The exponential growth of scientific submissions has strained the peer review system. Despite the rapidly expanding global pool of researchers, this unprecedented scale has rendered the previous approach of manual expert identification unfeasible. Therefore, institutions have naturally turned to Large Language Models (LLMs) to automate intricate processes like expert reviewer identification. However, the reliability of these new models in accurately identifying domain experts lacks rigorous evaluation. We conduct a comprehensive empirical evaluation of statistical and AI-driven expertise identification methodologies to benchmark their reliability and limitations. Framing expert identification as an information retrieval problem, we utilize the distributed peer review system of a major international astronomical observatory, where proposal authorship serves as our proxy ground truth for domain expertise. Evaluating six retrieval methodologies utilized across observatories and computer science conferences, we demonstrate that traditional statistical representations outperform generative AI. Specifically, Term Frequency-Inverse Document Frequency successfully identified a labeled expert within the top 25 recommendations 79.5% of the time, compared to 51.5% for GPT-4o mini. Our results highlight that distinguishing subfield expertise requires fine-grained vocabulary, which is obscured by the semantic smoothing in generative methods. By establishing a rigorous evaluation framework for automated peer review, we demonstrate that transparent and reproducible statistical representations still outperform computationally expensive LLMs in specialized scientific tasks.

Orbital eccentricity in gravitational-wave signals from merging compact object binaries is a powerful indicator of their formation channel. Several binary black hole mergers and a neutron star--black hole merger have been reported to exhibit signs of eccentricity, but which events are identified and the significance of the eccentricity differs between studies. Measurements of eccentricity can change depending on the choice of prior. The choice of prior is subtle: eccentricity is commonly measured at an arbitrary reference frequency, which varies from study to study. We use the candidate eccentric neutron star--black hole merger GW200105_162426 as a case study, employing a range of priors and reference frequencies, and find the results to be strongly prior-driven. We show that the varied results reported across different studies can be partially reconciled by accounting for the evolution of eccentricity with reference frequency. In order to make conclusive statements about eccentricity, we propose a detection statistic that does not depend on reference frequency, and which marginalises over astrophysically-motivated distributions in eccentricity. Using this detection statistic, we find reduced support for the eccentric hypothesis for GW200105_162426: we obtain a natural log Bayes factor ln B $\leq$ 0.9 comparing the eccentric, aligned-spin hypothesis to the quasi-circular, precessing hypothesis. Our results cast doubt on the eccentric interpretation of GW200105_162426 and underscore the importance of modelling the astrophysical distributions of eccentricity in nature.

Pulse profile modelling via relativistic ray-tracing can constrain the system parameters of neutron stars, notably their mass and radius. Among these objects, accreting millisecond pulsars (AMPs) are promising targets, because they are bright in X-rays and their potentially polarized radiation can lead to complementary constraints on the emission geometry. We perform combined analysis of NICER and IXPE observations of the recently discovered the 448-Hz pulsar SRGA J144459.2-604207, with IXPE providing X-ray polarization information. NICER and IXPE jointly favour a large mass and radius for our best-fitting model, for which the neutron star has two independent hotspots. The primary hotspot is centered near the northern rotational pole, the secondary in the southern hemisphere, and the observer inclination is in the range 50-75 degrees. The primary hotspot is large (up to half the surface area) and contributes the majority of the non-pulsed X-rays, while the secondary is hotter and the major contributor to the overall pulse profile shape. However, many parameters are inferred to be near the prior bounds, which could indicate that the model does not adequately account for important physics. Furthermore, we tested several different methodologies for joint analysis of the two data sets: the results are sensitive to the method used, something that merits further study with synthetic data. In the future, we expect simultaneously recorded data will lead to improved parameter constraints, especially when multi-band and polarized data are combined.

Penrose's original heuristic for his eponymous spacetime inequality -- a conjectured lower bound on the ADM mass in terms of the area of a horizon cross-section -- relies on the black hole final state conjecture. In this paper we isolate a substantially weaker but precise late-time condition, which we call the quasi final state hypothesis and prove the spacetime Penrose inequality under this hypothesis. More precisely, for an asymptotically flat globally hyperbolic spacetime with a black-hole-type apparent horizon tube ${H}_{app}$ satisfying the dominant energy condition and the quasi final state hypothesis, we show that every asymptotically flat initial data set whose boundary is a MOTS cross-section of ${H}_{app}$ satisfies the spacetime Penrose inequality. The quasi final state hypothesis requires only a late-time decay condition on the normal component of the shift and the ratio of timelike to spacelike mean curvature, together with convergence of the cross-sectional areas of ${H}_{app}$ to a finite limit. Our approach is new and formulated directly in spacetime. The main geometric object is what we call a \emph{tangentially maximal} hypersurface, carrying a foliation by spacelike spheres whose timelike mean curvature vanishes. We show that these hypersurfaces are governed by a quasilinear inward-parabolic PDE, and we develop the corresponding a priori theory and prove global existence. On these hypersurfaces, the spacetime Hawking mass reduces to the Riemannian Hawking mass, and the dominant energy condition gives nonnegative scalar curvature. The Riemannian Penrose inequality, combined with the area laws for dynamical and isolated horizons, then yields the result.

The asymptotic rates of information-theoretic protocols - including error exponents, compression rates, and channel capacities - are traditionally defined under the idealised assumption that the underlying resource (state or channel) is independent and identically distributed (i.i.d.). Somewhat surprisingly, even slight departures from the exact i.i.d. structure can lead to a drastic breakdown of these protocols. The asymptotic rates of information theoretic protocols - error exponents, compression rates, capacities - were originally evaluated taking for granted that the underlying source (state or channel) is i.i.d. Differently from what we might expect at first glance, it is not hard to exhibit instances of protocols that may drastically fail when the i.i.d. assumption holds only approximately rather than exactly. If the precise nature of the perturbation from the i.i.d. regime is known (e.g. a pointwise defect), we could design a bespoke protocol that compensates for the defect (for example, by discarding the corrupted subsystem). However, in any realistic setting, neither can the i.i.d. behaviour of the system be precisely guaranteed, nor can the deviations from the ideal regime be determined exactly. In this paper we answer the following question: are there protocols that can still achieve the optimal asymptotic rates when the i.i.d. resource is replaced by any arbitrary almost i.i.d. resource along it? What is the nature of the unknown perturbation under which protocols like these are possible? We focus, in particular, on hypothesis testing, data compression, and channel coding. As a by-product of our analysis, we introduce the notion of club distance, as a variant of the well-known diamond distance, and of an almost i.i.d. process, which may be of independent interest.

We investigate the emergence of random-matrix statistics in the D1D5 CFT by studying second-order lifting matrices in low-energy near-BPS sectors. We compare the $N=3$ finite-$N$ lifting problems with the planar large-$N$ limit at fixed orbifold conformal weight and R charges. In the planar large-$N$ limit at fixed orbifold energy, mixing between single-cycle and multi-cycle states is suppressed, and the symmetry-resolved lifting spectra display Poisson-like level statistics. At finite $N$, non-planar terms restore this mixing between different cycle structures. Within the resulting symmetry-resolved sectors, this finite-$N$ mixing is accompanied by level repulsion consistent with random-matrix behavior. These results suggest that, in the low-energy near-BPS sectors accessible to our analysis, non-planar cycle-structure mixing at finite $N$ is associated with the onset of level repulsion and random-matrix-like spacing statistics.

Habitable Worlds Observatory (HWO) presents a key challenge for technology development in the coming years, requiring a $>$ $100\times$ more stable system than \textit{JWST}. WaveDriver is a concept for a laser guide star spacecraft coupled to an adaptive optics (AO) system onboard HWO that would enable HWO to reach its picometer-level wavefront stability requirements while relaxing other HWO subsystem requirements. At LLNL and UCSC we are revisiting the concept initially proposed by Douglas et al.\ (2019). We present key results key initial results from the first phase of our project, including (1) AO control developments, including with Linear Quadratic Gaussian control and machine learning, (2) AO wavefront sensor (WFS) trade study simulations, and (3) simulations of a photonic lantern natural guide star WFS. A key finding from our work is that WaveDriver could be needed to enable HWO's primary mirror segment stability and/or low order wavefront stability requirements.

We explore the sensitivity of the upcoming MAGIX experiment at the MESA facility to light Beyond the Standard Model (BSM) mediators in the few to hundred MeV mass range. Utilizing high-intensity electron beams of 55 MeV and 105 MeV on a heavy $^{181}\text{Ta}$ target, we investigate the production of scalar, pseudoscalar, vector, and axial vector mediators via the Bethe-Heitler process. By optimizing the asymmetric kinematic acceptance of the double-spectrometer setup to enhance the signal over background ratio, we demonstrate that MAGIX can probe mediator-electron couplings down to $\mathcal{O}(10^{-4})$, offering a competitive probe of the dark sector in the sub-GeV mass range.

Recent DESI BAO measurements, combined with CMB data, reveal a tension within the $Λ$CDM model that leads to a discrepancy between cosmological and laboratory bounds on the summed neutrino mass. We show that a recoupled interacting radiation component can alleviate this cosmological tension, as well as the one with neutrino oscillation experiments. Sterile neutrinos interacting through a light pseudoscalar mediator provide a concrete realization of this scenario. The resulting interacting fluid modifies the CMB phenomenology, lowers the preferred matter density, and improves the consistency between CMB and DESI BAO measurements. Combining CMB with DESI DR2 BAO measurements, we find a $2.7 σ$ preference for a nonzero interacting sterile neutrino component, $\nsp=0.253 \pm 0.094$, corresponding to an improvement $Δχ^2=-8.98$ relative to $Λ$CDM. The model also reduces the tension with the SH0ES determination of the Hubble constant to the $2.4σ$ level.

We address a fundamental question: Can one determine whether a received signal is squeezed when each copy arrives with a different displacement/amplitude? We introduce an interaction Hamiltonian that converts quadrature squeezing into number squeezing. Using this conversion, we test whether the copies satisfy $g^{(2)}(0)<1$. The Hamiltonian itself does not create nonclassicality; it only transfers it from quadrature squeezing to number squeezing. This allows us to identify squeezing even when individual copies have random displacements.

We describe the design, hardware integration, and calibration performance of the Wide-Field Imager (WFI) instruments for the Polarimeter to Unify the Corona and Heliosphere (PUNCH) mission. The WFI instruments are a trio of visible-light heliospheric imagers that, together, view the outer corona and solar wind from under 3.5° to over 47° from the Sun, via sunlight that is Thomson-scattered from free electrons. In flight, the WFIs are arranged so that their collective fields of view form an approximately symmetric trefoil on the sky, comprising three circular-truncated square fields spaced 120° apart in position angle. The WFIs work with the NFI instrument, described elsewhere, to implement the full PUNCH field spanning all solar position angles, at elongations from 1.5° to 47° from disk center. WFI is implemented using dioptric (lens) optics and deep multi-stage baffles that attenuate solar, planetary, and lunar stray light sufficiently for ground processing to reveal the faint signal for the primary science. WFI measures both total brightness (tB) and polarized brightness (pB), via an on-board polarizing filter wheel (PFW) and charge-coupled device (CCD) camera that share a common design with those of the NFI instrument.

The general idea of this paper is to start from a classical integrable (partial differential) equation which arises as a compatibility condition for a matrix linear differential problem. For definitiveness' sake, a generalised sinh-Gordon equation depending on $2N-1$ complex coefficients or moduli is considered. Then, the connexion coefficients (Wronskians) of different solutions to this problem satisfy, in the spirit of the Ordinary Differential Equation/Integrable Model correspondence, functional relations, which can be considered, -- if supplemented by suitable asymptotic behaviours --, as identifying a specific state of a quantum integrable model: in fact they are the eigenvalues of extensions of Baxter operators $Q$ and $T$, the transfer matrix. Moreover, Y-system and (implementing the asymptotic conditions) thermodynamic Bethe Ansatz equations originate from them, without any passage through the scattering theory, and providing an invariant parametrisation of the monodromy space. The crucial novelty is the modification of all the relations because of their dependence on the moduli. For zero momentum, they fully describe physically the quantum homogeneous sine-Gordon model, {\it i.e.} scattering amplitudes of gauge fields in $\mathcal{N} = 4$ SYM at strong coupling or their dual null polygonal light-like Wilson loops in $AdS_3$. As a direct consequence of the correspondence, two Zamolodchikov's conjectures, based on previous results, are also proven.

Integrated photonics has enabled a wide class of chip-scale light sources and quantum technologies. Within this field, microresonator-based degenerate optical parametric oscillators (DOPOs) have gained prominence. Above a critical power threshold, these systems undergo spontaneous symmetry breaking to settle into one of two stable, π-phase-shifted states -- a mechanism successfully used for quantum random number generation and photonic Ising machines. Here, we show that DOPOs based on the Kerr nonlinearity host a significantly broader range of nonlinear dynamics than previously explored. Using a silicon nitride microring resonator, we experimentally identify Hopf bifurcations that trigger a transition from stationary operation to self-sustained oscillations at MHz frequencies. By adjusting pump detunings and powers, we achieve turnkey control over these oscillatory regimes, navigating the system between stable binary states and periodic limit cycles. Furthermore, we report the experimental observation of period-doubling bifurcations, which numerical simulations reveal as the precursor to a cascading instability culminating in chaos at elevated pump powers. Our results establish a framework for controlling nonlinear instabilities in chip-scale parametric oscillators, with applications in programmable photonic hardware and dynamical optical computing.

Virtually all aspects of many-body atomic physics are challenging: experiments are technically demanding, datasets have become enormous, and the memory and CPU requirements for classical simulation of generic quantum systems often scale exponentially with system size. Machine learning (ML) methods are already assisting in each of these areas and are poised to become transformative. Here, we focus on two specific applications of ML to cold-atom-based quantum simulators. These devices generally generate data in the form of images; we first showcase denoising of raw images and then identify solitonic waves in Bose-Einstein condensates. In both of these examples, we comment on the interplay between performance, model complexity, and interpretability.

The influence of the Hall voltage on the photoluminescence of a dense hydrodynamic electron-hole plasma laser generated in a mesoscopic n-doped GaAs channel under intense laser excitation is studied. Laser excitation induces an interband current determined by the recombination of photogenerated electron-hole pairs. As a result, background electrons drifting under the influence of the Hall voltage form an effective Hall current. The Coulomb drag caused by the Hall current causes the accumulation of light holes, leading to the appearance of a double photoluminescence line formed by the recombination of excitons and trions. In contrast, in the absence of a Hall current, the shift in the photoluminescence energy associated with heavy holes occurs due to the electric field created by the Hall potential difference.

We present next-to-leading-order (NLO) QCD and electroweak (EW) results using the dimension-6 SMEFT for all 2- and 4- body Higgs decays, for $Z$ and $W$ decays along with the corresponding EW precision observables, and for the Higgstrahlung process $e^+e^-\rightarrow ZH$ at $\sqrt{s}=240$, $365$ and $500$ GeV. The results are presented in the POPxf format for ease of use in experimental and phenomenological studies. Of particular utility is the total Higgs width, including all dimension-6 contributions at NLO. In addition, we present the differential distributions $dΓ/dm_{Z*}$ for $H\rightarrow l^+l^- Z^*, Z^*\rightarrow l^+l^-$ at NLO in the SMEFT.

The distribution of entangled states is a core task for quantum networks facilitating quantum communication, and the use of multipartite entangled states comes with its own set of considerations. In this work, we analyze a quantum conference agreement protocol based on GHZ states in a network with a central station to which multiple clients are connected. Using comprehensive numerical simulations, we investigate how minor variations in the scenario-such as the number of parties, the number of memories, and asymmetric distances from the central station-can drastically influence the performance of the protocol. In particular, we demonstrate that it is crucial to adjust the strategy by optimizing cutoff times. From a broader perspective, we argue that numerical simulations are an indispensable tool for protocol design for devising realistic schemes for quantum communication.

Reconnections and rotations of lines are dual descriptions of the same saddle-shaped spacetime surface. We show that a reconnection between two line occurring over time is a single line that rotates over space progression. Both rotating lines and reconnections possess the same saddle shape sheet geometry in four-dimensional space-time, with different orientations. Cyclic precessing lines occurring over time are arrays of reconnections occurring spatially. We show that a magnetic reconnection occurring over time can be seen as a single continuous line vector potential rotating spatially, where the full evolution traces a saddle shape surface. Finally, we show that a single tilted spatiotemporal optical vortex precesses with spatial progression, and as a result can be seen as two vortices reconnecting. Given the unique spatiotemporal evolution, we also analyzed the relativistic angular momentum of these electromagnetic fields.

Interactions of relativistically intense laser pulses with structured targets have long been explored for controlling energy absorption and particle acceleration. However, at upcoming multi-petawatt laser facilities, the survivability of such nanostructures under realistic temporal contrast conditions remains a key concern. We report an experimental and simulation study of nanowire targets irradiated by the ELI-NP 1-PW laser without a plasma mirror. At the built in, readily available contrast of $10^{-10}$, the nanowires survive the laser pre-pulse and produce a robust enhancement in relativistic electron flux, energy, and directional emission compared to flat targets indicating that at better contrasts they can show similar enhancement at the 10 PW level. These results establish nanowire targets as resilient and reliable tools for relativistic electron manipulation at state of the art facilities.

We present new astrophysical parameters for the open cluster NGC~6793 based on new CCD $UBV(RI)_{KC}$ photometry. We derived a reddening of $E(B-V) = 0.24 \pm 0.02$~mag and a heavy element abundance of $Z = 0.024$ ($[Fe/H] = +0.20$~dex). Padova isochrone fitting to the $V \times (B-V)$ colour-magnitude diagram yields an intermediate age of $525 \pm 51$~Myr and a distance modulus of $μ= 8.80 \pm 0.05$~mag, corresponding to a distance of $d = 575 \pm 58$~pc from the Sun. The core radius of NGC~6793 appears to be shrinking due to advanced dynamical evolution ($\logτ_{2} = 1.13$), driven by mass segregation and the evaporation of low-mass stars from the central region. The ratios of core to half-mass radius ($R_{c}/R_{h}$) and half-mass to Jacobi radius ($R_{h}/R_{J}$) indicate that the cluster's evolution is governed by the combined effects of internal two-body relaxation, mass segregation, and external tidal perturbations. The ratio $R_{t}/R_{J} = 0.99$ suggests that the cluster is currently in a tidally filling state. The parameter pairs ($t_{diss}/t_{rlx_{1}} = 40$, $\log R_{J}/R_{c} = 0.72$) and ($R_{h}/R_{J} = 0.38$, $\logρ_{amb} = -0.88$) place NGC~6793 among the relatively compact clusters within $R_{GC} < 7.9$~kpc. This implies a compact internal structure that is stable against the combined effects of two-body encounters and tidal heating. Given its current state, NGC~6793 will likely dissolve and disperse before entering the final contraction phase ($R_{4}$ regime).

Atom-based quantum computing exploits the ability to enhance atom-atom interactions by employing laser excitation to higher-excited Rydberg states. Additional fields that drive transitions between Rydberg states can offer independent control of these atom-atom interactions. However, as microwave (mw) fields only provide access to states with similar principal quantum number $n$, their ability to switch the interactions' strength is limited. Here, we use a pulsed terahertz field to rapidly switch the strength of interactions between Rydberg atoms by three orders of magnitude. We demonstrate interaction switching using photon storage, where the terahertz field induces an interaction induced dephasing of the stored photon. This ability to switch interactions offers advantages for single-qubit readout, state-detection schemes, quantum annealing, and Rydberg quantum optics.

We present a new method for fast computation of the realization-dependent bias, a major computational bottleneck in measurements of the cosmic microwave background (CMB) lensing power spectrum. The method accelerates the bias calculation by differencing two correlated estimates: one based on fully realistic masked simulations and the other on isotropic simulations, for which the bias is analytically tractable. We show that our algorithm reduces the total computational cost of a lensing power spectrum measurement by approximately a factor of five for Atacama Cosmology Telescope- or Simons Observatory-like noise levels, or by a factor of three if current anisotropic filtering methods are left unchanged. Owing to its simplicity, the method can be readily implemented in existing CMB lensing analysis pipelines.

The Jaynes-Cummings (JC) interaction-the coherent exchange of excitations between a two-level system and a harmonic oscillator-is one of the fundamental interactions of quantum optics, realized across platforms such as cavity quantum electrodynamics, trapped ions, mechanical resonators, and superconducting circuits. Although JC interactions and qubit rotations form a universal gate set for oscillator control, practical implementations have not been demonstrated. Here we develop and experimentally demonstrate universal JC-based oscillator control by compiling arbitrary unitary gates into sequences of JC interactions and qubit rotations. In our experiment, the oscillator is realized using a mode of a high quality factor microwave cavity and the ancilla qubit using a superconducting transmon circuit, with the JC interaction implemented by a sideband interaction enabled by the Josephson nonlinearity. The native gates are constructed to be closed below a chosen cutoff photon number, encoding a qudit with suppressed leakage errors, while ancilla relaxation errors are detectable. We further find that the dispersive shift serves as a compilation resource that reduces circuit depths. We demonstrate universal qudit control and implement a single-qutrit gate set with a mean post-selected process fidelity of 96%, as well as ququart and ququint shift gates. These results establish Jaynes-Cummings control as a practical route to universal oscillator control, enabling programmable bosonic processors across a variety of quantum platforms.

Inverse problems are ubiquitous in modern scientific studies and involve recovering an underlying signal from noisy observations often transformed by a measurement operator. These problems are frequently ill-posed, particularly in imaging, leading to multiple plausible solutions and considerable uncertainty in reconstructed images. In fields like the physical and biological sciences, accurate uncertainty quantification (UQ) is critical for trustworthy scientific analyses and confident diagnoses. Current UQ methods for imaging often fall short; they can be inaccurate, or require unavailable or difficult-to-acquire ground truth data for calibration, which can introduce hidden biases due to distribution shifts between calibration and observed data. We introduce a UQ approach that leverages equivariant bootstrapping to generate heuristic coverages by exploiting data symmetries. We then refine these coverages through a conformal prediction calibration step, while crucially employing a self-supervised approach to avoid the need for ground truth calibration data. We demonstrate this method with weak lensing mass-mapping, where we aim to reconstruct the convergence field from shear measurements of distant galaxies weakly-lensed by gravitational fields. Mass-mapping in particular benefits from the self-supervised approach, as simulating calibration data is expensive and relies on specific cosmological models that could introduce biases in downstream cosmological inference tasks.

The defocusing nonlinear Schrödinger hydrodynamics supports exact dark solitons under finite density boundary conditions. However, the dark soliton gas, an interacting ensemble of dark solitons, has not yet been studied. In this work, we introduce an arbitrary-genus potential of dark soliton gases by considering the limit of the $\mathcal{N}$-dark soliton as $\mathcal{N}\to \infty$. The large-space asymptotics and long-time evolution of this dark soliton gas potential are analytically investigated through Deift-Zhou nonlinear steepest descent approach. The genus-$N$ dark soliton gas potential approaches the genus-$N$ finite-gap solution as $x \to -\infty$ and the background $1$ as $x \to +\infty$. In the long-time evolution, as the self-similar variable $ξ=x/t$ increases, the gas configuration exhibits a cascade of behaviours, passing from unmodulated and modulated genus-$N$ regions and progressively reducing the genus down to the planar region (unmodulated genus-$0$ region). Notably, the evolution of lower-genus soliton gases can be embedded within that of higher-genus gases, exhibiting identical dynamics within specific regimes. This phenomenon is encoded by the underlying spectra. We also include numerical validations, in perfect agreement with the theoretical predictions.

The Reeh-Schlieder theorem says that every target vector can be approximated from the vacuum by an operator localized in an arbitrarily small spacetime region, but it gives no quantitative cost for doing so. This note isolates a standard Tomita-Takesaki estimate as a model-independent preparation bound. Targets with deeply negative modular energy require large local operators. After rescaling such an operator to a physical contraction, the same estimate becomes a lower bound on postselection overhead. In geometries where the modular Hamiltonian is known, the bound becomes explicit. Bisognano-Wichmann turns it into a boost energy statement for wedges, and the Casini-Huerta-Myers formula gives a stress-tensor version for bounded regions of conformal field theories. Local unitaries can only reach states of nonnegative modular energy. Negative modular sectors require nonunitary or postselected outcomes, giving a preparation cost bound that complements vacuum embezzlement in type III local algebras.

The requirement of complete positivity is very often regarded as a fundamental consistency condition for the description of open quantum dynamics. We critically examine this requirement and discuss both its physical motivations and its limitations. We analyze proposals based on restricting the domain of non-completely positive maps to subsets of compatible initial states. Using isotropic states as a concrete example, we show that such domain restrictions become increasingly severe with growing system dimension, revealing an intrinsic weakness of the compatibility-based approach.

A quantitative understanding of the processes that trigger light-induced demagnetization on ultrashort timescales is crucial for achieving an ultrafast, radiation-controlled magnetic response in materials. This milestone is essential for developing next-generation magnetic storage devices and ultrafast magnetic switches. In this theoretical study, we investigated demagnetization triggered in a single magnetic domain by light pulses ranging from a few to a few tens of femtoseconds in duration, with photon energies spanning the optical and X-ray regimes, under strongly non-equilibrium conditions. We predicted a loss of magnetization in the sub-100-fs range in all cases, primarily due to the excitation of the electronic system and the subsequent redistribution of electrons within the magneto-sensitive band. The considered timescales were too short for phonon-mediated processes or inter-site Heisenberg exchange processes to contribute significantly. These findings pave the way for highly accurate, radiation-driven magnetization control in magnetic materials at sub-100-femtosecond timescales with potential practical applications.

Here we discuss direct links of the number of fundamental dimensions to the fundamental natural constants using simple arguments of dimensional analysis \corr{based on Maxwell's dimensions length (L), time (T) and mass (M) as well as the constants $G$, $c$, $\hbar$ and $e$}. We find that the \corr{form} of the fine-structure constant is a direct consequence of this connection. Additionally, our approach emphasises that gravity is a quite distinct area of physics which is not yet successfully quantised, i.e. not yet combined with quantum mechanics. We also discuss different unit systems based on dimensional analysis and natural constants.

Large Language Models (LLMs) are increasingly deployed as scientific AI as- sistants, and a growing body of benchmarks evaluates their capabilities across knowledge retrieval, reasoning, code generation, and tool use. These evaluations, however, typically assume the scientific problem is already well-posed, whereas practical scientific assistance often begins with an ill-posed user request that must be refined through dialogue before any computation, analysis, or experiment can be carried out reliably. We introduce SCICONVBENCH, a benchmark for multi- turn clarification in scientific task formulation across four computational science problem domains: fluid mechanics, solid mechanics, materials science, and par- tial differential equations (PDEs). SCICONVBENCH targets two complementary capabilities: eliciting missing information (disambiguation) and detecting and correcting erroneous requests containing internally contradictory information (in- consistency resolution). Our benchmark pairs a structured task ontology with a rubric-based evaluation framework, enabling systematic measurement of LLM per- formance across three dimensions: clarification behavior, conversational grounding, and final-specification fidelity. Current frontier models perform relatively well on inconsistency resolution, but even the best model resolves only 52.7% of the disambiguation cases in fluid mechanics. We further find that frontier LLMs fre- quently make silent assumptions and perform implicit specification repairs that are not grounded in the conversation with users. SCICONVBENCH establishes a foundation for evaluating the upstream conversational reasoning that a reliable computational science assistant requires. The code and data can be found at https://github.com/csml-rpi/SciConvBench.