Search

Underwater acoustic environment estimation is a challenging but important task for remote sensing scenarios. Current estimation methods require high signal strength and a solution to the fragile echo labeling problem to be effective. In previous publications, we proposed a general deep learning-based method for two-dimensional environment estimation which outperformed the state-of-the-art, both in simulation and in real-life experimental settings. A limitation of this method was that some prior information had to be provided by the user on the number and locations of the reflective boundaries, and that its neural networks had to be re-trained accordingly for different environments. Utilizing more advanced neural network and time delay estimation techniques, the proposed improved method no longer requires prior knowledge the number of boundaries or their locations, and is able to estimate two-dimensional environments with one or two boundaries. Future work will extend the proposed method to more boundaries and larger-scale environments.

This survey uncovers the tension between AI techniques designed for energy saving in mobile networks and the energy demands those same techniques create. We compare modeling approaches that estimate power usage cost of current commercial terrestrial next-generation radio access network deployments. We then categorize emerging methods for reducing power usage by domain: time, frequency, power, and spatial. Next, we conduct a timely review of studies that attempt to estimate the power usage of the AI techniques themselves. We identify several gaps in the literature. Notably, real-world data for the power consumption is difficult to source due to commercial sensitivity. Comparing methods to reduce energy consumption is beyond challenging because of the diversity of system models and metrics. Crucially, the energy cost of AI techniques is often overlooked, though some studies provide estimates of algorithmic complexity or run-time. We find that extracting even rough estimates of the operational energy cost of AI models and data processing pipelines is complex. Overall, we find the current literature hinders a meaningful comparison between the energy savings from AI techniques and their associated energy costs. Finally, we discuss future research opportunities to uncover the utility of AI for energy saving., Comment: 16 pages, 4 figures, Accepted for publication in IEEE Access

Recent sustainability drives place energy-consumption metrics in centre-stage for the design of future radio access networks (RAN). At the same time, optimising the trade-off between performance and system energy usage by machine-learning (ML) is an approach that requires large amounts of granular RAN data to train models, and to adapt in near realtime. In this paper, we present extensions to the system-level discrete-event AIMM (AI-enabled Massive MIMO) Simulator, generating realistic figures for throughput and energy efficiency (EE) towards digital twin network modelling. We further investigate the trade-off between maximising either EE or spectrum efficiency (SE). To this end, we have run extensive simulations of a typical macrocell network deployment under various transmit power-reduction scenarios with a range of difference of 43 dBm. Our results demonstrate that the EE and SE objectives often require different power settings in different scenarios. Importantly, low mean user CPU execution times of 2.17 $\pm$ 0.05 seconds (2~s.d.) demonstrate that the AIMM Simulator is a powerful tool for quick prototyping of scalable system models which can interface with ML frameworks, and thus support future research in energy-efficient next generation networks., Comment: 6 pages, 3 figures, Accepted for 2024 IEEE Wireless Communications and Networking Conference (WCNC)

The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in integrated circuit design, network optimization, and robot path planning. Since OARSMT is NP-hard, exact algorithms scale poorly with the number of terminals, leading practical solvers to sacrifice accuracy for large problems. We propose MazeNet, a deep learning-based method that learns to solve the OARSMT from data. MazeNet reframes OARSMT as a maze-solving task that can be addressed with a recurrent convolutional neural network (RCNN). A key hallmark of MazeNet is its scalability: we only need to train the RCNN blocks on mazes with a small number of terminals; larger mazes can be solved by replicating the same pre-trained blocks to create a larger network. Across a wide range of experiments, MazeNet achieves perfect OARSMT-solving accuracy, significantly reduces runtime compared to classical exact algorithms, and can handle more terminals than state-of-the-art approximate algorithms., Comment: 15 pages, 15 figures. Submitted to ICLR 2025

ATOMKI nuclear anomaly has suggested a new BSM (Beyond the Standard Model) boson with mass $\sim17$ MeV emitted from excited nuclei and quickly decays into a pair of $e^+e^-$. In order to search for the new particle, we propose a new approach that utilizes the ongoing Coherent CAPTAIN-Mills (CCM) 10-ton LAr (liquid argon) detectors. The neutrons from the Lujan target can scatter inelastically by the PMT glass in the CCM detector can produce the new boson which solves the ATOMKI anomaly. The new boson can be detected from its decay to a $e^+e^-$ pair. We find that CCM probe a large area of the anomaly allowed parameter space. We also show the prediction for a 100 ton LAr detector., Comment: 6 pages, 3 figures

We present a widefield fluorescence microscope that integrates an event-based image sensor (EBIS) with a CMOS image sensor (CIS) for ultra-fast microscopy with spectral distinction capabilities. The EBIS achieves temporal resolution of $\sim10\thinspace\mu$s ($\sim\thinspace$50,000 frames/s), while the CIS provides diffraction-limited spatial resolution. A diffractive optical element encodes spectral information into a diffractogram, which is recorded by the CIS. The diffractogram is processed using a deep neural network to resolve the fluorescence of two beads, whose emission peaks are separated by only 7 nm and exhibit an 88\% spectral overlap. We validate our microscope by imaging the capillary flow of fluorescent beads, demonstrating a significant advancement in ultra-fast spectral microscopy. This technique holds broad potential for elucidating foundational dynamic biological processes.

Accurately modeling student cognition is crucial for developing effective AI-driven educational technologies. A key challenge is creating realistic student models that satisfy two essential properties: (1) accurately replicating specific misconceptions, and (2) correctly solving problems where these misconceptions are not applicable. This dual requirement reflects the complex nature of student understanding, where misconceptions coexist with correct knowledge. This paper investigates whether Large Language Models (LLMs) can be instruction-tuned to meet this dual requirement and effectively simulate student thinking in algebra. We introduce MalAlgoPy, a novel Python library that generates datasets reflecting authentic student solution patterns through a graph-based representation of algebraic problem-solving. Utilizing MalAlgoPy, we define and examine Cognitive Student Models (CSMs) - LLMs instruction tuned to faithfully emulate realistic student behavior. Our findings reveal that LLMs trained on misconception examples can efficiently learn to replicate errors. However, the training diminishes the model's ability to solve problems correctly, particularly for problem types where the misconceptions are not applicable, thus failing to satisfy second property of CSMs. We demonstrate that by carefully calibrating the ratio of correct to misconception examples in the training data - sometimes as low as 0.25 - it is possible to develop CSMs that satisfy both properties. Our insights enhance our understanding of AI-based student models and pave the way for effective adaptive learning systems.

JWST observations of the young Galactic supernova remnant Cassiopeia A revealed an unexpected structure seen as a green emission feature in colored composite MIRI F1130W and F1280W images - hence dubbed the Green Monster - that stretches across the central parts of the remnant in projection. Combining the kinematic information from NIRSpec and MIRI MRS with the multi-wavelength imaging from NIRCam and MIRI, we associate the Green Monster with circumstellar material that was lost during an asymmetric mass-loss phase. MIRI images are dominated by dust emission but its spectra show emission lines from Ne, H and Fe with low radial velocities indicative of a CSM nature. An X-ray analysis of this feature in a companion paper (Vink et al. 2024) supports its CSM nature and detects significant blue shifting, thereby placing the Green Monster on the near side, in front of the Cas A SN remnant. The most striking features of the Green Monster are dozens of almost perfectly circular 1" - 3" sized holes, most likely created by interaction between high-velocity SN ejecta material and the CSM. Further investigation is needed to understand whether these holes were formed by small 8000-10500 km/s N-rich ejecta knots that penetrated and advanced out ahead of the remnant's 5000 - 6000 km/s outer blastwave, or by narrow ejecta fingers that protrude into the forward-shocked CSM. The detection of the Green Monster provides further evidence of the highly asymmetric mass-loss that Cas A's progenitor star underwent prior to explosion., Comment: 28 pages, 12 figures, resubmitted to ApJL after minor revision, comments welcome

From the Golgi apparatus to endosomes, organelles in the endomembrane system exhibit complex and varied morphologies that are often related to their function. Such membrane-bound organelles operate far from equilibrium due to directed fluxes of smaller trafficking vesicles; the physical principles governing the emergence and maintenance of these structures have thus remained elusive. By understanding individual fission and fusion events in terms of active mechano-chemical cycles, we show how such trafficking manifests at the hydrodynamic scale, resulting not only in fluxes of material -- such as membrane area and encapsulated volume -- but also in active stresses that drive momentum transfer between an organelle and its cytosolic environment. Due to the fluid and deformable nature of the bounding membrane, this gives rise to novel physics, coupling nonequilibrium forces to organelle composition, morphology and hydrodynamic flows. We demonstrate how both stable compartment drift and ramified sac-like morphologies, each reminiscent of Golgi-cisternae, emerge naturally from the same underlying nonequilibrium dynamics of fission and fusion.

Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is typically trained to capture one signal of interest, resulting in learned neural features that are highly attuned to that signal. Assumed to be less generalizable, we explore the aspect of transferability of such learned neural features for fitting similar signals. We introduce a new INR training framework, STRAINER that learns transferrable features for fitting INRs to new signals from a given distribution, faster and with better reconstruction quality. Owing to the sequential layer-wise affine operations in an INR, we propose to learn transferable representations by sharing initial encoder layers across multiple INRs with independent decoder layers. At test time, the learned encoder representations are transferred as initialization for an otherwise randomly initialized INR. We find STRAINER to yield extremely powerful initialization for fitting images from the same domain and allow for $\approx +10dB$ gain in signal quality early on compared to an untrained INR itself. STRAINER also provides a simple way to encode data-driven priors in INRs. We evaluate STRAINER on multiple in-domain and out-of-domain signal fitting tasks and inverse problems and further provide detailed analysis and discussion on the transferability of STRAINER's features. Our demo can be accessed at https://colab.research.google.com/drive/1fBZAwqE8C_lrRPAe-hQZJTWrMJuAKtG2?usp=sharing .

Machine-learned interatomic potentials (MLIPs) are becoming an essential tool in materials modeling. However, optimizing the generation of training data used to parameterize the MLIPs remains a significant challenge. This is because MLIPs can fail when encountering local enviroments too different from those present in the training data. The difficulty of determining \textit{a priori} the environments that will be encountered during molecular dynamics (MD) simulation necessitates diverse, high-quality training data. This study investigates how training data diversity affects the performance of MLIPs using the Ultra-Fast Force Field (UF$^3$) to model amorphous silicon nitride. We employ expert and autonomously generated data to create the training data and fit four force-field variants to subsets of the data. Our findings reveal a critical balance in training data diversity: insufficient diversity hinders generalization, while excessive diversity can exceed the MLIP's learning capacity, reducing simulation accuracy. Specifically, we found that the UF$^3$ variant trained on a subset of the training data, in which nitrogen-rich structures were removed, offered vastly better prediction and simulation accuracy than any other variant. By comparing these UF$^3$ variants, we highlight the nuanced requirements for creating accurate MLIPs, emphasizing the importance of application-specific training data to achieve optimal performance in modeling complex material behaviors., Comment: 6 pages, 4 figures

We present a procedure for calculating the heating of, and the infrared emission from, dust in a homogeneous spherical shell surrounded by a spherically symmetric source of radiation. The results are applicable to newly formed dust either in supernova ejecta or in the circumstellar medium that has been swept up by the expanding shock wave. They can also be applied to the heating and IR emission from dust in clumps or clouds embedded in a homogeneous radiation field.

The study of transmission and progression of human papillomavirus (HPV) is crucial for understanding the incidence of cervical cancers, and has been identified as a priority worldwide. The complexity of the disease necessitates a detailed model of HPV transmission and its progression to cancer; to infer properties of the above we require a careful process that can match to imperfect or incomplete observational data. In this paper, we describe the HPVsim simulator to satisfy the former requirement; to satisfy the latter we couple this stochastic simulator to a process of emulation and history matching using the R package hmer. With these tools, we are able to obtain a comprehensive collection of parameter combinations that could give rise to observed cancer data, and explore the implications of the variability of these parameter sets as it relates to future health interventions., Comment: 21 pages, 15 figures; submitted to Epidemics

Short-term changes in the resonance frequency of silicon nitride (SiN) nanomechanical resonators can be measured very precisely due to low thermomechanical fluctuations resulting from large mechanical quality factors. These properties enable high-performance detection of quasi-instantaneous stimuli, such as sudden exposure to radiation or adsorption of mass. However, practical use of such sensors will eventually raise questions regarding their less-studied longer-term stability, notably for calibration purposes. We characterize aging of an as-fabricated SiN membrane by continuously tracking changes of its resonance frequency over 135 days in a temperature-controlled high vacuum environment. The aging behavior is consistent with previously reported double-logarithmic and drift-reversal aging trends observed in quartz oscillators. The aging magnitude (300 ppm) is also comparable to typical temperature compensated quartz oscillators (TCXO), after normalization to account for the greater importance of interfaces in our thin (90 nm) resonator, compared to several microns thick TCXOs. Possible causes of aging due to surface adsorption are investigated. We review models on how water adsorption and desorption can cause significant frequency changes, predominantly due to chemisorption stress. Chemical species adsorbed on the resonator surface are also identified by X-ray photoelectron spectroscopy (XPS). These measurements show a significant increase in carbon every time the sample is placed under vacuum, while subsequent exposure to air causes an increase in oxidated carbon. Developing models for the contribution of carbon and oxygen to the membrane stress should therefore be an important future direction. Other contaminants, notably alkaline and halide ions, are detected in smaller quantities and briefly discussed.

We report the discovery of the most eccentric transiting brown dwarf in the brown dwarf desert, TOI02490b. The brown dwarf desert is the lack of brown dwarfs around main sequence stars within $\sim3$~AU and is thought to be caused by differences in formation mechanisms between a star and planet. To date, only $\sim40$ transiting brown dwarfs have been confirmed. \systemt is a $73.6\pm2.4$ \mjupnospace, $1.00\pm0.02$ \rjup brown dwarf orbiting a $1.004_{-0.022}^{+0.031}$ \msunnospace, $1.105_{-0.012}^{+0.012}$ \rsun sun-like star on a 60.33~d orbit with an eccentricity of $0.77989\pm0.00049$. The discovery was detected within \tess sectors 5 (30 minute cadence) and 32 (2 minute and 20 second cadence). It was then confirmed with 31 radial velocity measurements with \feros by the WINE collaboration and photometric observations with the Next Generation Transit Survey. Stellar modelling of the host star estimates an age of $\sim8$~Gyr, which is supported by estimations from kinematics likely placing the object within the thin disc. However, this is not consistent with model brown dwarf isochrones for the system age suggesting an inflated radius. Only one other transiting brown dwarf with an eccentricity higher than 0.6 is currently known in the brown dwarf desert. Demographic studies of brown dwarfs have suggested such high eccentricity is indicative of stellar formation mechanisms., Comment: Accepted for publication in MNRAS, 18 pages, 14 figures

The topological understanding of nematic liquid crystals is traditionally centered on singularities, or defects, and their classification via homotopy theory. However, this approach has ultimately proved insufficient to properly capture a range of complex behaviours that have been reported in three dimensions. To address this, we argue that a finer understanding of topology is required, in which non-singular but non-trivial topological solitons - so-called merons - play a central role in mediating interactions between disclination lines. We present a comprehensive framework for capturing such behaviour that draws heavily on aspects of Morse theory; the key notion being that merons appear singular under projection onto a two-dimensional surface. This permits the use of singularity theory and dividing curves to characterise nematic textures via tomography, as well as an understanding of topological transitions via surgery theory. We use our ideas to understand and classify complex three-dimensional behaviours, such as the linking, rewiring and crossing of disclination lines, as well as to provide a new perspective on defect charge., Comment: 31 pages, 11 figures

Approximate Bayesian computation (ABC) is the most popular approach to inferring parameters in the case where the data model is specified in the form of a simulator. It is not possible to directly implement standard Monte Carlo methods for inference in such a model, due to the likelihood not being available to evaluate pointwise. The main idea of ABC is to perform inference on an alternative model with an approximate likelihood (the ABC likelihood), estimated at each iteration from points simulated from the data model. The central challenge of ABC is then to trade-off bias (introduced by approximating the model) with the variance introduced by estimating the ABC likelihood. Stabilising the variance of the ABC likelihood requires a computational cost that is exponential in the dimension of the data, thus the most common approach to reducing variance is to perform inference conditional on summary statistics. In this paper we introduce a new approach to estimating the ABC likelihood: using iterative ensemble Kalman inversion (IEnKI) (Iglesias, 2016; Iglesias et al., 2018). We first introduce new estimators of the marginal likelihood in the case of a Gaussian data model using the IEnKI output, then show how this may be used in ABC. Performance is illustrated on the Lotka-Volterra model, where we observe substantial improvements over standard ABC and other commonly-used approaches.

In the dynamic landscape of the Web, we are witnessing the emergence of the Web3 paradigm, which dictates that platforms should rely on blockchain technology and cryptocurrencies to sustain themselves and their profitability. Cryptocurrencies are characterised by high market volatility and susceptibility to substantial crashes, issues that require temporal analysis methodologies able to tackle the high temporal resolution, heterogeneity and scale of blockchain data. While existing research attempts to analyse crash events, fundamental questions persist regarding the optimal time scale for analysis, differentiation between long-term and short-term trends, and the identification and characterisation of shock events within these decentralised systems. This paper addresses these issues by examining cryptocurrencies traded on the Ethereum blockchain, with a spotlight on the crash of the stablecoin TerraUSD and the currency LUNA designed to stabilise it. Utilising complex network analysis and a multi-layer temporal graph allows the study of the correlations between the layers representing the currencies and system evolution across diverse time scales. The investigation sheds light on the strong interconnections among stablecoins pre-crash and the significant post-crash transformations. We identify anomalous signals before, during, and after the collapse, emphasising their impact on graph structure metrics and user movement across layers. This paper pioneers temporal, cross-chain graph analysis to explore a cryptocurrency collapse. It emphasises the importance of temporal analysis for studies on web-derived data and how graph-based analysis can enhance traditional econometric results. Overall, this research carries implications beyond its field, for example for regulatory agencies aiming to safeguard users from shocks and monitor investment risks for citizens and clients.

Morphodynamic descriptions of fluid deformable surfaces are relevant for a range of biological and soft matter phenomena, spanning materials that can be passive or active, as well as ordered or topological. However, a principled, geometric formulation of the correct hydrodynamic equations has remained opaque, with objective rates proving a central, contentious issue. We argue that this is due to a conflation of several important notions that must be disambiguated when describing fluid deformable surfaces. These are the Eulerian and Lagrangian perspectives on fluid motion, and three different types of gauge freedom: in the ambient space; in the parameterisation of the surface, and; in the choice of frame field on the surface. We clarify these ideas, and show that objective rates in fluid deformable surfaces are time derivatives that are invariant under the first of these gauge freedoms, and which also preserve the structure of the ambient metric. The latter condition reduces a potentially infinite number of possible objective rates to only two: the material derivative and the Jaumann rate. The material derivative is invariant under the Galilean group, and therefore applies to velocities, whose rate captures the conservation of momentum. The Jaumann derivative is invariant under all time-dependent isometries, and therefore applies to local order parameters, or symmetry-broken variables, such as the nematic $Q$-tensor. We provide examples of material and Jaumann rates in two different frame fields that are pertinent to the current applications of the fluid mechanics of deformable surfaces., Comment: 27 pages, 4 figures

Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision. Like neural network layers, these attention mechanisms are often developed by heuristics and experience. To provide a principled framework for constructing attention layers in transformers, we show that the self-attention corresponds to the support vector expansion derived from a support vector regression problem, whose primal formulation has the form of a neural network layer. Using our framework, we derive popular attention layers used in practice and propose two new attentions: 1) the Batch Normalized Attention (Attention-BN) derived from the batch normalization layer and 2) the Attention with Scaled Head (Attention-SH) derived from using less training data to fit the SVR model. We empirically demonstrate the advantages of the Attention-BN and Attention-SH in reducing head redundancy, increasing the model's accuracy, and improving the model's efficiency in a variety of practical applications including image and time-series classification., Comment: Accepted to ICLR 2023, 26 pages, 4 figures, 14 tables

This study examined the relationship between using the Ignite by Hatch™ educational gaming system and assessments of the developmental status of young children participating in the 2023 Georgia Department of Early Care and Learning (DECAL) Summer Transition Program. Researchers collected data that describe the extent to which the children engaged with Ignite system and the skill levels they achieved within the system. Teachers also rated the developmental status of the children using rating scales that focused on Literacy and Mathematics skills.

Generative models unfairly penalize data belonging to minority classes, suffer from model autophagy disorder (MADness), and learn biased estimates of the underlying distribution parameters. Our theoretical and empirical results show that training generative models with intentionally designed hypernetworks leads to models that 1) are more fair when generating datapoints belonging to minority classes 2) are more stable in a self-consumed (i.e., MAD) setting, and 3) learn parameters that are less statistically biased. To further mitigate unfairness, MADness, and bias, we introduce a regularization term that penalizes discrepancies between a generative model's estimated weights when trained on real data versus its own synthetic data. To facilitate training existing deep generative models within our framework, we offer a scalable implementation of hypernetworks that automatically generates a hypernetwork architecture for any given generative model.

As hydrogen is touted as a key player in the decarbonization of modern society, it is critical to enable quantitative H analysis at high spatial resolution, if possible at the atomic scale. Indeed, H has a known deleterious impact on the mechanical properties (strength, ductility, toughness) of most materials that can hinder their use as part of the infrastructure of a hydrogen-based economy. Enabling H mapping, including local hydrogen concentration analyses at specific microstructural features, is essential for understanding the multiple ways that H affect the properties of materials, including for instance embrittlement mechanisms and their synergies, but also spatial mapping and quantification of hydrogen isotopes is essential to accurately predict tritium inventory of future fusion power plants, ensuring their safe and efficient operation for example. Atom probe tomography (APT) has the intrinsic capabilities for detecting hydrogen (H), and deuterium (D), and in principle the capacity for performing quantitative mapping of H within a material's microstructure. Yet the accuracy and precision of H analysis by APT remain affected by the influence of residual hydrogen from the ultra-high vacuum chamber that can obscure the signal of H from within the material, along with a complex field evaporation behavior. The present article reports the essence of discussions at a focused workshop held at the Max-Planck Institute for Sustainable Materials in April 2024. The workshop was organized to pave the way to establishing best practices in reporting APT data for the analysis of H. We first summarize the key aspects of the intricacies of H analysis by APT and propose a path for better reporting of the relevant data to support interpretation of APT-based H analysis in materials.

We introduce Many-Shot Regurgitation (MSR) prompting, a new black-box membership inference attack framework for examining verbatim content reproduction in large language models (LLMs). MSR prompting involves dividing the input text into multiple segments and creating a single prompt that includes a series of faux conversation rounds between a user and a language model to elicit verbatim regurgitation. We apply MSR prompting to diverse text sources, including Wikipedia articles and open educational resources (OER) textbooks, which provide high-quality, factual content and are continuously updated over time. For each source, we curate two dataset types: one that LLMs were likely exposed to during training ($D_{\rm pre}$) and another consisting of documents published after the models' training cutoff dates ($D_{\rm post}$). To quantify the occurrence of verbatim matches, we employ the Longest Common Substring algorithm and count the frequency of matches at different length thresholds. We then use statistical measures such as Cliff's delta, Kolmogorov-Smirnov (KS) distance, and Kruskal-Wallis H test to determine whether the distribution of verbatim matches differs significantly between $D_{\rm pre}$ and $D_{\rm post}$. Our findings reveal a striking difference in the distribution of verbatim matches between $D_{\rm pre}$ and $D_{\rm post}$, with the frequency of verbatim reproduction being significantly higher when LLMs (e.g. GPT models and LLaMAs) are prompted with text from datasets they were likely trained on. For instance, when using GPT-3.5 on Wikipedia articles, we observe a substantial effect size (Cliff's delta $= -0.984$) and a large KS distance ($0.875$) between the distributions of $D_{\rm pre}$ and $D_{\rm post}$. Our results provide compelling evidence that LLMs are more prone to reproducing verbatim content when the input text is likely sourced from their training data.

Titan's atmospheric composition and dynamical state have previously been studied over numerous epochs by both ground- and space-based facilities. However, stratospheric measurements remain sparse during Titan's northern summer and fall. The lack of seasonal symmetry in observations of Titan's temperature field and chemical abundances raises questions about the nature of the middle atmosphere's meridional circulation and evolution over Titan's 29-yr seasonal cycle that can only be answered through long-term monitoring campaigns. Here, we present maps of Titan's stratospheric temperature, acetonitrile (or methyl cyanide; CH$_3$CN), and monodeuterated methane (CH$_3$D) abundances following Titan's northern summer solstice obtained with Band 9 ($\sim0.43$ mm) ALMA observations. We find that increasing temperatures towards high-southern latitudes, currently in winter, resemble those observed during Titan's northern winter by the Cassini mission. Acetonitrile abundances have changed significantly since previous (sub)millimeter observations, and we find that the species is now highly concentrated at high-southern latitudes. The stratospheric CH$_3$D content is found to range between 4-8 ppm in these observations, and we infer the CH$_4$ abundance to vary between $\sim0.9-1.6\%$ through conversion with previously measured D/H values. A global value of CH$_4=1.15\%$ was retrieved, lending further evidence to the temporal and spatial variability of Titan's stratospheric methane when compared with previous measurements. Additional observations are required to determine the cause and magnitude of stratospheric enhancements in methane during these poorly understood seasons on Titan., Comment: Accepted for publication in the Planetary Science Journal. 9 Figures, 1 table

We present the results from the first two years of the Planet Hunters NGTS citizen science project, which searches for transiting planet candidates in data from the Next Generation Transit Survey (NGTS) by enlisting the help of members of the general public. Over 8,000 registered volunteers reviewed 138,198 light curves from the NGTS Public Data Releases 1 and 2. We utilize a user weighting scheme to combine the classifications of multiple users to identify the most promising planet candidates not initially discovered by the NGTS team. We highlight the five most interesting planet candidates detected through this search, which are all candidate short-period giant planets. This includes the TIC-165227846 system that, if confirmed, would be the lowest-mass star to host a close-in giant planet. We assess the detection efficiency of the project by determining the number of confirmed planets from the NASA Exoplanet Archive and TESS Objects of Interest (TOIs) successfully recovered by this search and find that 74% of confirmed planets and 63% of TOIs detected by NGTS are recovered by the Planet Hunters NGTS project. The identification of new planet candidates shows that the citizen science approach can provide a complementary method to the detection of exoplanets with ground-based surveys such as NGTS., Comment: 42 pages, 20 figures, 17 tables. To be published in AJ

The pursuit of personalized education has led to the integration of Large Language Models (LLMs) in developing intelligent tutoring systems. To better understand and adapt to individual student needs, including their misconceptions, LLMs need to be trained on extensive datasets of student-tutor dialogues. Our research uncovers a fundamental challenge in this approach: the ``Student Data Paradox.'' This paradox emerges when LLMs, trained on student data to understand learner behavior, inadvertently compromise their own factual knowledge and reasoning abilities. We investigate this paradox by training state-of-the-art language models on student-tutor dialogue datasets and evaluating their performance across multiple benchmarks. These benchmarks assess various aspects of language model capabilities, including reasoning, truthfulness, and common sense understanding. Our findings reveal significant declines in the models' performance across these diverse benchmarks, indicating a broad impact on their capabilities when trained to model student behavior. Our research makes two primary contributions: (1) empirical demonstration of the Student Data Paradox through quantitative analysis of model performance, and (2) introduction of ``hallucination tokens'' as a mitigation strategy. These tokens, while improving performance, highlight the persistent challenge of balancing accurate student behavior modeling with maintaining the LLM's integrity as an educational tool. This study emphasizes the need for innovative solutions to reconcile the conflicting goals of faithfully understanding diverse student cognition while preserving the model's ability to provide accurate information and guidance., Comment: Accepted at EMNLP 2024 Findings Track

We introduce a new area of study in the field of educational Natural Language Processing: Automated Long Answer Grading (ALAG). Distinguishing itself from Automated Short Answer Grading (ASAG) and Automated Essay Grading (AEG), ALAG presents unique challenges due to the complexity and multifaceted nature of fact-based long answers. To study ALAG, we introduce RiceChem, a dataset derived from a college chemistry course, featuring real student responses to long-answer questions with an average word count notably higher than typical ASAG datasets. We propose a novel approach to ALAG by formulating it as a rubric entailment problem, employing natural language inference models to verify whether each criterion, represented by a rubric item, is addressed in the student's response. This formulation enables the effective use of MNLI for transfer learning, significantly improving the performance of models on the RiceChem dataset. We demonstrate the importance of rubric-based formulation in ALAG, showcasing its superiority over traditional score-based approaches in capturing the nuances of student responses. We also investigate the performance of models in cold start scenarios, providing valuable insights into the practical deployment considerations in educational settings. Lastly, we benchmark state-of-the-art open-sourced Large Language Models (LLMs) on RiceChem and compare their results to GPT models, highlighting the increased complexity of ALAG compared to ASAG. Despite leveraging the benefits of a rubric-based approach and transfer learning from MNLI, the lower performance of LLMs on RiceChem underscores the significant difficulty posed by the ALAG task. With this work, we offer a fresh perspective on grading long, fact-based answers and introduce a new dataset to stimulate further research in this important area. Code: \url{https://github.com/luffycodes/Automated-Long-Answer-Grading}.

In this paper, we introduce "Marking", a novel grading task that enhances automated grading systems by performing an in-depth analysis of student responses and providing students with visual highlights. Unlike traditional systems that provide binary scores, "marking" identifies and categorizes segments of the student response as correct, incorrect, or irrelevant and detects omissions from gold answers. We introduce a new dataset meticulously curated by Subject Matter Experts specifically for this task. We frame "Marking" as an extension of the Natural Language Inference (NLI) task, which is extensively explored in the field of Natural Language Processing. The gold answer and the student response play the roles of premise and hypothesis in NLI, respectively. We subsequently train language models to identify entailment, contradiction, and neutrality from student response, akin to NLI, and with the added dimension of identifying omissions from gold answers. Our experimental setup involves the use of transformer models, specifically BERT and RoBERTa, and an intelligent training step using the e-SNLI dataset. We present extensive baseline results highlighting the complexity of the "Marking" task, which sets a clear trajectory for the upcoming study. Our work not only opens up new avenues for research in AI-powered educational assessment tools, but also provides a valuable benchmark for the AI in education community to engage with and improve upon in the future. The code and dataset can be found at https://github.com/luffycodes/marking.

JWST/NIRCam obtained high angular-resolution (0.05-0.1''), deep near-infrared 1--5 micron imaging of Supernova (SN) 1987A taken 35 years after the explosion. In the NIRCam images, we identify: 1) faint H2 crescents, which are emissions located between the ejecta and the equatorial ring, 2) a bar, which is a substructure of the ejecta, and 3) the bright 3-5 micron continuum emission exterior to the equatorial ring. The emission of the remnant in the NIRCam 1-2.3 micron images is mostly due to line emission, which is mostly emitted in the ejecta and in the hot spots within the equatorial ring. In contrast, the NIRCam 3-5 micron images are dominated by continuum emission. In the ejecta, the continuum is due to dust, obscuring the centre of the ejecta. In contrast, in the ring and exterior to the ring, synchrotron emission contributes a substantial fraction to the continuum. Dust emission contributes to the continuum at outer spots and diffuse emission exterior to the ring, but little within the ring. This shows that dust cooling and destruction time scales are shorter than the synchrotron cooling time scale, and the time scale of hydrogen recombination in the ring is even longer than the synchrotron cooling time scale. With the advent of high sensitivity and high angular resolution images provided by JWST/NIRCam, our observations of SN 1987A demonstrate that NIRCam opens up a window to study particle-acceleration and shock physics in unprecedented details, probed by near-infrared synchrotron emission, building a precise picture of how a SN evolves., Comment: Accepted for publication in MNRAS; 18 pages

Hyperspectral imagery (HSI) is an established technique with an array of applications, but its use is limited due to both practical and technical issues associated with spectral devices. The goal of the ICASSP 2024 'Hyper-Skin' Challenge is to extract skin HSI from matching RGB images and an infrared band. To address this problem we propose a model using features of the scattering transform - a type of convolutional neural network with predefined filters. Our model matches and inverts those features, rather than the pixel values, reducing the complexity of matching while grouping similar features together, resulting in an improved learning process., Comment: Corresponding Author: bkolstoe@umd.edu Presented at ICASSP 2024

We derive a stochastic partial differential equation that describes the fluctuating behaviour of reaction-diffusion systems of N particles, undergoing Markovian, unary reactions. This generalises the work of Dean [J. Phys. A: Math. and Gen., 29 (24), L613, (1996)] through the inclusion of random Poisson fields. Our approach is based on weak interactions, which has the dual benefit that the resulting equations asymptotically converge (in the N to infinity limit) on a variation of a McKean- Vlasov diffusion, whilst still being related to the case of Dean-like strong interactions via a trivial rescaling. Various examples are presented, alongside a discussion of possible extensions to more complicated reaction schemes., Comment: 31 pages

Tractography algorithms are used extensively to delineate white matter structures, by operating on the voxel-wise information generated through the application of diffusion tensor imaging (DTI) or other models to diffusion weighted (DW) magnetic resonance imaging (MRI) data. We demonstrate that these methods commonly yield systematic streamline length dependent distortions of tractography derived tissue microstructure parameters, such as fractional anisotropy (FA). This dependency may be described as piecewise linear. For streamlines shorter than an inflection point (determined for a group of tracts delineated for each individual brain), estimates of tissue microstructure exhibit a positive linear relation with streamline length. For streamlines longer than the point of inflection, the association is weaker, with the slope of the relationship between streamline length and tissue microstructure differing only marginally from zero. As the dependency is most pronounced for a range of streamline lengths encountered typically in DW imaging of the human brain (less than ~100 mm), our results suggest that some previous estimates of tissue microstructure should be treated with considerable caution. A method is described, whereby an Akaike information weighted average of linear, Blackman and piecewise linear model predictions, may be used to compensate effectively for the dependence of FA (and other estimates of tissue microstructure) on streamline length, across the entire range of streamline lengths present in each specimen., Comment: 8 figures in main text; 7 figures in Supplementary Material

As part of a graduate student internship, an alignment study was completed for Ignite™ by Hatch®, in partnership between The University of North Carolina at Charlotte's Center for Educational Measurement and Evaluation and Hatch®. Ignite™ has 341 Core games amongst 7 domains to assist early childhood learners: Mathematics, Language and Communication Development, Literacy, Physical Development, Science and Technology, Social Studies, and Social-Emotional Development. This study was completed as part of an initiative to review the program's Core games and their respective alignment with appropriate learning standards. Although Ignite™ is utilized across the country, North Carolina (NC) was used as a case for this study, which serves as an example when considering other states' learning standards. The following items were used when matching game objectives from Ignite™ with corresponding learning standards: (1) NC Foundations for Early Learning and Development; (2) The North Carolina Standard Course of Study -- Kindergarten; (3) The North Carolina Standard Course of Study -- Grade 1; and (4) The North Carolina Standard Course of Study -- Grade 2. [This report was written in partnership with Alexandra Miller.]