, and executes constrained Structured Query Language (SQL) over the selected full table. On DataBench (80 datasets, 1,810 questions), FiCo reaches 76.2% accuracy: 9.9 points above a strong TableRAG-style baseline on the same frozen workbook choices (66.3%) under the tracks' prespecified evaluators, and 63.4 points above prefix RAG (12.8%). On 508 MiMoTable questions, FiCo reaches 79.7%, versus 22.2% for prefix RAG. Giving the strong baseline the gold workbook raises it from 66.3% to 76.3%, exposing a 10.0-point source-selection cost under fixed compute. Despite 95.1% document recall and 98.5% executable SQL, only 81.3% of questions execute on the gold workbook. FiCo's advantage comes from integrating semantic source selection with exact, schema-grounded computation.

In this paper we introduce a geometrically constrained optimal transport problem on Riemannian manifolds endowed with a Borel foliation, in which mass is transported only within individual leaves. We characterize the existence of foliated transport plans through the equality of the transverse projections of the marginals and show that the corresponding quadratic transport cost decomposes into a measurable family of leafwise optimal transport problems. We also formulate the problem as a classical Kantorovich problem with an extended-valued leafwise cost. Finally, we introduce a foliated continuity equation and establish a Benamou-Brenier formula relating the static and dynamical foliated formulations.

We propose a data-driven framework for estimating the Bayesian Cramér-Rao bound (CRB) in high-dimensional imaging systems with complex, analytically intractable priors. Direct CRB computation is challenging in this setting due to the need to model the prior score and to form and invert the Bayesian Fisher information matrix in very high dimensions. To address these issues, we first reformulate the inverse problem in the latent space of a pre-trained variational autoencoder, thereby dramatically reducing the dimensionality of the bound estimation problem while preserving the spatial structure of the images. The Bayesian CRB is formed in this latent space and mapped back to the native parameter space using a change-of-variables formula. Second, to learn the latent prior score, we introduce a new sliced score matching objective defined in a Bochner space endowed with an $H^1(\Omega)$ Sobolev norm in space. This "Bochner-space sliced score matching" objective is consistent with standard sliced score matching, but penalizes errors in the spatial gradients of the score, suppressing high-frequency artifacts that otherwise contaminate the resulting CRB estimates. We validate the approach on a stylized quantitative photoacoustic computed tomography (qPACT) breast imaging problem with over one million unknown parameters, using a foundation-model autoencoder derived from Stable Diffusion. The proposed method yields stable, artifact-free Bayesian CRB estimates that reflect the highly non-Gaussian structure of the learned prior and reveal the substantial impact of the prior on the relative performance of competing qPACT design schemes.

Large language model (LLM) watermarking is important for ownership verification and intellectual property protection. However, existing approaches focus on algorithmic design while treating LLM inference engines as separate components. This separation often introduces auxiliary models or external tools, increasing latency and memory overhead while limiting the use of modern inference optimizations. As a result, a deployment gap remains: practical watermarking must preserve utility, detectability, and robustness while minimizing serving overhead. To bridge this gap, we propose SWIFT, a framework that co-designs LLM watermarking with modern inference infrastructure. SWIFT (i) integrates text generation and watermark construction within a shared LLM backend to reduce re-computation, improve cache reuse, and simplify system complexity; (ii) uses instruction-guided candidate generation with semantic protection to preserve factual consistency and meaning; (iii) executes watermarking concurrently with generation through asynchronous co-serving and adaptive scheduling to reduce latency and improve resource utilization; and (iv) leverages vLLM optimizations to enhance serving efficiency. Extensive experiments across domains and tasks show that SWIFT achieves strong utility, detectability, robustness, and downstream performance while substantially improving serving efficiency. Specifically, it achieves the highest utility score (4.87), 99.65% detection accuracy compared with 76.65% for the low-latency baseline SynthID, and up to 97.7% detection under watermark removal attacks, with 5.9x lower latency than the highest-utility baseline, SafeSeal. These results demonstrate the benefits of co-designing watermarking with inference infrastructure for practical LLM serving.

A reinterpretation of ATLAS searches targeting $b$-tagged dijet resonances and monotop-alike signatures at a center-of-mass energy of 13 TeV is presented using $pp$ collision data corresponding to integrated luminosities of 139 $\mathrm{fb}^{-1}$. These searches are used to constrain a baryon-number-violating new physics model that introduces two scalar mediators $X_{1}$ and $X_{2}$ to simultaneously address the baryon asymmetry of the universe and the dark matter relic abundance. By exploiting heavy-flavor signatures and allowing for jet-rich final states, this reinterpretation provides complementary sensitivity to the model relative to non-flavor-tagged inclusive dijet searches and conventional monotop reinterpretations. Assuming the mediators decay either into a pair of down-type quarks or into a top quark and a dark matter candidate, we translate the experimental upper limits into the model's parameter space. 95% confidence level exclusion limits are derived in the $\lambda_1$-$\lambda_2$ coupling plane for benchmark mediator masses of 1.5, 1.75, and 2.0 TeV. For all three benchmark masses, the $b$-tagged dijet reinterpretation excludes $\lambda_1 > 0.45$, while the bottom-squark reinterpretation excludes the region with $\lambda_1 > 0.3$ and $\lambda_2 > 0.6$, within the respective validated parameter domains.

Video games hold a prominent role in the entertainment industry, which constitutes a multibillion-dollar global market. Within this ecosystem, independent studios, small teams, and solo developers operate with constrained budgets while making their games available through platforms such as itch.io, where many projects are also available as open-source. Where even if the project is fully released, other developers can still have access to the development process through the source code, helping other developers to develop their own games. These open-source games also constitute a valuable corpus for empirical software engineering research, offering transparent access to development artifacts that are typically inaccessible in commercial projects. This study characterizes open-source video games from a Software Engineering standpoint, focusing on their genres, popularity, repository activity, implementation characteristics, and testing practices. To this end, we extracted metadata from 491 video games from itch.io, published as open-source projects in GitHub. The results indicate that open-source games predominantly fall within limited genres (Puzzle, Action, and Platformer), that player ratings, when available, tend to be high, bringing a perception that the community receives well those kind of games, that repositories are largely dormant or minimally maintained, that the majority of these projects adopt either Godot or Unity as their game engine, and that documentation of testing-related practices is seldom included. The results offer insights into the development of open-source video games and may contribute to advancing software engineering practices and tools designed for small teams and independent game developers.

A one-step curvature probe evaluates an initial direction, whereas continual learners are judged after reaching comparable new-task fit. In an overparameterized linearization, projected gradient descent converges to $\Delta_P=PJ^\top(JPJ^\top)^{-1}r$, and its squared-displacement inflation is exactly the reciprocal of the retained fitting capacity $c_P(r)$. More generally, the terminal old-task quadratic ratio factorizes as $1/[c_P(r)G_{\rm end}(P,r)]$, where $G_{\rm end}$ compares curvature along endpoint directions. In the rank-one case, $G_{\rm end}$ equals the one-step probe gain; for multiple outputs, the two gains can differ. The terminal quadratic also separates into a curvature-optimal fitting floor and an algorithm-dependent null-space excess, motivating terminal null-space correction, which preserves linearized new-task outputs on its Jacobian batch. Controlled checks validate the local quadratic and show that projection can greatly reduce matched-norm curvature while barely changing terminal forgetting. Across common-threshold configurations, projection yields the larger signed old-task loss change in 73/99 matched pairs, retained fitting capacity falls with rank, and fixed-rank comparisons separate terminal forgetting even when probe gain is approximately matched. On Permuted MNIST and Split CIFAR-100, terminal correction decreases signed old-task loss in 166/180 method–dataset–seed pairs under the all-seed intention-to-correct analysis; because acceptance and outcome reporting use the same held-out split, this result is descriptive and test-conditioned. Overall, terminal cost depends jointly on retained fitting capacity, endpoint-direction curvature, and the null-space component selected by optimization.

Large language models (LLMs) are increasingly used as classifiers, yet they operate as opaque systems whose decisions are difficult to interpret, which complicates their use in regulated domains such as credit scoring or medical diagnosis. We propose an evolutionary framework that iteratively discovers natural language feature definitions (rubrics) for interpretable classification. An LLM generates candidate binary features, evaluates each sample against them, and the resulting vectors can be used to train a transparent classifier such as logistic regression. The feature set evolves over multiple iterations guided by classification errors, per-class activation rates, and feature ablation scores. We evaluate across three benchmarks, including a credit risk dataset representative of regulated domains, comparing single-shot LLM rubrics, evolved rubrics, and direct zero-shot LLM classification. Evolved features improve over single-shot rubrics by +2.9 pp on average and outperform zero-shot LLM classification on two of three tasks, while providing fully auditable decision logic. On the credit risk task, the zero-shot LLM performs at chance (50.7%) with a strong bias toward a single class, whereas evolved features achieve balanced, interpretable predictions. Crucially, this failure is invisible in aggregate accuracy and surfaces only under per-class auditing. Analysis reveals that evolution is most effective when label boundaries cannot be inferred from category names alone or when the LLM lacks reliable domain-specific reasoning.

We conjecture an exact formula for the effective central charge, ceff, of a family of three- dimensional superconformal field theories related to Chern-Simons theory on a three-manifold by the 3d-3d correspondence. The formula determines ceff , which governs the growth of a protected sector of states in the conformal theory, in terms of the dimension of a particular space of modular forms. We confirm our approach by checking against known results computed through resurgent continuation.

The increasing complexity of 5G and emerging 6G wireless networks has intensified the need for scalable optimization techniques capable of addressing computationally challenging combinatorial problems. While quantum optimization offers a promising alternative, current near-term quantum hardware remains limited by qubit availability, noise, and scalability constraints. Pauli Correlation Encoding (PCE) has emerged as a qubit-efficient optimization framework that addresses these challenges through polynomial variable compression. However, the impact of compression on representability and solution recovery remains poorly understood. In this work, we investigate the hypothesis that increasing compression ratios introduce representability constraints arising from algebraic closure relationships among encoded Pauli observables. Using Maximum Independent Set benchmark problems, we evaluate multiple PCE ansatz designs and compression ratios. We find that ansatz selection is critical to both solution quality and feasibility, with two ansatz families consistently outperforming alternatives and achieving approximation ratios approaching 0.9. Furthermore, increasing circuit repetitions provides limited benefit and can degrade performance. Most notably, reducing compression by increasing the number of available qubits significantly improves raw solution quality, while post-processed performance remains comparatively stable. These findings suggest that representability effects play an important role in compressed PCE encodings and provide new insight into the relationship among compression, ansatz design, decoding, and solution quality in scalable quantum optimization.

Autonomous driving decision systems must balance safety, efficiency, and social norms in complex traffic interactions. Philosophical and ethical considerations have received limited attention in existing autonomous driving decision-making approaches based on numerical optimization, sequence prediction, and large language models (LLMs). We propose Chinese Philosophical Wisdom-Guided Driving (CPW-Drive), a closed-loop retrieval-augmented generation (RAG) framework that incorporates value guidance derived from Chinese philosophy into autonomous driving decision-making. Using Chinese Confucian thought as its knowledge source, CPW-Drive consolidates LLM-extracted keywords from relevant classical texts into driving-relevant value principles through manual screening and validation. It then contextualizes these principles through scenario-specific cases to form retrievable and reusable value guidance. We further propose Physics-aware Spatial Similarity Retrieval (PSSR), which compares vehicle layouts and velocity-extrapolated states to retrieve physically relevant historical cases. On Highway-env's multilane highway-driving task, CPW-Drive achieves success rates of 93.0%, 86.0%, and 72.0% across three traffic configurations. These results outperform the strongest baseline by 8.0, 22.5, and 25.0 percentage points, respectively. Across all configurations, CPW-Drive achieves the highest collision-free step count and maintains a low lane-change frequency. The results suggest that structured value guidance can improve simulated closed-loop safety and stability while introducing efficiency and latency trade-offs.

Finding a compact formula that fits a set of input-output pairs and predicts outputs on unseen inputs is a fundamental problem in science. Symbolic regression automates the search for such formulae: search-based methods explore the space of possible formulae directly, while transformers pre-trained on synthetic data produce formulae of comparable quality substantially faster. Existing transformers, however, are prone to overfitting — they find formulae that fit the training data well but do not extrapolate to input ranges unseen during training. We address this by shaping the set of formulae used to train a transformer, and show that the resulting formulae extrapolate substantially better. Fine-tuning the transformer on data with noise-corrupted target values further makes the synthesized formulae robust to noise in the observations. On SRBench and LLM-SRBench our transformer synthesizes a formula in about ten seconds and extrapolates better than all evaluated methods at a comparable budget. Search-based methods surpass our accuracy only when given one to three orders of magnitude more time.

The halo concentration, which represents the distribution of matter within a halo, is a vital tool for modeling the matter distribution on scales ranging from megaparsecs to sub-kiloparsecs. While significant progress has been made on connecting the impact of astrophysics on the mean concentration as a function of halo mass, the same connection to higher moments of the concentration distribution remains far less explored. We employ the IllustrisTNG runs in the CAMELS simulation suite to simultaneously quantify the astrophysics and cosmology dependence of the first four moments of the concentration-mass relation; the mean, the scatter, the skewness, and the kurtosis. We use normalizing flows to model the concentration distribution as a function of halo mass, redshift, and six cosmological/astrophysical parameters. We focus on the mass range $M_{\rm vir} \in [10^{11}, 10^{14.5}] M_{\odot}/h$, and the redshift range $z \in [0, 1]$. All higher-order moments exhibit a mass-dependent sensitivity to both astrophysics and cosmology. The behavior in dark matter-only simulations follows the known effects of active mergers and of tidal stripping in smaller halos. Once galaxy formation is included, the scatter shows non-monotonic behavior at the Milky Way (MW) mass-scale, and the amplitude of this behavior is strongly influenced by the baryon fraction and supernovae (SNe) feedback parameters. The skewness has a large sensitivity to the baryon fraction as well and is mostly insensitive to the other parameters, while the kurtosis follows the behavior set by the skewness. Results for the ASTRID simulation suite show similar behavior as that of IllustrisTNG. The cosmology and astrophysics dependence of these higher-order moments impact analyses that are sensitive to the full distribution of the concentration-mass relation, particularly for halos at/below the MW mass scale.