Magnetic reconnection is a highly dynamic process that excites a wide variety of kinetic waves and instabilities. Transverse current sheet instabilities such as the lower-hybrid drift and secondary drift-kink instabilities in particular have been shown by kinetic simulations to modify the reconnection and introduce significant turbulence and mixing to the reconnection layer. Past studies using the ten-moment fluid model to capture important kinetic physics such as the electron inertia and full representation of the pressure tensor proved advantageous to a two-fluid representation of reconnection, but the model struggled when using a local relaxation closure for the heat flux to replicate the current sheet instabilities and subsequent mixing seen in kinetic simulations. This work uses the \texttt{Gkeyll} software framework to perform simulations of asymmetric reconnection based on the 16 October 2015 MMS crossing of a diffusion region, the Burch event. An improved gradient-based heat flux closure is implemented, showing significant improvement in secondary kinetic instabilities that grow in the current sheet. These instabilities generate turbulence which leads to growth of secondary magnetic islands and flux ropes.

A theory of the spectral "zebra" pattern of the Crab pulsar's high-frequency interpulse (HFIP) radio emission is developed. The observed emission bands are interference maxima caused by multiple ray propagation through the pulsar magnetosphere. The high-contrast interference pattern is the combined effect of gravitational lensing and plasma de-lensing of light rays. The model enables space-resolved tomography of the pulsar magnetosphere, yielding a radial plasma density profile of $n_{e}\propto r^{-3}$, which agrees with theoretical insights. We predict the zebra pattern trend to change at a higher frequency when the ray separation becomes smaller than the pulsar size. This frequency is predicted to be in the range between 42 GHz and 650 GHz, which is within the reach of existing facilities like ALMA and SMA. These observations hold significant importance and would contribute to our understanding of the magnetosphere. Furthermore, they offer the potential to investigate gravity in the strong field regime near the star's surface.

The advent of 5G and the emergence of 6G networks demand unprecedented flexibility and efficiency in Radio Access Network (RAN) resource management to satisfy diverse service-level agreements (SLAs). Existing RAN slicing frameworks predominantly rely on per-slice resource reservation, which ensures performance isolation but leads to inefficient utilization, particularly under bursty traffic. We introduce HyRA, a hybrid resource allocation framework for RAN slicing that combines dedicated per-slice allocations with shared resource pooling across slices. HyRA preserves performance isolation while improving resource efficiency by leveraging multiplexing gains in bursty traffic conditions. We formulate this design as a bi-level stochastic optimization problem, where the outer loop determines the dedicated and shared resource budgets and the inner loop performs per-UE scheduling under a novel water-filling approach. By using the sample-average approximation, the Karush-Kuhn-Tucker (KKT) conditions of the inner loop, and Big-M encoding, we transform the problem into a tractable mixed-integer program that standard optimization solvers can solve. Extensive simulations under diverse demand patterns, SLA configurations, and traffic burstiness show that HyRA achieves up to 50-75% spectrum savings compared to dedicated-only and shared-only baselines. These results highlight HyRA as a viable approach for resource-efficient, SLA-compliant RAN slicing in future mobile networks.

The preparation of a quantum state using a noisy quantum computer (gate noise strength $δ$), will necessarily affect an O($δ$)-fraction of the qubits, no matter which protocol is used. Here, we show that fault-tolerant quantum state preparation can be achieved with constant space overhead improving on previous constructions requiring polylogarithmic overhead. To achieve this, we add to the toolbox of fault-tolerant schemes for circuits with quantum input and output. More specifically, we construct fault-tolerant interfaces that decrease the level of protection for quantum low-density parity-check (LDPC) codes. When information is encoded in multiple code blocks, our interfaces have constant space overhead. In our decoder construction that change the level of protection by an arbitrary amount, we circumvent bottlenecks to error pileup and overhead by gradual lowering of the level of encoding at the same time as we increase the number of blocks on which decoding is carried out simultaneously.

We discuss the behavior of the default ``wavecal'' spectra obtained together with most STIS spectroscopic exposures, which are needed for proper wavelength calibration of the science data. Because the Pt/Cr-Ne lamps used for the wavecals have been fading (especially at the shortest wavelengths), some changes in the default lamp and/or exposure time have been implemented in recent years to maintain accurate calibrations. To assess whether additional changes might be appropriate, we examine the distribution of the SHIFTA1, SHIFTA2 values derived from the wavecals (the x and y offsets of the spectral image on the detector), we re-visit the wavelength-dependent fading of the lamps, and we perform simulations to estimate the exposure times that would be needed to obtain accurate SHIFTA values. While the current wavecals do appear to yield reasonable SHIFTA, increases in the default exposure times for some of the shortest-wavelength settings would help to ensure reliable wavelength zero points as the lamps continue to fade.

We prove that globally $+$-regular varieties are rationally chain connected in dimension three and mixed characteristic with residue field characteristic $p>5$. We also introduce a notion of strongly globally $+$-regular, and show that varieties of arbitrary dimension which are strongly globally $+$-regular over a dense open subset of $\mathrm{Spec}(\mathbb{Z})$ are rationally chain connected.

Finite time extinction of any bounded solution to the fast diffusion equation with spatially inhomogeneous absorption $$ \partial_tu=Δu^m-|x|^σu^p, \quad (x,t)\in\mathbb{R}^N\times(0,\infty), $$ with $N\geq1$ and exponents $$ p>1, \quad m_c=\frac{(N-2)_+}{N}<m<1, \quad σ>σ_*:=\frac{2(p-1)}{1-m}, $$ is established. Moreover, the existence of self-similar solutions of the form $$ U(x,t)=(T-t)^αf(|x|(T-t)^β), \quad α=\frac{σ+2}{(1-m)(σ-σ_*)}, \ β=\frac{p-m}{(1-m)(σ-σ_*)}, $$ with $f(0)>0$, $f'(0)=0$ and $$ \lim\limits_{ξ\to\infty}ξ^{(σ+2)/(p-m)}f(ξ)=L\in(0,\infty). $$ is proved, together with some unbounded self-similar solutions as well. The property of finite time extinction is in striking contrast to the standard fast diffusion equation with absorption (that is, $σ=0$), where the strict positivity of solutions for any $t\in(0,\infty)$ is well-known.

Ineffective meetings are pervasive. Thinking ahead explicitly about meeting goals may improve effectiveness, but current collaboration platforms lack integrated support. We tested a lightweight goal-reflection intervention in a preregistered field experiment in a global technology company (361 employees, 7196 meetings). Over two weeks, workers in the treatment group completed brief pre-meeting surveys in their collaboration platform, nudging attention to goals for upcoming meetings. To measure impact, both treatment and control groups completed post-meeting surveys about meeting effectiveness. While the intervention impact on meeting effectiveness was not statistically significant, mixed-methods findings revealed improvements in self-reported awareness and behaviour across both groups, with post-meeting surveys unintentionally functioning as an intervention. We highlight the promise of supporting goal reflection, while noting challenges of evaluating and supporting workplace reflection for meetings, including workflow and collaboration norms, and attitudes and behaviours around meeting preparation. We conclude with implications for designing technological support for meeting intentionality.

We demonstrate that graph-based models are fully capable of representing higher-order interactions, and have a long history of being used for precisely this purpose. This stands in contrast to a common claim in the recent literature on "higher-order networks" that graph-based representations are fundamentally limited to "pairwise" interactions, requiring hypergraph formulations to capture richer dependencies. We clarify this issue by emphasizing two frequently overlooked facts. First, graph-based models are not restricted to pairwise interactions, as they naturally accommodate interactions that depend simultaneously on multiple adjacent nodes. Second, hypergraph formulations are strict special cases of more general graph-based representations, as they impose additional constraints on the allowable interactions between adjacent elements rather than expanding the space of possibilities. We show that key phenomenology commonly attributed to hypergraphs -- such as abrupt transitions -- can, in general, be recovered exactly using graph models, even locally tree-like ones, and thus do not constitute a class of phenomena that is inherently contingent on hypergraphs models. Finally, we argue that the broad relevance of hypergraphs for applications that is sometimes claimed in the literature is not supported by evidence. Instead it is likely grounded in misconceptions that network models cannot accommodate multibody interactions or that certain phenomena can only be captured with hypergraphs. We argue that clearly distinguishing between multivariate interactions, parametrized by graphs, and the functions that define them enables a more unified and flexible foundation for modeling interacting systems.

Large Language Models (LLMs) have demonstrated remarkable effectiveness in adapting to downstream tasks through fine-tuning. Federated Learning (FL) extends this capability by enabling collaborative fine-tuning across distributed clients using Low-Rank Adaptation (LoRA), while preserving data privacy by avoiding raw data sharing. However, practical deployments face challenges when clients have heterogeneous resources and thus adopt different LoRA ranks, leading to substantial initialization and aggregation noise that undermines performance. To address these challenges, we propose Fed-PLoRA, a novel lightweight heterogeneous federated fine-tuning (FFT) framework. Fed-PLoRA introduces Parallel One-Rank Adaptation (PLoRA), a new LoRA variant that replaces the classic multi-rank LoRA module with multiple parallel one-rank modules, and a novel Select-N-Fold strategy that folds untrained PLoRA modules into the pre-trained weights before local training, thereby accommodating heterogeneous client resources. We provide a unified analysis of initialization and aggregation noise of Fed-PLoRA and demonstrate how it addresses the limitations of state-of-the-art methods. Extensive experiments on diverse LLM fine-tuning tasks demonstrate that Fed-PLoRA consistently outperforms existing methods in both accuracy and efficiency. The code is available at https://github.com/TNI-playground/Fed-PLoRA.

Quantum error correction (QEC) is essential for realizing fault-tolerant quantum computation. Current QEC controllers execute all scheduled syndrome (parity-bit) measurement rounds before decoding, even when early syndrome data indicates that the run will result in an error. The resulting excess measurements increase the decoder's workload and system latency. To address this, we introduce an adaptive abort module that simultaneously reduces decoder overhead and suppresses logical error rates in surface codes and color codes under an existing QEC controller. The key idea is that initial syndrome information allows the controller to terminate risky shots early before additional resources are spent. An effective scheme balances the cost of further measurement against the restart cost and thus increases decoder efficiency. Adaptive abort schemes dynamically adjust the number of syndrome measurement rounds per shot using real-time syndrome information. We consider three schemes: fixed-depth (FD) decoding (the standard non-adaptive approach used in current state-of-the-art QEC controllers), and two adaptive schemes, AdAbort and One-Step Lookahead (OSLA) decoding. For surface and color codes under a realistic circuit-level depolarizing noise model, AdAbort substantially outperforms both OSLA and FD, yielding higher decoder efficiency across a broad range of code distances. Numerically, as the code distance increases from 5 to 15, AdAbort yields an improvement that increases from 5% to 35% for surface codes and from 7% to 60% for color codes. To our knowledge, these are the first adaptive abort schemes considered for QEC. Our results highlight the potential importance of abort rules for increasing efficiency as we scale to large, resource-intensive quantum architectures.

Quantum computing improves substantially on known classical algorithms for various important problems, but the nature of the relationship between quantum and classical computing is not yet fully understood. This relationship can be clarified by free models, that add to classical computing just enough physical principles to represent quantum computing and no more. Here we develop an axiomatisation of quantum computing that replaces the standard continuous postulates with a small number of discrete equations, as well as a free model that replaces the standard linear-algebraic model with a category-theoretical one. The axioms and model are based on reversible classical computing, isolate quantum advantage in the ability to take certain well-behaved square roots, and link to various quantum computing hardware platforms. This approach allows combinatorial optimisation, including brute force computer search, to optimise quantum computations. The free model may be interpreted as a programming language for quantum computers, that has the same expressivity and computational universality as the standard model, but additionally allows automated verification and reasoning.

Recent advances in foundation models, including large language models (LLMs), have created new opportunities to automate building energy modeling (BEM). However, systematic evaluation has remained challenging due to the absence of publicly available, task-specific datasets and standardized performance metrics. We present BEMEval, a benchmark framework designed to assess foundation models' performance across BEM tasks. The first benchmark in this suite, BEMEval-Doc2Schema, focuses on structured data extraction from building documentation, a foundational step toward automated BEM processes. BEMEval-Doc2Schema introduces the Key-Value Overlap Rate (KVOR), a metric that quantifies the alignment between LLM-generated structured outputs and ground-truth schema references. Using this framework, we evaluate two leading models (GPT-5 and Gemini 2.5) under zero-shot and few-shot prompting strategies across three datasets: HERS L100, NREL iUnit, and NIST NZERTF. Results show that Gemini 2.5 consistently outperforms GPT-5, and that few-shot prompts improve accuracy for both models. Performance also varies by schema: the EPC schema yields significantly higher KVOR scores than HPXML, reflecting its simpler and reduced hierarchical depth. By combining curated datasets, reproducible metrics, and cross-model comparisons, BEMEval-Doc2Schema establishes the first community-driven benchmark for evaluating LLMs in performing building energy modeling tasks, laying the groundwork for future research on AI-assisted BEM workflows.

OB stars generally form in open clusters within the Milky Way's thin disk, so when they are found at high Galactic latitudes, it is thought that they were ejected from their birth clusters during the past few tens of millions of years. Using Gaia Data Release 3 (hereafter DR3) data, we traced the kinematic trajectories of 39 high-latitude B-type stars and 447 Galactic open clusters with high-quality astrometry to search for moments of past intersection. In cases where we found matching trajectories, we also considered the clusters' HR diagrams to confirm parent-orphan pairs have matching ages. Further analysis of the clusters' core environments allowed us to determine a probable ejection mechanism. Through these paternity tests, we have identified possible origins for five of these orphaned B-type stars. Here we present the likely travel times, ejection velocities, and a discussion of the runaway mechanism for each case. We also identify one star whose trajectory did not bring it near the disk during the time period of our analysis, and we discuss its possible origins as well.

Capture the Flag (CTF) competitions are powerful pedagogical tools for addressing the global cybersecurity workforce gap, yet their effective K-12 implementation is often undermined by significant barriers, including educator preparedness gaps and equity concerns. This paper addresses these challenges by proposing the Ethical-Cognitive Apprenticeship in Cybersecurity (ECAC) framework, a new model derived from a systematic Framework Synthesis of existing literature and empirical evidence. ECAC systematically integrates cognitive apprenticeship theory with embedded ethical development across five phases: (1) Foundational Modeling, (2) Scaffolding the Arena, (3) Coaching and Articulation, (4) Ethical Dilemma Injections, and (5) Reflective Exploration. The framework provides a "low floor, high ceiling" learning pathway designed to broaden participation among diverse student groups, including underrepresented minorities and women, while fostering deep, transferable skills. By reframing the educator role as a lead learner," ECAC also offers a sustainable solution to the teacher expertise gap. Ultimately, this framework provides a practical roadmap for transforming CTFs from standalone competitions into integral learning experiences that cultivate a more skilled, ethical, and diverse generation of cybersecurity professionals.

We compute relativistic corrections to the gluon fragmentation functions to ${}^3P_J^{[1,8]}$ Fock states of heavy quarkonium within non-relativistic QCD factorization framework. We find that, at $\mathcal{O}(v^2)$ sub-leading order, the $S$-$D$ mixing effect must be taken into account to absorb the infrared divergence of spin-triplet $P$-wave production within full QCD into the NRQCD long-distance matrix elements. Unlike the $S$-wave case, we find that the short-distance coefficients of the fragmentation functions at leading and sub-leading order are no longer proportional to each other. However, upon convolution with the gluon production cross section, their ratios are almost constant across the whole $p_T$ region. We find the relativistic corrections to be negative and substantial, which makes them a non-negligible ingredient in the study of $J/ψ$ production at the LHC.

We study a setting in which a data buyer seeks to estimate an unknown parameter by purchasing samples from one of K data sellers. Each seller has privately known data quality (e.g., high vs. low variance) and a private per-sample cost. We consider a multi-stage game in which the first stage is a free-trial stage in which the sellers have the option of signaling data quality by offering a few samples of data for free. Buyers update their beliefs based on the sample variance of the free data and then run a procurement auction to buy data in a second stage. For the auction stage, we characterize an approximately optimal Bayesian incentive compatible mechanism: the buyer selects a single seller by minimizing a belief-adjusted virtual cost and chooses the purchased sample size as a function of posterior quality and virtual cost. For the free-trial stage, we characterize the equilibrium, taking the above mechanism as the continuation game. Free trials may fail to emerge: for some parameters, all sellers reveal zero samples. However, under sufficiently strong competition (large K), there is an equilibrium in which sellers reveal the maximum allowable number of samples; in fact, it is the unique equilibrium.

Black hole mimickers (BHMs) are horizonless globally regular ultracompact relativistic self-gravitating objects (UCOs) of mass $M$ and radius $R$ with compactness $C = M/R$ higher than that of a neutron star and that produce an effective potential for null geodesics (photons) that possesses a local maximum, which is usually accompanied by an inner local minimum. The presence of a local maximum allows for unstable circular orbits to exist similar to light rings present in actual BH solutions, while it has been conjectured that the presence of a local minimum is symptomatic of potential instabilities. One such candidate for a BHM is a solitonic boson star (SBS) which is a boson star endowed with a sextic potential. In this paper we investigate further solutions of static and spherically symmetric SBSs in general relativity with a larger set of parameter values, and argue that such solutions are very similar to UCOs composed of an incompressible perfect fluid (IPF) with a sufficiently large pressure (the mimicker of a BHM). These IPFUCOs reach the Buchdahl limit $C= 4/9$ for arbitrarily large pressures. We investigate the extent to which the IPFUCOs constructed within a quadratic model in $f(R)$ gravity can overcome this limit or not, and thus pave the way for possibly building SBSs (or other kind of UCO) within this (or other alternative theory of gravity). We further elaborate about the stability properties of SBSs which have been the subject of some controversy recently.

Chirality in polymeric systems enables a wide range of emergent optical, mechanical, and transport phenomena, yet a unified framework that quantitatively connects molecular-scale geometry to chiral behavior remains lacking. Existing theoretical descriptions typically emphasize either continuum models, such as the helical wormlike chain (HWLC), which neglect intermolecular interactions, or mesophase-level theories, which obscure the role of molecular geometry. In this work, we introduce a comprehensive framework for quantifying chirality in helical polymers by extending the Kremer-Grest bead-spring model to explicitly map intrinsic curvature and torsion onto bond angle and dihedral potentials. We establish direct theoretical relationships between helical parameters such as pitch and radius, and connect them to a normalized, dimensionless chirality characteristic, $χ$ that captures local geometric correlations absent from conventional HWLC descriptions. Furthermore, using molecular dynamics simulations, we systematically quantify the influence of excluded volume interactions and thermal fluctuations on helical geometry and chirality, dispelling the common assumption that monotonic increases in chirality are associated only with decreasing pitch. Finally, we present a coarse-graining procedure that facilitates a direct comparison between experimental helical polymers and the Kremer-Grest helical chain, demonstrating quantitative agreement across a diverse set of polymer classes. This unified geometric and particle-based description provides a predictive roadmap for selecting and engineering chiral Kremer-Grest models and offers a general platform for designing polymeric materials with controlled and tunable chirality.

This article is a sequel to our previous paper (arXiv:2511.12311), where we considered the conceptual problem on the empirical laws for the Klein\textendash Gordon quantum field theory in curved spacetime (QFTCS), and we will consider the similar problems for the Majorana field on curved spacetime here. A ``law'' in theoretical physics is said to be observable or empirical only if it can be verified/falsified by some experimental procedure. The notion of empiricality/observability becomes far more unclear in QFTCS, than in QFT in Minkowski (flat) spacetime (QFTM), mainly because QFTCS lacks the notion of vacuum. This could potentially undermine the status of QFTCS as a physical (not only mathematical) theory. We consider this problem for the Majorana field in curved spacetime, and examine some examples of the empirical laws.

We explore the multimetric theory of gravitation, also known as multigravity. We derive additional new exact solutions for the theory in proportional Kerr-Schild and double Kerr-Schild forms. We extend several solutions from the theory of General Relativity, characterized by a constant Ricci scalar in single and double Kerr-Schild forms, to derive solutions in the multi-gravity context. We also examine and extend the classical double copy relations that can be constructed out from these solutions in multigravity exploring the dynamics of the single copy and zero copy fields.

A translational surface is a tensor product surface constructed from two space curves by translating one along the other. These surfaces are common within geometric modeling and, since their description is parametric, it is desirable to obtain the implicit equation of such a surface. These surfaces have been studied thoroughly by Goldman and Wang, where a particular set of syzygies was identified and shown to yield the implicit equation through an inhomogeneous resultant. As this method may fail in the presence of ill-behaved basepoints of the parameterization, we offer an alternative method in this article using iterated homogeneous resultants. The algorithm presented here involves smaller Sylvester matrices overall, potentially resulting in faster computation, and succeeds in many instances where the previous method cannot be applied.

In the context of asynchronous concurrent shared-memory systems, a snapshot algorithm allows failure-prone processes to concurrently and atomically write on the entries of a shared array MEM , and also atomically read the whole array. Recently, Read-Modify-Writable (RMWable) snapshot was proposed, a variant of snapshot that allows processes to perform operations more complex than just read and write, specifically, each entry MEM[k] is an arbitrary readable object. The known RMWable snapshot algorithms heavily rely on powerful low-level operations such as compare&swap or load-link/store-conditional to correctly produce snapshots of MEM. Following the large body of research devoted to understand the limits of what can be solved using the simple read/write low-level operations, which are known to be strictly weaker than compare&swap and load-link/store-conditional, we explore if RMWable snapshots are possible using only read/write operations. We present two read/write RMWable snapshot algorithms, the first one in the standard concurrent shared-memory model where the number of processes n is finite and known in advance, and the second one in a variant of the standard model with unbounded concurrency, where there are infinitely many processes, but at any moment only finitely many processes participate in an execution.

Recently, machine learning Hamiltonian (MLH) models have gained traction as fast approximations of electronic structures such as orbitals and electron densities, while also enabling direct evaluation of energies and forces from their predictions. However, despite their physical grounding, existing Hamiltonian models are evaluated mainly by reconstruction metrics, leaving it unclear how well they perform as energy-force predictors. We address this gap with a benchmark that computes energies and forces directly from predicted Hamiltonians. Within this framework, we propose QHFlow2, a state-of-the-art Hamiltonian model with an SO(2)-equivariant backbone and a two-stage edge update. QHFlow2 achieves $40\%$ lower Hamiltonian error than the previous best model with fewer parameters. Under direct evaluation on MD17/rMD17, it is the first Hamiltonian model to reach NequIP-level force accuracy while achieving up to $20\times$ lower energy MAE. On QH9, QHFlow2 reduces energy error by up to $20\times$ compared to MACE. Finally, we demonstrate that QHFlow2 exhibits consistent scaling behavior with respect to model capacity and data, and that improvements in Hamiltonian accuracy effectively translate into more accurate energy and force computations.

Plasma-based acceleration schemes have attracted sustained interest as a pathway toward compact particle accelerators, owing to the large electric fields supported by plasmas. Although recent studies have demonstrated the excitation of plasma wakefields using high-power microwave pulses in plasma-filled waveguides, the conditions required for efficient electron acceleration in such configurations remain insufficiently characterized. In this work, we investigate the acceleration of externally injected electrons by microwave-driven plasma wakefields in rectangular waveguides filled with low-density plasma. Three-dimensional particle-in-cell simulations are employed to analyze the dynamics of electron injection and energy gain under both reduced and fully self-consistent numerical models. The results show that electron acceleration is strongly dependent on the injection phase and initial velocity. Optimal acceleration is achieved when electrons are pre-accelerated to velocities close to the group velocity of the driving microwave pulse. For the parameters considered, energy gains of the order of $10^2 \mathrm{keV}$ are obtained over interaction lengths of the order of meters, while maintaining a quasi-monoenergetic energy distribution under suitable injection conditions. The influence of transverse dynamics and space-charge effects is also examined, revealing additional constraints on acceleration efficiency associated with the transverse electromagnetic field of the driving microwave pulse. These results provide a quantitative assessment of the acceleration stage in microwave-driven plasma wakefield schemes and support their evaluation as a viable platform for compact plasma-based accelerators.

Understanding information-dense documents like recipes and scientific papers requires readers to find, interpret, and connect details scattered across text, figures, tables, and other visual elements. These documents are often long and filled with specialized terminology, hindering the ability to locate relevant information or piece together related ideas. Existing tools offer limited support for synthesizing information across media types. As a result, understanding complex material remains cognitively demanding. This paper presents a framework for fine-grained integration of information in complex documents. We instantiate the framework in an augmented reading interface, which populates a scientific paper with clickable points on figures, interactive highlights in the body text, and a persistent reference panel for accessing consolidated details without manual scrolling. In a controlled between-subjects study, we find that participants who read the paper with our tool achieved significantly higher scores on a reading quiz without evidence of increased time to completion or cognitive load. Fine-grained integration provides a systematic way of revealing relationships within a document, supporting engagement with complex, information-dense materials.

In response to the exponential growth in the use of artificial intelligence and machine learning applications, educators, researchers and policymakers have taken steps to integrate artificial intelligence applications into K-12 education. Among these efforts, one equally important approach has received little, if any attention: What if students and teachers were not just learning to be competent users of AI but also its creators? This question is at the heart of CreateAI in which K12 educators, researchers, and learning scientists addressed the following questions: (1) What tools, skills, and knowledge will empower students and teachers to build their own AI/ML applications? (2) How can we integrate these approaches into classrooms? and (3) What new possibilities for learning emerge when students and teachers become innovators and creators? In the report we provide recommendations for what tools designed for creating AI/ML applications should address in terms of design features, and learner progression in investigations. To promote effective learning and teaching of creating AI applications, we also need to help students and teachers select appropriate tools. We outline how we need to develop a better understanding of learning practices and funds of knowledge to support youth as they create and evaluate AI/ML applications. This also includes engaging youth in learning about ethics and critically that is authentic, empowering, and relevant throughout the design process. Here we advocate for the integration of ethics in the curriculum. We also address what teachers need to know and how assessments can help establish baselines, include different instruments, and promote students as responsible creators of AI. Together, these recommendations provide important insights for preparing students to engage thoughtfully and critically with these technologies.

We investigate the collective dynamics of a three-level ensemble under the Dicke limit, revealing a unified connection between superradiant emission and electromagnetically induced transparency (EIT). Our results show that the transient superradiant burst exhibits the expected peak intensity scaling $I_{\max}\!\sim\! N^2$, with a universal finite-size correction $|ξ(N)-2|\!\sim\! 1/\ln N$ that governs the apparent scaling exponent in realistic ensembles. In the stationary regime, collective broadening modifies the EIT response: although it typically enhances absorption, it counterintuitively increases the group velocity, leading to a relative scaling $v_g\!\propto\! N^2$, even while $v_g\!\ll\! c$. This effect suggests that cooperative interactions fundamentally limit the achievable slow-light delay in dense media. To achieve these results, we derive a representative-atom master equation that quantitatively reproduces both the superradiant and EIT regimes, in excellent agreement with the exact symmetric-subspace dynamics and correctly incorporating collective feedback and $N$-dependent broadening. This unified framework bridges transient superradiant emission and steady-state quantum interference, with direct implications for slow light, quantum memories, and precision metrology.

The introduction of generative artificial intelligence applications to the public has led to heated discussions about its potential impacts and risks for K-12 education. One particular challenge has been to decide what students should learn about AI, and how this relates to computational thinking, which has served as an umbrella for promoting and introducing computing education in schools. In this paper, we situate in which ways we should expand computational thinking to include artificial intelligence and machine learning technologies. Furthermore, we discuss how these efforts can be informed by lessons learned from the last decade in designing instructional programs, integrating computing with other subjects, and addressing issues of algorithmic bias and justice in teaching computing in schools.

The Oberwolfach problem asks for a $2$-factorization of the complete graph in which each $2$-factor is isomorphic to a specific factor $F$. Recently, this problem has been extended to directed graphs. In this case, the directed Oberwolfach problem asks for a directed 2-factorization of the complete symmetric digraph in which each directed $2$-factor is isomorphic to a specific directed factor $F$. In this paper, we consider the directed Oberwolfach problem with directed 2-factors comprised of cycles of even lengths. Specifically, we provide a complete solution to this particular case when the order of the complete symmetric digraph is congruent to 2 modulo 4.