Search

The EdResearch for Action "Overview Series" summarizes the research on key topics to provide K-12 education decision makers and advocates with an evidence base to ground discussions about how to best serve students. This brief discusses the central question: How can schools and districts promote the educational and social-emotional well-being of the diverse population of immigrant-origin students? Key insights are arranged in the following sections: (1) breaking down the issue; (2) evidence-based practices; and (3) practices to avoid. [This brief was co-prepared by Re-Imagining Migration and UC Santa Barbara, The Gevirtz School Graduate School of Education.]

Bug fixing and code generation have been core research topics in software development for many years. The recent explosive growth in Large Language Models has completely transformed these spaces, putting in reach incredibly powerful tools for both. In this survey, 27 recent papers have been reviewed and split into two groups: one dedicated to Automated Program Repair (APR) and LLM integration and the other to code generation using LLMs. The first group consists of new methods for bug detection and repair, which include locating semantic errors, security vulnerabilities, and runtime failure bugs. The place of LLMs in reducing manual debugging efforts is emphasized in this work by APR toward context-aware fixes, with innovations that boost accuracy and efficiency in automatic debugging. The second group dwells on code generation, providing an overview of both general-purpose LLMs fine-tuned for programming and task-specific models. It also presents methods to improve code generation, such as identifier-aware training, fine-tuning at the instruction level, and incorporating semantic code structures. This survey work contrasts the methodologies in APR and code generation to identify trends such as using LLMs, feedback loops to enable iterative code improvement and open-source models. It also discusses the challenges of achieving functional correctness and security and outlines future directions for research in LLM-based software development., Comment: A survey of recent developments in AI-assisted automated program repair

JWST/MIRI images have been used to study the Fourier transform power spectra (PS) of two spiral galaxies, NGC 628 and NGC 5236, and two dwarfs, NGC 4449 and NGC 5068, at distances ranging from 4 to 10 Mpc. The PS slopes on scales larger than 200 pc range from -0.6 at 21 microns to -1.2 at 5.6 microns, suggesting a scaling of region luminosity with size as a power law with index ranging from 2.6 to 3.2, respectively. This result is consistent with the size-luminosity relation of star-forming regions found elsewhere, but extending here to larger scales. There is no evidence for a kink or steepening of the PS at some transition from two-dimensional to three-dimensional turbulence on the scale of the disk thickness. This lack of a kink could be from large positional variations in the PS depending on two opposite effects: local bright sources that make the slope shallower and exponential galaxy profiles that make the slope steeper. The sources could also be confined to a layer of molecular clouds that is thinner than the HI or cool dust layers where PS kinks have been observed before. If the star formation layers observed in the near-infrared here are too thin, then the PS kink could be hidden in the broad tail of the JWST point spread function., Comment: 12 pages, 32 figures

Radially extended disk winds could be the key to unlocking how protoplanetary disks accrete and how planets form and migrate. A distinctive characteristic is their nested morphology of velocity and chemistry. Here we report JWST/NIRSpec spectro-imaging of four young stars with edge-on disks in the Taurus star-forming region that demonstrate the ubiquity of this structure. In each source, a fast collimated jet traced by [Fe II] is nested inside a hollow cavity within wider lower-velocity H2 and, in one case, also CO ro-vibrational (v=1-0) emission. Furthermore, in one of our sources, ALMA CO(2-1) emission, paired with our NIRSpec images, reveals the nested wind structure extends further outward. This nested wind morphology strongly supports theoretical predictions for wind-driven accretion and underscores the need for theoretical work to assess the role of winds in the formation and evolution of planetary systems, Comment: This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this article is published in Nature Astronomy and is available online at https://doi.org/10.1038/s41550-024-02385-7

Material segmentation is a complex task, particularly when dealing with aerial data in poor lighting and atmospheric conditions. To address this, hyperspectral data from specialized cameras can be very useful in addition to RGB images. However, due to hardware constraints, high spectral data often come with lower spatial resolution. Additionally, incorporating such data into a learning-based segmentation framework is challenging due to the numerous data channels involved. To overcome these difficulties, we propose an innovative Siamese framework that uses time series-based compression to effectively and scalably integrate the additional spectral data into the segmentation task. We demonstrate our model's effectiveness through competitive benchmarks on aerial datasets in various environmental conditions., Comment: Accepted to the International Conference on Neural Information Processing (ICONIP) 2024. To be published in Springer-Nature Communications in Computer and Information Science (CCIS) Series

Large Language Models (LLMs) have shown remarkable capabilities in a multitude of Natural Language Processing (NLP) tasks. However, these models are still not immune to limitations such as social biases, especially gender bias. This work investigates whether current closed and open-source LLMs possess gender bias, especially when asked to give moral opinions. To evaluate these models, we curate and introduce a new dataset GenMO (Gender-bias in Morality Opinions) comprising parallel short stories featuring male and female characters respectively. Specifically, we test models from the GPT family (GPT-3.5-turbo, GPT-3.5-turbo-instruct, GPT-4-turbo), Llama 3 and 3.1 families (8B/70B), Mistral-7B and Claude 3 families (Sonnet and Opus). Surprisingly, despite employing safety checks, all production-standard models we tested display significant gender bias with GPT-3.5-turbo giving biased opinions in 24% of the samples. Additionally, all models consistently favour female characters, with GPT showing bias in 68-85% of cases and Llama 3 in around 81-85% instances. Additionally, our study investigates the impact of model parameters on gender bias and explores real-world situations where LLMs reveal biases in moral decision-making., Comment: Accepted by EMNLP Findings 2024

We present JWST/MIRI observations of T~Cha, a highly variable ($\Delta V \sim$3-5\,mag) accreting Sun-like star surrounded by a disk with a large ($\sim 15$\,au) dust gap. We find that the JWST mid-infrared spectrum is signiticantly different from the {\it Spitzer} spectrum obtained 17 years before, where the emission at short wavelengths ($5-10 \mu m$) has decreased by $\sim 2/3$ while at longer wavelengths ($15-25 \mu m$) it increased by up to a factor of $\sim 3$. This 'seesaw' behavior is contemporary with a fairly constant higher optical emission captured by the All Sky Automated Survey. By analyzing and modelling both SEDs, we propose that JWST caught the star during an outburst that destructed the asymmetric inner disk wall responsible for the high optical variability and lower $15-25$\,micron\ emission during the {\it Spitzer} time. The dust mass lost during this outburst is estimated to be comparable ($\sim 1/5$) to the upper limit of the total micron-sized dust mass in the inner disk of T~Cha now. Monitoring this system during possible future outbursts and more observations of its quiescent state will reveal if the inner disk can be replenished or will continue to be depleted and vanish., Comment: 16 pages, 7 figures, submitted to ApJ

There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhouse of large-scale non-parametric knowledge, however existing techniques do not directly transfer to the embodied domain, which is multimodal, data is highly correlated, and perception requires abstraction. To address these challenges, we introduce Embodied-RAG, a framework that enhances the foundational model of an embodied agent with a non-parametric memory system capable of autonomously constructing hierarchical knowledge for both navigation and language generation. Embodied-RAG handles a full range of spatial and semantic resolutions across diverse environments and query types, whether for a specific object or a holistic description of ambiance. At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail. This hierarchical organization allows the system to efficiently generate context-sensitive outputs across different robotic platforms. We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 200 explanation and navigation queries across 19 environments, highlighting its promise for general-purpose non-parametric system for embodied agents., Comment: Web: https://quanting-xie.github.io/Embodied-RAG-web/

In this paper, we first study hypergraph rewriting in categorical terms in an attempt to define the notion of events and develop foundations of causality in graph rewriting. We introduce novel concepts within the framework of double-pushout rewriting in adhesive categories. Secondly, we will study the notion of events in $\lambda-$calculus, wherein we construct an algorithm to determine causal relations between events following the evaluation of a $\lambda-$expression satisfying certain conditions. Lastly, we attempt to extend this definition to arbitrary $\lambda-$expressions., Comment: 19 pages, 6 figures Corrected some typos

This study addresses the use of Reed-Solomon error correction codes in QR codes to enhance resilience against failures. To fully grasp this approach, a basic cryptographic context is provided, necessary for understanding Reed-Solomon codes. The study begins by defining a code and explores key outcomes for codes with additional properties, such as linearity. The theoretical framework is further developed with specific definitions and examples of Reed-Solomon codes, presented as a particular variant of BCH codes. Additionally, the structure of QR codes is analyzed, encompassing different versions and how data is represented in the form of black and white pixels within an image. Finally, an inherent vulnerability of Reed-Solomon Codes, and particularly of QR codes, related to selective manipulation of modules is examined. This vulnerability leverages the error correction mechanisms present in Reed-Solomon codes.

Given the ubiquity of charts as a data analysis, visualization, and decision-making tool across industries and sciences, there has been a growing interest in developing pre-trained foundation models as well as general purpose instruction-tuned models for chart understanding and reasoning. However, existing methods suffer crucial drawbacks across two critical axes affecting the performance of chart representation models: they are trained on data generated from underlying data tables of the charts, ignoring the visual trends and patterns in chart images, and use weakly aligned vision-language backbone models for domain-specific training, limiting their generalizability when encountering charts in the wild. We address these important drawbacks and introduce ChartGemma, a novel chart understanding and reasoning model developed over PaliGemma. Rather than relying on underlying data tables, ChartGemma is trained on instruction-tuning data generated directly from chart images, thus capturing both high-level trends and low-level visual information from a diverse set of charts. Our simple approach achieves state-of-the-art results across $5$ benchmarks spanning chart summarization, question answering, and fact-checking, and our elaborate qualitative studies on real-world charts show that ChartGemma generates more realistic and factually correct summaries compared to its contemporaries. We release the code, model checkpoints, dataset, and demos at https://github.com/vis-nlp/ChartGemma.

This study investigates the nonlinear normal modes (NNMs) of a system comprising of two coupled Duffing oscillators, with one oscillator being grounded and with the coupling being both linear and nonlinear. The study utilizes the eigenfunctions of the Koopman operator and validates their connection with the Shaw-Piere invariant manifold framework for NNMs. Furthermore, the study delves into the impact of internal resonance and dissipation on the accuracy of this framework by defining a continuous quantitative measure for internal resonance. The applicability and robustness of the framework for the systems which are very similar qualitatively to that of an ENO, are also observed and discussed about the limitations of the approximation technique.

This paper presents a novel approach 4DRecons that takes a single camera RGB-D sequence of a dynamic subject as input and outputs a complete textured deforming 3D model over time. 4DRecons encodes the output as a 4D neural implicit surface and presents an optimization procedure that combines a data term and two regularization terms. The data term fits the 4D implicit surface to the input partial observations. We address fundamental challenges in fitting a complete implicit surface to partial observations. The first regularization term enforces that the deformation among adjacent frames is as rigid as possible (ARAP). To this end, we introduce a novel approach to compute correspondences between adjacent textured implicit surfaces, which are used to define the ARAP regularization term. The second regularization term enforces that the topology of the underlying object remains fixed over time. This regularization is critical for avoiding self-intersections that are typical in implicit-based reconstructions. We have evaluated the performance of 4DRecons on a variety of datasets. Experimental results show that 4DRecons can handle large deformations and complex inter-part interactions and outperform state-of-the-art approaches considerably.

New JWST near-infrared imaging of the nearby galaxy NGC 628 from the Cycle 1 program JWST-FEAST is combined with archival JWST mid-infrared imaging to calibrate the 21 $\mu$m emission as a star formation rate indicator (SFR) at $\sim$120 pc scales. The Pa$\alpha$ ($\lambda$1.8756 $\mu$m) hydrogen recombination emission line targeted by FEAST provides a reference SFR indicator that is relatively insensitive to dust attenuation, as demonstrated by combining this tracer with the HST H$\alpha$ imaging. Our analysis is restricted to regions that appear compact in nebular line emission and are sufficiently bright to mitigate effects of both age and stochastic sampling of the stellar initial mass function. We find that the 21 $\mu$m emission closely correlates with the nebular line emission, with a power-law with exponent=1.07$\pm$0.01, in agreement with past results. We calibrate a hybrid SFR indicator using a combination of H$\alpha$ and 24 $\mu$m (extrapolated from 21 $\mu$m) tracers and derive the proportionality constant between the two tracers $b=0.095\pm0.007$, which is $\sim$ 3-5 times larger than previous derivations using large regions/entire galaxies. We model these discrepancies as an increasing contribution to the dust heating by progressively older stellar populations for increasing spatial scales, in agreement with earlier findings that star formation is hierarchically distributed in galaxies. Thus, use of hybrid SFR indicators requires prior knowledge of the mean age of the stellar populations dominating the dust heating, which makes their application uncertain. Conversely, non-linear calibrations of SFRs from L(24) alone are more robust, with a factor $\lesssim$2.5 variation across the entire range of L(24) luminosities from HII regions to galaxies., Comment: 28 pages, 9 figures. Accepted for publication on the Astrophysical Journal

We investigate the emergence phase of young star clusters in the nearby spiral galaxy NGC 628. We use JWST NIRCam and MIRI observations to create spatially resolved maps of the Pa$\alpha$-1.87 $\mu$m and Br$\alpha$-4.05 $\mu$m hydrogen recombination lines, as well as the 3.3 $\mu$m and 7.7 $\mu$m emission from polycyclic aromatic hydrocarbons (PAHs). We extract 953 compact HII regions and analyze the PAH emission and morphology at $\sim$10 pc scales in the associated photo-dissociation regions (PDRs). While HII regions remain compact, radial profiles help us to define three PAH morphological classes: compact ($\sim$ 42%), extended ($\sim$ 34%) and open ($\sim$ 24%). The majority of compact and extended PAH morphologies are associated with very young star clusters ($<$5 Myr), while open PAH morphologies are mainly associated with star clusters older than 3 Myr. We observe a general decrease in the 3.3 $\mu$m and 7.7 $\mu$m PAH band emission as a function of cluster age, while their ratio remains constant with age out to 10 Myr and morphological class. The recovered PAH$_{3.3 \mu{\rm m}}$/PAH$_{7.7 \mu{\rm m}}$ ratio is lower than values reported in the literature for reference models that consider neutral and ionized PAH populations and analyses conducted at galactic scales. The 3.3 $\mu$m and 7.7 $\mu$m bands are typically associated to neutral and ionised PAHs, respectively. While we expected neutral PAHs to be suppressed in proximity of the ionizing source, the constant PAH$_{3.3 \mu{\rm m}}$/PAH$_{7.7 \mu{\rm m}}$ ratio would indicate that both families of molecules disrupt at similar rates in proximity of the HII regions., Comment: 25 pages, 14 figures, 3 tables. Accepted for publication in ApJ V2: Minor changes to Figures 7, 8, and 9, and to the text

Graph Neural Networks (GNNs) have gained significant attention in recent years due to their ability to learn representations of graph structured data. Two common methods for training GNNs are mini-batch training and full-graph training. Since these two methods require different training pipelines and systems optimizations, two separate classes of GNN training systems emerged, each tailored for one method. Works that introduce systems belonging to a particular category predominantly compare them with other systems within the same category, offering limited or no comparison with systems from the other category. Some prior work also justifies its focus on one specific training method by arguing that it achieves higher accuracy than the alternative. The literature, however, has incomplete and contradictory evidence in this regard. In this paper, we provide a comprehensive empirical comparison of representative full-graph and mini-batch GNN training systems. We find that the mini-batch training systems consistently converge faster than the full-graph training ones across multiple datasets, GNN models, and system configurations. We also find that mini-batch training techniques converge to similar or often higher accuracy values as full-graph training ones, showing that mini-batch sampling is not necessarily detrimental to accuracy. Our work highlights the importance of comparing systems across different classes, using time-to-accuracy rather than epoch time for performance comparison, and selecting appropriate hyperparameters for each training method separately., Comment: 12 pages, 1 appendix, 8 Figures, 16 Tables, Graph Neural Network, Graph Neural Networks, Full-graph training, Mini-batch training, full-batch training, distributed training, performance, epoch time, time to accuracy, accuracy

Thermoelectric materials are of great interest for heat energy harvesting applications. One such promising material is TlGaSe$_{2}$, a p-type semiconducting ternary chalcogenide. Recent reports show it can be processed as a thin film, opening the door for large-scale commercialization. However, TlGaSe$_{2}$ is prone to stacking faults along the [001] stacking direction and their role in its thermoelectric properties has not been understood to date. Herein, TlGaSe$_{2}$ is investigated via (scanning) transmission electron microscopy and first-principles calculations. Stacking faults are found to be present throughout the material, as density functional theory calculations reveal a lack of preferential stacking order. Electron transport calculations show an enhancement of thermoelectric power factors when stacking faults are present. This implies the presence of stacking faults is key to the material's excellent thermoelectric properties along the [001] stacking direction, which can be further enhanced by doping the material to hole carrier concentrations to approx. 10$^{19}$ cm$^{-3}$.

A major challenge facing the world is the provision of equitable and universal access to quality education. Recent advances in generative AI (gen AI) have created excitement about the potential of new technologies to offer a personal tutor for every learner and a teaching assistant for every teacher. The full extent of this dream, however, has not yet materialised. We argue that this is primarily due to the difficulties with verbalising pedagogical intuitions into gen AI prompts and the lack of good evaluation practices, reinforced by the challenges in defining excellent pedagogy. Here we present our work collaborating with learners and educators to translate high level principles from learning science into a pragmatic set of seven diverse educational benchmarks, spanning quantitative, qualitative, automatic and human evaluations; and to develop a new set of fine-tuning datasets to improve the pedagogical capabilities of Gemini, introducing LearnLM-Tutor. Our evaluations show that LearnLM-Tutor is consistently preferred over a prompt tuned Gemini by educators and learners on a number of pedagogical dimensions. We hope that this work can serve as a first step towards developing a comprehensive educational evaluation framework, and that this can enable rapid progress within the AI and EdTech communities towards maximising the positive impact of gen AI in education.

We present maps of ionized gas (traced by Pa$\alpha$ and Br$\alpha$) and 3.3 $\mu$m Polycyclic Aromatic Hydrocarbon (PAH) emission in the nearby spiral galaxy NGC 628, derived from new JWST/NIRCam data from the FEAST survey. With this data, we investigate and calibrate the relation between 3.3 $\mu$m PAH emission and star formation rate (SFR) in and around emerging young star clusters (eYSCs) on a scale of ${\sim}40$ pc. We find a tight (correlation coefficient $\rho$${\sim}$0.9) sub-linear (power-law exponent $\alpha$${\sim}$0.75) relation between the 3.3 $\mu$m PAH luminosity surface density and SFR traced by Br$\alpha$ for compact, cospatial (within 0.16$''$ or ${\sim}$7 pc) peaks in Pa$\alpha$, Br$\alpha$, and 3.3 $\mu$m (eYSC-I). The scatter in the relationship does not correlate well with variations in local interstellar medium (ISM) metallicity due to a radial metallicity gradient, but rather is likely due to stochastic sampling of the stellar initial mass function (IMF) and variations in the PAH heating and age of our sources. The deviation from a linear relation may be explained by PAH destruction in more intense ionizing environments, variations in age, and IMF stochasticity at intermediate to low luminosities. We test our results with various continuum subtraction techniques using combinations of NIRCam bands and find that they remain robust with only minor differences in the derived slope and intercept. An unexpected discrepancy is identified between the relations of hydrogen recombination lines (Pa$\alpha$ versus Br$\alpha$; H$\alpha$ versus Br$\alpha$)., Comment: 28 pages, 10 figures, 3 tables

The aim of this article is to detect the ascent and descent of weighted composition operators on Lorentz spaces. We investigate the conditions on the measurable transformation $T$ and the complex-valued measurable function $u$ defined on measure space $(X, \mathcal{A}, \mu)$ that cause the weighted composition operators on Lorentz space $L(p, q)$, $1 < p \leq \infty, 1 \leq q \leq \infty$ to have finite or infinite ascent (descent). We also give a number of examples in support of our findings., Comment: 18 pages and no figure

Reinforcement learning (RL) with continuous state and action spaces remains one of the most challenging problems within the field. Most current learning methods focus on integral identities such as value functions to derive an optimal strategy for the learning agent. In this paper, we instead study the dual form of the original RL formulation to propose the first differential RL framework that can handle settings with limited training samples and short-length episodes. Our approach introduces Differential Policy Optimization (DPO), a pointwise and stage-wise iteration method that optimizes policies encoded by local-movement operators. We prove a pointwise convergence estimate for DPO and provide a regret bound comparable with the best current theoretical derivation. Such pointwise estimate ensures that the learned policy matches the optimal path uniformly across different steps. We then apply DPO to a class of practical RL problems with continuous state and action spaces, and which search for optimal configurations with Lagrangian rewards. DPO is easy to implement, scalable, and shows competitive results on benchmarking experiments against several popular RL methods.

We survey the young star cluster population in the dwarf galaxy NGC4449 with the goal of investigating how stellar feedback may depend on the clusters' properties. Using Ultraviolet(UV)-optical-NearIR(NIR) photometry obtained from the Hubble Space Telescope, we have recovered 99 compact sources exhibiting emission in the Pa$\beta$ hydrogen recombination line. Our analysis reveals these sources possess masses $10^{2}

Formulating effective search queries remains a challenging task, particularly when users lack expertise in a specific domain or are not proficient in the language of the content. Providing example documents of interest might be easier for a user. However, such query-by-example scenarios are prone to concept drift, and the retrieval effectiveness is highly sensitive to the query generation method, without a clear way to incorporate user feedback. To enable exploration and to support Human-In-The-Loop experiments we propose QueryExplorer -- an interactive query generation, reformulation, and retrieval interface with support for HuggingFace generation models and PyTerrier's retrieval pipelines and datasets, and extensive logging of human feedback. To allow users to create and modify effective queries, our demo supports complementary approaches of using LLMs interactively, assisting the user with edits and feedback at multiple stages of the query formulation process. With support for recording fine-grained interactions and user annotations, QueryExplorer can serve as a valuable experimental and research platform for annotation, qualitative evaluation, and conducting Human-in-the-Loop (HITL) experiments for complex search tasks where users struggle to formulate queries., Comment: NAACL 2024 Demonstration Track

We formulate a novel planar motion planning problem for a Dubins-Laser system that consists of a Dubins vehicle with an attached controllable laser. The vehicle moves with unit speed and the laser, having a finite range, can rotate in a clockwise or anti-clockwise direction with a bounded angular rate. From an arbitrary initial position and orientation, the objective is to steer the system so that a given static target is within the range of the laser and the laser is oriented at it in minimum time. We characterize multiple properties of the optimal trajectory and establish that the optimal trajectory for the Dubins-laser system is one out of a total of 16 candidates. Finally, we provide numerical insights that illustrate the properties characterized in this work.

The recent emergence of van der Waals (vdW) ferromagnets has opened new opportunities for designing spintronic devices. We theoretically investigate the coherent spin-dependent transport properties of the vdW ferromagnet Fe$_4$GeTe$_2$, by using density functional theory combined with the non-equilibrium Green's functions method. We find that the conductance in the direction perpendicular to the layers is half-metallic, namely it is entirely spin-polarized, as a result of the material's electronic structure. This characteristic persists from bulk to single layer, even under significant bias voltages, and it is little affected by spin-orbit coupling and electron correlation. Motivated by this observation, we then investigate the tunnel magnetoresistance (TMR) effect in an magnetic tunnel junction, which comprises two Fe$_4$GeTe$_2$ layers separated by the vdW gap acting as insulating barrier. We predict a TMR ratio of almost 500\%, which can be further boosted by increasing the number of Fe$_4$GeTe$_2$ layers in the junction., Comment: 16 pages, 15 figures and 4 tables

[Ne II] 12.81 $\mu\mathrm{m}$ emission is a well-used tracer of protoplanetary disk winds due to its blueshifted line profile. MIRI-MRS recently observed T Cha, detecting this line along with lines of [Ne III], [Ar II] and [Ar III], with the [Ne II] and [Ne III] lines found to be extended while the [Ar II] was not. In this complementary work, we use these lines to address long-debated questions about protoplanetary disk winds regarding their mass-loss rate, the origin of their ionization, and the role of magnetically-driven winds as opposed to photoevaporation. To this end, we perform photoionization radiative transfer on simple hydrodynamic wind models to map the line emission. We compare the integrated model luminosities to those observed with MIRI-MRS to identify which models most closely reproduce the data and produce synthetic images from these to understand what information is captured by measurements of the line extents. Along with the low degree of ionization implied by the line ratios, the relative compactness of [Ar II] compared to [Ne II] is particularly constraining. This requires Ne II production by hard X-rays and Ar II production by soft X-rays (and/or EUV) in an extended ($\gtrsim 10$ au) wind that is shielded from soft X-rays - necessitating a dense wind with material launched on scales down to ~1 au. Such conditions could be produced by photoevaporation, whereas an extended MHD wind producing equal shielding would likely underpredict the line fluxes. However, a tenuous inner MHD wind may still contribute to shielding the extended wind. This picture is consistent with constraints from spectrally-resolved line profiles., Comment: 32 pages, 16 figures, Accepted 14/03/24 to the Astronomical Journal. Complementary modeling to Bajaj et al. 2024 (arXiv:2403.01060)

Python has emerged as one of the most popular programming languages, extensively utilized in domains such as machine learning, data analysis, and web applications. Python's dynamic nature and extensive usage make it an attractive candidate for dynamic program analysis. However, unlike for other popular languages, there currently is no comprehensive benchmark suite of executable Python projects, which hinders the development of dynamic analyses. This work addresses this gap by presenting DyPyBench, the first benchmark of Python projects that is large scale, diverse, ready to run (i.e., with fully configured and prepared test suites), and ready to analyze (by integrating with the DynaPyt dynamic analysis framework). The benchmark encompasses 50 popular opensource projects from various application domains, with a total of 681k lines of Python code, and 30k test cases. DyPyBench enables various applications in testing and dynamic analysis, of which we explore three in this work: (i) Gathering dynamic call graphs and empirically comparing them to statically computed call graphs, which exposes and quantifies limitations of existing call graph construction techniques for Python. (ii) Using DyPyBench to build a training data set for LExecutor, a neural model that learns to predict values that otherwise would be missing at runtime. (iii) Using dynamically gathered execution traces to mine API usage specifications, which establishes a baseline for future work on specification mining for Python. We envision DyPyBench to provide a basis for other dynamic analyses and for studying the runtime behavior of Python code.

Understanding when and how circumstellar disks disperse is crucial to constrain planet formation and migration. Thermal winds powered by high-energy stellar photons have long been theorized to drive disk dispersal. However, evidence for these winds is currently based only on small (~3-6 km/s) blue-shifts in [Ne II] 12.81 um lines, which does not exclude MHD winds. We report JWST MIRI MRS spectro-imaging of T Cha, a disk with a large dust gap (~30 au in radius) and blue-shifted [Ne II] emission. We detect four forbidden noble gas lines, [Ar II], [Ar III], [Ne II], and [Ne III], of which [Ar III] is the first detection in any protoplanetary disk. We use line flux ratios to constrain the energy of the ionizing photons and find that Argon is ionized by EUV whereas Neon is most likely ionized by X-rays. After performing continuum and Point Spread Function (PSF) subtraction on the IFU cube, we discover a spatial extension in the [Ne II] emission off the disk continuum emission. This is the first spatially resolved [Ne II] disk wind emission. The mostly ionic spectrum of T Cha, in combination with the extended [Ne II] emission, points to an evolved stage for any inner MHD wind and is consistent with the existence of an outer thermal wind ionized and driven by high-energy stellar photons. This work acts as a pathfinder for future observations aiming at investigating disk dispersal using JWST., Comment: 20 pages, 8 figures, Accepted for publication in AJ

Despite being extensively studied, time series classification and forecasting on noisy data remain highly difficult. The main challenges lie in finding suitable mathematical concepts to describe time series and effectively separating noise from the true signals. Instead of treating time series as a static vector or a data sequence as often seen in previous methods, we introduce a novel framework that considers each time series, not necessarily of fixed length, as a sample realization of a continuous-time stochastic process. Such mathematical model explicitly captures the data dependence across several timestamps and detects the hidden time-dependent signals from noise. However, since the underlying data is often composed of several distinct dynamics, modeling using a single stochastic process is not sufficient. To handle such settings, we first assign each dynamics a signature vector. We then propose the abstract concept of the most informative timestamps to infer a sparse approximation of the individual dynamics based on their assigned vectors. The final model, referred to as Motion Code, contains parameters that can fully capture different underlying dynamics in an integrated manner. This allows unmixing classification and generation of specific sub-type forecasting simultaneously. Extensive experiments on sensors and devices noisy time series data demonstrate Motion Code's competitiveness against time series classification and forecasting benchmarks., Comment: 20 pages, 5 figures, 4 tables

Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding, its significance for collaborative agents, and similarities and differences in grounding approaches in both communities. The article examines the potential of neuro-symbolic approaches tailored for grounding tasks, showcasing how they can more comprehensively address grounding. Finally, we discuss areas for further exploration and development in grounding.