Search

We introduce {\bf Swan}, a family of embedding models centred around the Arabic language, addressing both small-scale and large-scale use cases. Swan includes two variants: Swan-Small, based on ARBERTv2, and Swan-Large, built on ArMistral, a pretrained Arabic large language model. To evaluate these models, we propose ArabicMTEB, a comprehensive benchmark suite that assesses cross-lingual, multi-dialectal, multi-domain, and multi-cultural Arabic text embedding performance, covering eight diverse tasks and spanning 94 datasets. Swan-Large achieves state-of-the-art results, outperforming Multilingual-E5-large in most Arabic tasks, while the Swan-Small consistently surpasses Multilingual-E5-base. Our extensive evaluations demonstrate that Swan models are both dialectally and culturally aware, excelling across various Arabic domains while offering significant monetary efficiency. This work significantly advances the field of Arabic language modelling and provides valuable resources for future research and applications in Arabic natural language processing. Our models and benchmark will be made publicly accessible for research.

This study investigates the application of wave functions to explore various solutions of the Klein-Gordon and Schr\"{o}dinger equations within the framework of Lovelock gravity. We also present the derived Smarr formula from the topological density. The Klein-Gordon solution leads to the Wheeler-de Witt Hamiltonian and quasinormal modes, and we demonstrate the connection between the potential and the black hole temperature within the Schwarzschild limit. Additionally, we discuss different solutions of the Schr% \"{o}dinger equation, with one solution highlighting the influence of the Airy solution on the wave function's evolution over time., Comment: 20 pages, 5 figures

The KM3NeT Collaboration has tackled a common challenge faced by the astroparticle physics community, namely adapting the experiment-specific simulation software to work with the CORSIKA air shower simulation output. The proposed solution is an extension of the open-source code gSeaGen, allowing for the transport of muons generated by CORSIKA to a detector of any size at an arbitrary depth. The gSeaGen code was not only extended in terms of functionalities but also underwent a thorough redesign of the muon propagation routine, resulting in a more accurate and efficient simulation. This paper presents the capabilities of the new gSeaGen code as well as prospects for further developments., Comment: 27 pages, 13 figures

Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The extent of harm these attacks can produce in non-convex settings is still to be determined. Gradient attacks can affect far less systems than data poisoning but have been argued to be more harmful since they can be arbitrary, whereas data poisoning reduces the attacker's power to only being able to inject data points to training sets, via e.g. legitimate participation in a collaborative dataset. This raises the question of whether the harm made by gradient attacks can be matched by data poisoning in non-convex settings. In this work, we provide a positive answer in a worst-case scenario and show how data poisoning can mimic a gradient attack to perform an availability attack on (non-convex) neural networks. Through gradient inversion, commonly used to reconstruct data points from actual gradients, we show how reconstructing data points out of malicious gradients can be sufficient to perform a range of attacks. This allows us to show, for the first time, an availability attack on neural networks through data poisoning, that degrades the model's performances to random-level through a minority (as low as 1%) of poisoned points., Comment: 8 pages, 10 figures

In this paper, we investigate the existence and uniqueness of solutions for the following model problem, involving singularities and inhomogeneous Robin boundary conditions \begin{equation*} \left\{ \begin{array}{ll} -\Delta_{p}u_{p}=\frac{f}{u_{p}^{\gamma}}& \hbox{in $\Omega,$} \frac{\partial u_{p}}{\partial \sigma}+\lambda\vert u_{p}\vert^{p-2} u_{p}+\vert u_{p}\vert^{s-1}u_{p}=\frac{g}{u_{p}^{\eta}} & \hbox{on $\partial\Omega,$} \end{array} \right. \end{equation*} where $\Omega \subset \mathbb{R}^{m}$ represents an open bounded domain, with smooth boundary, $m \geq 2$, the symbol $\sigma $ stands for the unit outward normal vector, $ \Delta_{p}u:=\mbox{div}(\vert\nabla u\vert^{p-2}\nabla u) $ is the $p-$Laplacian operator $(1\leq p0$ and $s\geq 1.$ The function $ f\in L^{\frac{m}{p}}(\Omega)$ is a nonnegative additionally $ \lambda$ and $ g$ are nonnegative functions in $L^{\infty}(\partial \Omega).$

``When a measure becomes a target, it ceases to be a good measure'', this adage is known as {\it Goodhart's law}. In this paper, we investigate formally this law and prove that it critically depends on the tail distribution of the discrepancy between the true goal and the measure that is optimized. Discrepancies with long-tail distributions favor a Goodhart's law, that is, the optimization of the measure can have a counter-productive effect on the goal. We provide a formal setting to assess Goodhart's law by studying the asymptotic behavior of the correlation between the goal and the measure, as the measure is optimized. Moreover, we introduce a distinction between a {\it weak} Goodhart's law, when over-optimizing the metric is useless for the true goal, and a {\it strong} Goodhart's law, when over-optimizing the metric is harmful for the true goal. A distinction which we prove to depend on the tail distribution. We stress the implications of this result to large-scale decision making and policies that are (and have to be) based on metrics, and propose numerous research directions to better assess the safety of such policies in general, and to the particularly concerning case where these policies are automated with algorithms., Comment: 47 pages, 11 figures

Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only high-quality data based on a score function (human or machine feedback). Previous work Feng et al. (2024) analyzed models trained on synthetic data as sample size increases. We extend this by using random matrix theory to derive the performance of a binary classifier trained on a mix of real and pruned synthetic data in a high dimensional setting. Our findings identify conditions where synthetic data could improve performance, focusing on the quality of the generative model and verification strategy. We also show a smooth phase transition in synthetic label noise, contrasting with prior sharp behavior in infinite sample limits. Experiments with toy models and large language models validate our theoretical results.

Dataset ownership verification, the process of determining if a dataset is used in a model's training data, is necessary for detecting unauthorized data usage and data contamination. Existing approaches, such as backdoor watermarking, rely on inducing a detectable behavior into the trained model on a part of the data distribution. However, these approaches have limitations, as they can be harmful to the model's performances or require unpractical access to the model's internals. Most importantly, previous approaches lack guarantee against false positives. This paper introduces data taggants, a novel non-backdoor dataset ownership verification technique. Our method uses pairs of out-of-distribution samples and random labels as secret keys, and leverages clean-label targeted data poisoning to subtly alter a dataset, so that models trained on it respond to the key samples with the corresponding key labels. The keys are built as to allow for statistical certificates with black-box access only to the model. We validate our approach through comprehensive and realistic experiments on ImageNet1k using ViT and ResNet models with state-of-the-art training recipes. Our findings demonstrate that data taggants can reliably make models trained on the protected dataset detectable with high confidence, without compromising validation accuracy, and demonstrates superiority over backdoor watermarking. Moreover, our method shows to be stealthy and robust against various defense mechanisms., Comment: 16 pages, 7 figures

Morocco's Vision 2030, known as Maroc Digital 2030, aims to position the country as a regional leader in digital technology by boosting digital infrastructure, fostering innovation, and advancing digital skills. Complementing this initiative, the Pacte ESRI 2030 strategy, launched in 2023, seeks to transform the higher education, research, and innovation sectors by integrating state-of-the-art digital technologies. In alignment with these national strategies, this paper introduces BlockMEDC, a blockchain-based system for securing and managing Moroccan educational digital certificates. Leveraging Ethereum smart contracts and the InterPlanetary File System, BlockMEDC automates the issuance, management, and verification of academic credentials across Moroccan universities. The proposed system addresses key issues such as document authenticity, manual verification, and lack of interoperability, delivering a secure, transparent, and cost-effective solution that aligns with Morocco's digital transformation goals for the education sector.

In spite of the recent progress in speech processing, the majority of world languages and dialects remain uncovered. This situation only furthers an already wide technological divide, thereby hindering technological and socioeconomic inclusion. This challenge is largely due to the absence of datasets that can empower diverse speech systems. In this paper, we seek to mitigate this obstacle for a number of Arabic dialects by presenting Casablanca, a large-scale community-driven effort to collect and transcribe a multi-dialectal Arabic dataset. The dataset covers eight dialects: Algerian, Egyptian, Emirati, Jordanian, Mauritanian, Moroccan, Palestinian, and Yemeni, and includes annotations for transcription, gender, dialect, and code-switching. We also develop a number of strong baselines exploiting Casablanca. The project page for Casablanca is accessible at: www.dlnlp.ai/speech/casablanca.

Image similarity metrics play an important role in computer vision applications, as they are used in image processing, computer vision and machine learning. Furthermore, those metrics enable tasks such as image retrieval, object recognition and quality assessment, essential in fields like healthcare, astronomy and surveillance. Existing metrics, such as PSNR, MSE, SSIM, ISSM and FSIM, often face limitations in terms of either speed, complexity or sensitivity to small changes in images. To address these challenges, a novel image similarity metric, namely CSIM, that combines real-time while being sensitive to subtle image variations is investigated in this paper. The novel metric uses Gaussian Copula from probability theory to transform an image into vectors of pixel distribution associated to local image patches. These vectors contain, in addition to intensities and pixel positions, information on the dependencies between pixel values, capturing the structural relationships within the image. By leveraging the properties of Copulas, CSIM effectively models the joint distribution of pixel intensities, enabling a more nuanced comparison of image patches making it more sensitive to local changes compared to other metrics. Experimental results demonstrate that CSIM outperforms existing similarity metrics in various image distortion scenarios, including noise, compression artifacts and blur. The metric's ability to detect subtle differences makes it suitable for applications requiring high precision, such as medical imaging, where the detection of minor anomalies can be of a high importance. The results obtained in this work can be reproduced from this Github repository: https://github.com/safouaneelg/copulasimilarity., Comment: This work has been submitted to the IEEE for possible publication

Neutrinos described as an open quantum system may interact with the environment which introduces stochastic perturbations to their quantum phase. This mechanism leads to a loss of coherence along the propagation of the neutrino $-$ a phenomenon commonly referred to as decoherence $-$ and ultimately, to a modification of the oscillation probabilities. Fluctuations in space-time, as envisaged by various theories of quantum gravity, are a potential candidate for a decoherence-inducing environment. Consequently, the search for decoherence provides a rare opportunity to investigate quantum gravitational effects which are usually beyond the reach of current experiments. In this work, quantum decoherence effects are searched for in neutrino data collected by the KM3NeT/ORCA detector from January 2020 to November 2021. The analysis focuses on atmospheric neutrinos within the energy range of a few GeV to $100\,\mathrm{GeV}$. Adopting the open quantum system framework, decoherence is described in a phenomenological manner with the strength of the effect given by the parameters $\Gamma_{21}$ and $\Gamma_{31}$. Following previous studies, a dependence of the type $\Gamma_{ij} \propto (E/E_0)^n$ on the neutrino energy is assumed and the cases $n = -2,-1$ are explored. No significant deviation with respect to the standard oscillation hypothesis is observed. Therefore, $90\,\%$ CL upper limits are estimated as $\Gamma_{21} < 4.6\cdot 10^{-21}\,$GeV and $\Gamma_{31} < 8.4\cdot 10^{-21}\,$GeV for $n = -2$, and $\Gamma_{21} < 1.9\cdot 10^{-22}\,$GeV and $\Gamma_{31} < 2.7\cdot 10^{-22}\,$GeV for $n = -1$, respectively., Comment: 17 pages, 5 figures

The spin structure functions of the proton and the deuteron were measured during the EG4 experiment at Jefferson Lab in 2006. Data were collected for longitudinally polarized electron scattering off longitudinally polarized NH$_3$ and ND$_3$ targets, for $Q^2$ values as small as 0.012 and 0.02 GeV$^2$, respectively, using the CEBAF Large Acceptance Spectrometer (CLAS). This is the archival paper of the EG4 experiment that summaries the previously reported results of the polarized structure functions $g_1$, $A_1F_1$, and their moments $\overline \Gamma_1$, $\overline \gamma_0$, and $\overline I_{TT}$, for both the proton and the deuteron. In addition, we report on new results on the neutron $g_1$ extracted by combining proton and deuteron data and correcting for Fermi smearing, and on the neutron moments $\overline \Gamma_1$, $\overline \gamma_0$, and $\overline I_{TT}$ formed directly from those of the proton and the deuteron. Our data are in good agreement with the Gerasimov-Drell-Hearn sum rule for the proton, deuteron, and neutron. Furthermore, the isovector combination was formed for $g_1$ and the Bjorken integral $\overline \Gamma_1^{p-n}$, and compared to available theoretical predictions. All of our results provide for the first time extensive tests of spin observable predictions from chiral effective field theory ($\chi$EFT) in a $Q^2$ range commensurate with the pion mass. They motivate further improvement in $\chi$EFT calculations from other approaches such as the lattice gauge method., Comment: 33 pages. 26 figures. Data table provided in supplementary material (30 pages)

An alternative to the dependence on traditional student loans may offer a viable relief from the tremendous burden that those loans usually incur. This article establishes that it is desirable for governmental intervention to grant students 'more choice' in their funding decisions by allowing them to have portfolios, mixtures of different types of loans. To emphasize this point, a model is presented of a situation where students invest in higher education while facing uncertainty about their individual earning potential. The model reveals that when students are allowed to have portfolios of loans, some of them indeed take the opportunity and diversify their loans, benefiting themselves, but also improving the loan terms of other students. Therefore, when governments organize student loans, they should consider providing students with more choice in their funding decisions.

Underground forums serve as hubs for cybercriminal activities, offering a space for anonymity and evasion of conventional online oversight. In these hidden communities, malicious actors collaborate to exchange illicit knowledge, tools, and tactics, driving a range of cyber threats from hacking techniques to the sale of stolen data, malware, and zero-day exploits. Identifying the key instigators (i.e., key hackers), behind these operations is essential but remains a complex challenge. This paper presents a novel method called EUREKHA (Enhancing User Representation for Key Hacker Identification in Underground Forums), designed to identify these key hackers by modeling each user as a textual sequence. This sequence is processed through a large language model (LLM) for domain-specific adaptation, with LLMs acting as feature extractors. These extracted features are then fed into a Graph Neural Network (GNN) to model user structural relationships, significantly improving identification accuracy. Furthermore, we employ BERTopic (Bidirectional Encoder Representations from Transformers Topic Modeling) to extract personalized topics from user-generated content, enabling multiple textual representations per user and optimizing the selection of the most representative sequence. Our study demonstrates that fine-tuned LLMs outperform state-of-the-art methods in identifying key hackers. Additionally, when combined with GNNs, our model achieves significant improvements, resulting in approximately 6% and 10% increases in accuracy and F1-score, respectively, over existing methods. EUREKHA was tested on the Hack-Forums dataset, and we provide open-source access to our code., Comment: Accepted at IEEE Trustcom 2024

Entanglement serves as a core resource for quantum information technologies, including applications in quantum cryptography, quantum metrology, and quantum communication. In this study, we give a unifying description of the stationary bipartite and tripartite entanglement in a coupled optomechanical ring cavity comprising photon and phonon modes. We numerically analyze the stationary entanglement between the optical mode and each mechanical mode, as well as between the two mechanical modes, using the logarithmic negativity. Our results demonstrate that mechanical entanglement between the two mechanical modes is highly dependent on the optical normalized detuning and the mechanical coupling strength, with entanglement maximized within specific detuning intervals and increased coupling broadening the effective range. Furthermore, we study the entanglement's sensitivity to temperature, noting that higher coupling strengths can sustain entanglement at elevated temperatures. The study also reveals that the entanglement between the mechanical mode and the optical mode is enhanced with increasing laser power, but is similarly susceptible to thermal noise. Additionally, we explore tripartite entanglement through the minimum residual contangle, highlighting its dependence on detuning, temperature, and laser power. Our findings underscore the importance of parameter control in optimizing entanglement for quantum information processing applications.

This paper introduces a novel approach to urban pathfinding by transforming traditional heuristic-based algorithms into deep learning models that leverage real-time contextual data, such as traffic and weather conditions. We propose two methods: an enhanced A* algorithm that dynamically adjusts routes based on current environmental conditions, and a neural network model that predicts the next optimal path segment using historical and live data. An extensive benchmark was conducted to compare the performance of different deep learning models, including MLP, GRU, LSTM, Autoencoders, and Transformers. Both methods were evaluated in a simulated urban environment in Berlin, with the neural network model outperforming traditional methods, reducing travel times by up to 40%, while the enhanced A* algorithm achieved a 34% improvement. These results demonstrate the potential of deep learning to optimize urban navigation in real time, providing more adaptable and efficient routing solutions.

Multispectral pedestrian detection has gained significant attention in recent years, particularly in autonomous driving applications. To address the challenges posed by adversarial illumination conditions, the combination of thermal and visible images has demonstrated its advantages. However, existing fusion methods rely on the critical assumption that the RGB-Thermal (RGB-T) image pairs are fully overlapping. These assumptions often do not hold in real-world applications, where only partial overlap between images can occur due to sensors configuration. Moreover, sensor failure can cause loss of information in one modality. In this paper, we propose a novel module called the Hybrid Attention (HA) mechanism as our main contribution to mitigate performance degradation caused by partial overlap and sensor failure, i.e. when at least part of the scene is acquired by only one sensor. We propose an improved RGB-T fusion algorithm, robust against partial overlap and sensor failure encountered during inference in real-world applications. We also leverage a mobile-friendly backbone to cope with resource constraints in embedded systems. We conducted experiments by simulating various partial overlap and sensor failure scenarios to evaluate the performance of our proposed method. The results demonstrate that our approach outperforms state-of-the-art methods, showcasing its superiority in handling real-world challenges., Comment: Accepted for publication in IEEE Robotics and Automation Letters, October 2024

We introduce Agent K v1.0, an end-to-end autonomous data science agent designed to automate, optimise, and generalise across diverse data science tasks. Fully automated, Agent K v1.0 manages the entire data science life cycle by learning from experience. It leverages a highly flexible structured reasoning framework to enable it to dynamically process memory in a nested structure, effectively learning from accumulated experience stored to handle complex reasoning tasks. It optimises long- and short-term memory by selectively storing and retrieving key information, guiding future decisions based on environmental rewards. This iterative approach allows it to refine decisions without fine-tuning or backpropagation, achieving continuous improvement through experiential learning. We evaluate our agent's apabilities using Kaggle competitions as a case study. Following a fully automated protocol, Agent K v1.0 systematically addresses complex and multimodal data science tasks, employing Bayesian optimisation for hyperparameter tuning and feature engineering. Our new evaluation framework rigorously assesses Agent K v1.0's end-to-end capabilities to generate and send submissions starting from a Kaggle competition URL. Results demonstrate that Agent K v1.0 achieves a 92.5\% success rate across tasks, spanning tabular, computer vision, NLP, and multimodal domains. When benchmarking against 5,856 human Kaggle competitors by calculating Elo-MMR scores for each, Agent K v1.0 ranks in the top 38\%, demonstrating an overall skill level comparable to Expert-level users. Notably, its Elo-MMR score falls between the first and third quartiles of scores achieved by human Grandmasters. Furthermore, our results indicate that Agent K v1.0 has reached a performance level equivalent to Kaggle Grandmaster, with a record of 6 gold, 3 silver, and 7 bronze medals, as defined by Kaggle's progression system.

Finding correspondences between 3D shapes is an important and long-standing problem in computer vision, graphics and beyond. While approaches based on machine learning dominate modern 3D shape matching, almost all existing (learning-based) methods require that at least one of the involved shapes is complete. In contrast, the most challenging and arguably most practically relevant setting of matching partially observed shapes, is currently underexplored. One important factor is that existing datasets contain only a small number of shapes (typically below 100), which are unable to serve data-hungry machine learning approaches, particularly in the unsupervised regime. In addition, the type of partiality present in existing datasets is often artificial and far from realistic. To address these limitations and to encourage research on these relevant settings, we provide a generic and flexible framework for the procedural generation of challenging partial shape matching scenarios. Our framework allows for a virtually infinite generation of partial shape matching instances from a finite set of shapes with complete geometry. Further, we manually create cross-dataset correspondences between seven existing (complete geometry) shape matching datasets, leading to a total of 2543 shapes. Based on this, we propose several challenging partial benchmark settings, for which we evaluate respective state-of-the-art methods as baselines.

We prove that, on the $\mathrm{SL}(3,\mathbb R)$ Hitchin component, the Goldman symplectic form and the Labourie-Loftin complex structure are compatible and together determine a (mapping class group invariant) pseudo-K\"ahler structure.

The pursuit of realism in cinema has driven significant advancements in animatronics, where the integration of mechatronics, a multidisciplinary field that combines mechanical engineering, electronics, and computer science, plays a pivotal role in enhancing the functionality and realism of animatronics. This interdisciplinary approach facilitates smoother characters movements and enhances the sophistication of behaviors in animatronic creatures, thereby increasing their realism. This article examines the most recent developments in mechatronic technology and their significant impact on the art and engineering of animatronics in the filmmaking. It explores the sophisticated integration of system components and analyzes how these enhancements foster complexity and integration, crucial for achieving unprecedented levels of realism in modern cinema. Further, the article delves into in-depth case studies of well-known movie characters, demonstrating the practical applicability of these state-of-the-art mechatronic solutions in creating compelling, lifelike cinematic experiences. This paper aims to bridge the gap between the technical aspects of mechatronics and the creative demands of the film industry, ultimately contributing to the ongoing evolution of cinematic realism.

A new class of Multi-Rotor Aerial Vehicles (MRAVs), known as omnidirectional MRAVs (o-MRAVs), has attracted significant interest in the robotics community. These MRAVs have the unique capability of independently controlling their 3D position and 3D orientation. In the context of aerial communication networks, this translates into the ability to control the position and orientation of the antenna mounted on the MRAV without any additional devices tasked for antenna orientation. This additional Degrees of Freedom (DoF) adds a new dimension to aerial communication systems, creating various research opportunities in communications-aware trajectory planning and positioning. This paper presents this new class of MRAVs and discusses use cases in areas such as physical layer security and optical communications. Furthermore, the benefits of these MRAVs are illustrated with realistic simulation scenarios. Finally, new research problems and opportunities introduced by this advanced robotics technology are discussed., Comment: Accepted for IEEE Communications Magazine. \c{opyright}2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media

Choices in the semantics and the signature of a theory are integral in determining how the theory is used and how challenging it is to reason over it. Our interest in this paper lies in the SMT theory of sequences. Various versions of it exist in the literature and in state-of-the-art SMT solvers, but it has not yet been standardized in the SMT-LIB. We reflect on its existing variants, and we define a set of theory design criteria to help determine what makes one variant of a theory better than another. The criteria we define can be used to appraise theory proposals for other theories as well. Based on these criteria, we propose a series of changes to the SMT theory of sequences as a contribution to the discussion regarding its standardization.

Graph Signal Processing (GSP) provides a powerful framework for analysing complex, interconnected systems by modelling data as signals on graphs. Recent advances in GSP have enabled the learning of graph structures from observed signals, but these methods often struggle with time-varying systems and real-time applications. Adaptive filtering techniques, while effective for online learning, have seen limited application in graph topology estimation from a GSP perspective. To this end, we introduce AdaCGP, an online algorithm for adaptive estimation of the Graph Shift Operator (GSO) from multivariate time series. The GSO is estimated from an adaptive time-vertex autoregressive model through recursive update formulae designed to address sparsity, shift-invariance and bias. Through simulations, we show that AdaCGP performs consistently well across various graph topologies, and achieves improvements in excess of 82% for GSO estimation compared to baseline adaptive vector autoregressive models. In addition, our online variable splitting approach for enforcing sparsity enables near-perfect precision in identifying causal connections while maintaining low false positive rates upon optimisation of the forecast error. Finally, AdaCGP's ability to track changes in graph structure is demonstrated on recordings of ventricular fibrillation dynamics in response to an anti-arrhythmic drug. AdaCGP is shown to be able to identify the stability of critical conduction patterns that may be maintaining the arrhythmia in an intuitive way, together with its potential to support diagnosis and treatment strategies.

Large language models (LLMs) excel in tasks requiring processing and interpretation of input text. Abstract screening is a labour-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies identified by a literature search. Here, LLMs (GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o, Llama 3 70B, Gemini 1.5 Pro, and Claude Sonnet 3.5) were trialled on systematic reviews in a full issue of the Cochrane Library to evaluate their accuracy in zero-shot binary classification for abstract screening. Trials over a subset of 800 records identified optimal prompting strategies and demonstrated superior performance of LLMs to human researchers in terms of sensitivity (LLMmax = 1.000, humanmax = 0.775), precision (LLMmax = 0.927, humanmax = 0.911), and balanced accuracy (LLMmax = 0.904, humanmax = 0.865). The best performing LLM-prompt combinations were trialled across every replicated search result (n = 119,691), and exhibited consistent sensitivity (range 0.756-1.000) but diminished precision (range 0.004-0.096). 66 LLM-human and LLM-LLM ensembles exhibited perfect sensitivity with a maximal precision of 0.458, with less observed performance drop in larger trials. Significant variation in performance was observed between reviews, highlighting the importance of domain-specific validation before deployment. LLMs may reduce the human labour cost of systematic review with maintained or improved accuracy and sensitivity. Systematic review is the foundation of evidence-based medicine, and LLMs can contribute to increasing the efficiency and quality of this mode of research., Comment: RS and AJT are joint-first authors

In June 2022, the Gaia mission released a catalog of astrometric orbital solutions for 168,065 binary systems, by far the largest such catalog to date. Unlike previous binary stars catalogs, which were heterogeneous collections of orbits from different surveys and instruments, these orbits were derived using Gaia data alone. Despite this homogeneity, the selection function is difficult to characterize because of choices made in the construction of the catalog. Understanding the catalog's selection function is required to model and interpret its contents. We use a combination of analytic and empirical prescriptions to construct a function that computes the probability that a binary with a given set of properties would have been published in the Gaia Data Release 3 astrometric orbit catalog. We also construct a binary population synthesis model based on Moe & Di Stefano (2017) to validate our characterization of the selection function, finding good agreement with the actual Gaia NSS catalog, with the exception of the orbital eccentricity distribution. The NSS catalog suggests high-eccentricity orbits are relatively uncommon at intermediate periods $100 \lesssim P_{orb} \lesssim 1000$ days. As an example application of the selection function, we estimate the Gaia DR3 detection probabilities of the star + BH binaries Gaia BH1, BH2, and BH3. We also estimate the population of Sun-like star + BH binaries in the Galaxy to be $\sim 5000$ for $100 < P_{orb} < 400$ day, $\lesssim 2,000$ for $400 < P_{orb} < 1000$ day, and $ \lesssim 20,000$ for $1000 < P_{orb} < 2000$ days., Comment: 24 pages, 14 figures, 2 appendices. Submitted to ApJ, comments welcome. Selection function code will be available here: https://github.com/caseylam/dr3_nss_ast_orbits_selection

In this work, we explore modeling change points in time-series data using neural stochastic differential equations (neural SDEs). We propose a novel model formulation and training procedure based on the variational autoencoder (VAE) framework for modeling time-series as a neural SDE. Unlike existing algorithms training neural SDEs as VAEs, our proposed algorithm only necessitates a Gaussian prior of the initial state of the latent stochastic process, rather than a Wiener process prior on the entire latent stochastic process. We develop two methodologies for modeling and estimating change points in time-series data with distribution shifts. Our iterative algorithm alternates between updating neural SDE parameters and updating the change points based on either a maximum likelihood-based approach or a change point detection algorithm using the sequential likelihood ratio test. We provide a theoretical analysis of this proposed change point detection scheme. Finally, we present an empirical evaluation that demonstrates the expressive power of our proposed model, showing that it can effectively model both classical parametric SDEs and some real datasets with distribution shifts.

We present some regularity results on the gradient of the weak or entropic-renormalized solution $u$ to the homogeneous Dirichlet problem for the quasilinear equations of the form \begin{equation*}\label{p-laplacian_eq} -{\rm div~}(|\nabla u|^{p-2}\nabla u)+V(x;u)=f, \end{equation*} where $\Omega$ is a bounded smooth domain of $\mathbb R^n$, $V$ is a nonlinear potential and $f$ belongs to non-standard spaces like Lorentz-Zygmund spaces. Moreover, we collect some well-known and new results for identifying some interpolation spaces and enrich some contents with details.

Magnetic Tunnel Junctions (MTJs) are of great interest for non-conventional computing applications. The Toffoli gate is a universal reversible logic gate, enabling the construction of arbitrary boolean circuits. Here, we present a proof-of-concept construction of a gadget which encodes the Toffoli gate's truth table into the ground state of coupled uniaxial nanomagnets that could form the free layers of perpendicularly magnetized MTJs. This construction has three input bits, three output bits, and one ancilla bit. We numerically simulate the seven macrospins evolving under the stochastic Landau-Lifshitz-Gilbert (s-LLG) equation. We investigate the effect of the anisotropy-to-exchange-coupling strength ratio $H_A/H_\text{ex}$ on the working of the gadget. We find that for $H_A/H_\text{ex} \lesssim 0.93$, the spins evolve to the Toffoli gate truth table configurations under LLG dynamics alone, while higher $H_A/H_\text{ex}$ ratios require thermal annealing due to suboptimal metastable states. Under our chosen annealing procedure, the s-LLG simulation with thermal annealing achieves a 100% success rate up to $H_A/H_\text{ex}\simeq3.0$. The feasibility of constructing MTJ-free-layer-based Toffoli gates highlights their potential in designing new types of MTJ-based circuits.

We calculate the quark self-energy correction in light-cone gauge motivated by distribution amplitudes whose definition implies a Wilson line. The latter serves to preserve the gauge invariance of the hadronic amplitudes and becomes trivial in light-cone gauge. Therefore, the calculation of the distribution amplitudes simplifies significantly provided that wave functions and propagators are obtained in that gauge. In here, we explore the corresponding Dyson-Schwinger equation in its leading truncation and with a dressed vertex derived from a Ward identity in light-cone gauge. The quark's mass and wave renormalization functions, as well as a third complex-valued amplitude, are found to depend on the relative orientation of the quark momentum and a light-like four-vector, which expresses a geometric gauge dependence of the propagator., Comment: 9 pages, 6 figures

Astrometry from Gaia DR3 has produced a sample of $\sim$170,000 Keplerian orbital solutions, with many more anticipated in the next few years. These data have enormous potential to constrain the population of binary stars, giant planets, and compact objects in the Solar neighborhood. But in order to use the published orbit catalogs for statistical inference, it is necessary to understand their selection function: what is the probability that a binary with a given set of properties ends up in a catalog? We show that such a selection function for the Gaia DR3 astrometric binary catalog can be forward-modeled from the Gaia scanning law, including individual 1D astrometric measurements, the fitting of a cascade of astrometric models, and quality cuts applied in post-processing. We populate a synthetic Milky Way model with binary stars and generate a mock catalog of astrometric orbits. The mock catalog is quite similar to the DR3 astrometric binary sample, suggesting that our selection function is a sensible approximation of reality. Our fitting also produces a sample of spurious astrometric orbits similar to those found in DR3; these are mainly the result of scan angle-dependent astrometric biases in marginally resolved wide binaries. We show that Gaia's sensitivity to astrometric binaries falls off rapidly at high eccentricities, but only weakly at high inclinations. We predict that DR4 will yield $\sim 1$ million astrometric orbits, mostly for bright ($G \lesssim 15$) systems with long periods ($P_{\rm orb} \gtrsim 1000$ d). We provide code to simulate and fit realistic Gaia epoch astrometry for any data release and determine whether any hypothetical binary would receive a cataloged orbital solution., Comment: 22 pages, 17 figures, accepted to OJAp. Code at https://github.com/kareemelbadry/gaiamock

An important and often overlooked aspect of particle filtering methods is the estimation of unknown static parameters. A simple approach for addressing this problem is to augment the unknown static parameters as auxiliary states that are jointly estimated with the time-varying parameters of interest. This can be impractical, especially when the system of interest is high-dimensional. Multiple particle filtering (MPF) methods were introduced to try to overcome the curse of dimensionality by using a divide and conquer approach, where the vector of unknowns is partitioned into a set of subvectors, each estimated by a separate particle filter. Each particle filter weighs its own particles by using predictions and estimates communicated from the other filters. Currently, there is no principled way to implement MPF methods where the particle filters share unknown parameters or states. In this work, we propose a fusion strategy to allow for the sharing of unknown static parameters in the MPF setting. Specifically, we study the systems which are separable in states and observations. It is proved that optimal Bayesian fusion can be obtained for state-space models with non-interacting states and observations. Simulations are performed to show that MPF with fusion strategy can provide more accurate estimates within fewer time steps comparing to existing algorithms.

The advent of chiplet technology introduces cutting-edge opportunities for constructing highly heterogeneous platforms with specialized accelerators. However, the HPC community currently lacks expertise in hardware development, a gap that must be bridged to leverage these advancements. Additionally, technologies like chiplet is cutting-edge with limited educational resource available. This paper addresses potential hardware specialization direction in HPC and how to cultivate these skills among students and staff, emphasizing the importance of understanding and developing custom hardware (e.g., rapid prototyping and resource estimation). We have been mentoring graduate-level students and new staff in hardware designs in a hands-on manner, encouraging them to utilize modern open-source hardware tools for their designs, which facilitates the sharing of research ideas. Additionally, we provide a summary of theses tools as part of our approach to prototyping and mentoring., Comment: SC24 eduHPC 2 pages

Skin dose in radiotherapy is a key issue for reducing patient side effects, but dose calculations in this high-gradient region remains a challenge. To support radiation therapists and medical physicist in their decisions, a computational tool has been developed to systematically recalculate the skin dose for each treatment session, taking into account changes in breast geometry. This tool is based on Monte Carlo skin dose calculations from deformed vector fields (DVF)-driven CT images, using 3D-scanner data. The application of deformation fields to the initial patient CT, as well as the validation of Monte Carlo skin dose calculations and comparison with TPS algorithm, are presented. The tool is currently being evaluated using data from a clinical study involving 60 patients (MorphoBreast3D).

This article, is devoted to $n$-EP and $n$-hypo-EP operators. We give some characteristic properties of these two classes and various links with other known classes in the literature, especially the classes of EP, SD, hypo-EP and $n$-normal operators.

Strong stellar winds are an important feature in wind-accreting high-mass X-ray binary (HMXB) systems, providing insights into stellar evolution and their impact on surrounding environments. However, the long-term evolution and temporal variability of these winds are not fully understood. This work probes the archetypal wind-accreting HMXB Vela X-1 using MAXI observations over 14 years, focusing on orbit-to-orbit absorption variability in the 2-10 keV band. Additionally, the relation between hardness ratio trends in binary orbits and neutron star spin states is investigated. We calculate hardness ratios to track absorption variability, comparing flux changes across energy bands, as the effect of absorption on the flux is energy-dependent. Variability is analyzed by comparing hardness ratio trends across binary orbits to the MAXI long-term averaged evolution. The long-term averaged hardness ratio evolution displays a stable pattern. Yet, individual binary orbits reveal different hardness ratio evolutions between consecutive orbits with no evident periodicity. Less than half of the binary orbits align with the long-term evolution. Moreover, neutron star spin-up episodes exhibit harder-than-average hardness trends compared to spin-down episodes, although their distributions overlap considerably. The long-term averaged hardness ratio dispersion is consistent with absorption column densities reported in literature from shorter observations, suggesting that heterogeneous wind structures, including accretion wakes and wind clumps, drive observed variations. The orbit-to-orbit variability indicates that pointed X-ray observations provide limited insight into wind structure. The link between neutron star spin states and hardness trends underscores the influence of accretion on absorption, with variability tied to stellar wind density fluctuations.

We present a general and flexible framework for detecting regime changes in complex, non-stationary data across multi-trial experiments. Traditional change point detection methods focus on identifying abrupt changes within a single time series (single trial), targeting shifts in statistical properties such as the mean, variance, and spectrum over time within that sole trial. In contrast, our approach considers changes occurring across trials, accommodating changes that may arise within individual trials due to experimental inconsistencies, such as varying delays or event duration. By leveraging diverse metrics to analyze time-frequency characteristics specifically topological changes in the spectrum and spectrograms, our approach offers a comprehensive framework for detecting such variations. Our approach can handle different scenarios with various statistical assumptions, including varying levels of stationarity within and across trials, making our framework highly adaptable. We validate our approach through simulations using time-varying autoregressive processes that exhibit different regime changes. Our results demonstrate the effectiveness of detecting changes across trials under diverse conditions. Furthermore, we illustrate the effectiveness of our method by applying it to predictive maintenance using the NASA bearing dataset. By analyzing the time-frequency characteristics of vibration signals recorded by accelerometers, our approach accurately identifies bearing failures, showcasing its strong potential for early fault detection in mechanical systems.

SMILES-based molecular generative models have been pivotal in drug design but face challenges in fragment-constrained tasks. To address this, the Sequential Attachment-based Fragment Embedding (SAFE) representation was recently introduced as an alternative that streamlines those tasks. In this study, we investigate the optimal setups for training SAFE generative models, focusing on dataset size, data augmentation through randomization, model architecture, and bond disconnection algorithms. We found that larger, more diverse datasets improve performance, with the LLaMA architecture using Rotary Positional Embedding proving most robust. SAFE-based models also consistently outperform SMILES-based approaches in scaffold decoration and linker design, particularly with BRICS decomposition yielding the best results. These insights highlight key factors that significantly impact the efficacy of SAFE-based generative models.

We consider the adaptive-rank integration of general time-dependent advection-diffusion partial differential equations (PDEs) with spatially variable coefficients. We employ a standard finite-difference method for spatial discretization coupled with diagonally implicit Runge-Kutta schemes for temporal discretization. The fully discretized scheme can be written as a generalized Sylvester equation, which we solve with an adaptive-rank algorithm structured around three key strategies: (i) constructing dimension-wise subspaces based on an extended Krylov strategy, (ii) developing an effective Averaged-Coefficient Sylvester (ACS) preconditioner to invert the reduced system for the coefficient matrix efficiently, and (iii) efficiently computing the residual of the equation without explicitly reverting to the full-rank form. The proposed approach features a computational complexity of O(Nr2 + r3), where r represents the rank during the Krylov iteration and N is the resolution in one dimension, commensurate with the constant-coefficient case [El Kahza et al, J. Comput. Phys., 518 (2024)]. We present numerical examples that illustrate the computational efficacy and complexity of our algorithm.

We study stochastic second-order methods for solving general non-convex optimization problems. We propose using a special version of momentum to stabilize the stochastic gradient and Hessian estimates in Newton's method. We show that momentum provably improves the variance of stochastic estimates and allows the method to converge for any noise level. Using the cubic regularization technique, we prove a global convergence rate for our method on general non-convex problems to a second-order stationary point, even when using only a single stochastic data sample per iteration. This starkly contrasts with all existing stochastic second-order methods for non-convex problems, which typically require large batches. Therefore, we are the first to demonstrate global convergence for batches of arbitrary size in the non-convex case for the Stochastic Cubic Newton. Additionally, we show improved speed on convex stochastic problems for our regularized Newton methods with momentum.