Search

Prior case retrieval (PCR) is crucial for legal practitioners to find relevant precedent cases given the facts of a query case. Existing approaches often overlook the underlying semantic intent in determining relevance with respect to the query case. In this work, we propose LeCoPCR, a novel approach that explicitly generate intents in the form of legal concepts from a given query case facts and then augments the query with these concepts to enhance models understanding of semantic intent that dictates relavance. To overcome the unavailability of annotated legal concepts, we employ a weak supervision approach to extract key legal concepts from the reasoning section using Determinantal Point Process (DPP) to balance quality and diversity. Experimental results on the ECtHR-PCR dataset demonstrate the effectiveness of leveraging legal concepts and DPP-based key concept extraction., Comment: Accepted to NAACL 2025

Acoustic identification of individual animals (AIID) is closely related to audio-based species classification but requires a finer level of detail to distinguish between individual animals within the same species. In this work, we frame AIID as a hierarchical multi-label classification task and propose the use of hierarchy-aware loss functions to learn robust representations of individual identities that maintain the hierarchical relationships among species and taxa. Our results demonstrate that hierarchical embeddings not only enhance identification accuracy at the individual level but also at higher taxonomic levels, effectively preserving the hierarchical structure in the learned representations. By comparing our approach with non-hierarchical models, we highlight the advantage of enforcing this structure in the embedding space. Additionally, we extend the evaluation to the classification of novel individual classes, demonstrating the potential of our method in open-set classification scenarios., Comment: Under review; Submitted to ICASSP 2025

In the last decade, remarkable advances in integrated photonic technologies have enabled table-top experiments and instrumentation to be scaled down to compact chips with significant reduction in size, weight, power consumption, and cost. Here, we demonstrate an integrated continuously tunable laser in a heterogeneous gallium arsenide-on-silicon nitride (GaAs-on-SiN) platform that emits in the far-red radiation spectrum near 780 nm, with 20 nm tuning range, <6 kHz intrinsic linewidth, and a >40 dB side-mode suppression ratio. The GaAs optical gain regions are heterogeneously integrated with low-loss SiN waveguides. The narrow linewidth lasing is achieved with an extended cavity consisting of a resonator-based Vernier mirror and a phase shifter. Utilizing synchronous tuning of the integrated heaters, we show mode-hop-free wavelength tuning over a range larger than 100 GHz (200 pm). To demonstrate the potential of the device, we investigate two illustrative applications: (i) the linear characterization of a silicon nitride microresonator designed for entangled-photon pair generation, and (ii) the absorption spectroscopy and locking to the D1 and D2 transition lines of 87-Rb. The performance of the proposed integrated laser holds promise for a broader spectrum of both classical and quantum applications in the visible range, encompassing communication, control, sensing, and computing.

{We herein report on the calculation of thermoluminescence (TL) kinetic parameters determined from the TL emission of synthetic GdAlO3 (GAO) phosphors prepared by the co-precipitation method. The sample, characterized by means of X-ray diffraction with an orthorhombic phase structure (space group Pnma (62), shows complex glow curves consisting of at least four groups of components peaked at 100, 140, 240, and 290 {\deg}C where the two lower overlapped temperature peaks are difficult to identify using the $T_M-T_{stop}$. The coexistence of a continuum in the trap distribution (linked to the lower temperature peaks) and a discrete trap system (associated with the components at temperatures higher than 200 {\deg}C) can be distinguished. The estimation of the TL kinetic parameters is performed using GlowFit, TLAnal, the spreadsheet Origin, Computing Glow Curve Deconvolution (CGCD), and various heating rate (VHR) methods. However, only CGCD appears as the suitable technique for such purpose since it provides information on the TL physical process supported by mathematical models based on a linear combination of functions related to the First Order Kinetic approach., Comment: 27 pages, 6 figures and 1 table

The aim of this paper is to find an upper bound for the box-counting dimension of uniform attractors for non-autonomous dynamical systems. Contrary to the results in literature, we do not ask the symbol space to have finite box-counting dimension. Instead, we ask a condition on the semi-continuity of pullback attractors of the system as time goes to infinity. This semi-continuity can be achieved if we suppose the existence of finite-dimensional exponential uniform attractors for the limit symbols. After showing these new results, we apply them to study the box-counting dimension of the uniform attractor for a reaction-diffusion equation, and we find a specific forcing term such that the symbol space has infinite box-counting dimension but the uniform attractor has finite box-counting dimension anyway.

Detecting the presence of animal vocalisations in nature is essential to study animal populations and their behaviors. A recent development in the field is the introduction of the task known as few-shot bioacoustic sound event detection, which aims to train a versatile animal sound detector using only a small set of audio samples. Previous efforts in this area have utilized different architectures and data augmentation techniques to enhance model performance. However, these approaches have not fully bridged the domain gap between source and target distributions, limiting their applicability in real-world scenarios. In this work, we introduce an new dataset designed to augment the diversity and breadth of classes available for few-shot bioacoustic event detection, building on the foundations of our previous datasets. To establish a robust baseline system tailored for the DCASE 2024 Task 5 challenge, we delve into an array of acoustic features and adopt negative hard sampling as our primary domain adaptation strategy. This approach, chosen in alignment with the challenge's guidelines that necessitate the independent treatment of each audio file, sidesteps the use of transductive learning to ensure compliance while aiming to enhance the system's adaptability to domain shifts. Our experiments show that the proposed baseline system achieves a better performance compared with the vanilla prototypical network. The findings also confirm the effectiveness of each domain adaptation method by ablating different components within the networks. This highlights the potential to improve few-shot bioacoustic sound event detection by further reducing the impact of domain shift.

Diarrhetic Shellfish Poisoning (DSP) is a global health threat arising from shellfish contaminated with toxins produced by dinoflagellates. The condition, with its widespread incidence, high morbidity rate, and persistent shellfish toxicity, poses risks to public health and the shellfish industry. High biomass of toxin-producing algae such as DSP are known as Harmful Algal Blooms (HABs). Monitoring and forecasting systems are crucial for mitigating HABs impact. Predicting harmful algal blooms involves a time-series-based problem with a strong historical seasonal component, however, recent anomalies due to changes in meteorological and oceanographic events have been observed. Stream Learning stands out as one of the most promising approaches for addressing time-series-based problems with concept drifts. However, its efficacy in predicting HABs remains unproven and needs to be tested in comparison with Batch Learning. Historical data availability is a critical point in developing predictive systems. In oceanography, the available data collection can have some constrains and limitations, which has led to exploring new tools to obtain more exhaustive time series. In this study, a machine learning workflow for predicting the number of cells of a toxic dinoflagellate, Dinophysis acuminata, was developed with several key advancements. Seven machine learning algorithms were compared within two learning paradigms. Notably, the output data from CROCO, the ocean hydrodynamic model, was employed as the primary dataset, palliating the limitation of time-continuous historical data. This study highlights the value of models interpretability, fair models comparison methodology, and the incorporation of Stream Learning models. The model DoME, with an average R2 of 0.77 in the 3-day-ahead prediction, emerged as the most effective and interpretable predictor, outperforming the other algorithms.

In this paper we obtain the existence of a weak global attractor for the three-dimensional Navier-Stokes equations, that is, a weakly compact set with an invariance property, that uniformly attracts solutions, with respect to the weak topology, for initial data in bounded sets. To that end, we define this weak global attractor in terms of limits of solutions of the globally modified Navier-Stokes equations in the weak topology. We use the theory of semilinear parabolic equations and $\epsilon$-regularity to obtain the local well posedness for the globally modified Navier-Stokes equations and the existence of a global attractor and its regularity., Comment: 17 pages

We prove the existence of a normalized, stationary solution $\Psi \colon \mathbb{R}^{3} \to \mathbb{C}^{4}$ with frequency $w > 0$ of the nonlinear Dirac equation. The result covers the case in which the nonlinearity is the gradient of a function of the form \begin{equation*} F(\Psi) = a|(\Psi, \gamma^{0}\Psi)|^{\frac{\alpha}{2}} + b|(\Psi, \gamma^{1}\gamma^{2} \gamma^{3} \Psi)|^{\frac{\alpha}{2}} \end{equation*} with $\alpha \in (2,\frac{8}{3}]$, $b \geq 0$ and $a > 0$ sufficiently small. Here $\gamma^{i}$, $i = 0,\ldots, 3$ are the $4 \times 4$ Dirac's matrices. We find the solution as a critical point of a suitable functional restricted to the unit sphere in $L^{2}$, and $w$ turns out to be the corresponding Lagrange multiplier.

We consider the Microcanonical Variational Principle for the vortex system in a bounded domain. In particular we are interested in the thermodynamic properties of the system in domains of second kind, i.e. for which the equivalence of ensembles does not hold. For connected domains close to the union of disconnected disks (dumbbell domains), we show that the system may exhibit an arbitrary number of fist-order phase transitions, while the entropy is convex for large energy., Comment: 22 pages,15 figures

Few-shot bioacoustic event detection consists in detecting sound events of specified types, in varying soundscapes, while having access to only a few examples of the class of interest. This task ran as part of the DCASE challenge for the third time this year with an evaluation set expanded to include new animal species, and a new rule: ensemble models were no longer allowed. The 2023 few shot task received submissions from 6 different teams with F-scores reaching as high as 63% on the evaluation set. Here we describe the task, focusing on describing the elements that differed from previous years. We also take a look back at past editions to describe how the task has evolved. Not only have the F-score results steadily improved (40% to 60% to 63%), but the type of systems proposed have also become more complex. Sound event detection systems are no longer simple variations of the baselines provided: multiple few-shot learning methodologies are still strong contenders for the task., Comment: submitted to DCASE 2023 workshop

Automatic detection and classification of animal sounds has many applications in biodiversity monitoring and animal behaviour. In the past twenty years, the volume of digitised wildlife sound available has massively increased, and automatic classification through deep learning now shows strong results. However, bioacoustics is not a single task but a vast range of small-scale tasks (such as individual ID, call type, emotional indication) with wide variety in data characteristics, and most bioacoustic tasks do not come with strongly-labelled training data. The standard paradigm of supervised learning, focussed on a single large-scale dataset and/or a generic pre-trained algorithm, is insufficient. In this work we recast bioacoustic sound event detection within the AI framework of few-shot learning. We adapt this framework to sound event detection, such that a system can be given the annotated start/end times of as few as 5 events, and can then detect events in long-duration audio -- even when the sound category was not known at the time of algorithm training. We introduce a collection of open datasets designed to strongly test a system's ability to perform few-shot sound event detections, and we present the results of a public contest to address the task. We show that prototypical networks are a strong-performing method, when enhanced with adaptations for general characteristics of animal sounds. We demonstrate that widely-varying sound event durations are an important factor in performance, as well as non-stationarity, i.e. gradual changes in conditions throughout the duration of a recording. For fine-grained bioacoustic recognition tasks without massive annotated training data, our results demonstrate that few-shot sound event detection is a powerful new method, strongly outperforming traditional signal-processing detection methods in the fully automated scenario.

Can quantum mechanical thermodynamic engines outperform their classical counterparts? To address one aspect of this question, we experimentally realize and characterize an isentropic thermodynamic engine that uses a Bose-condensed working fluid. In this engine, an interacting quantum degenerate gas of bosonic lithium is subjected to trap compression and relaxation strokes interleaved with strokes strengthening and weakening interparticle interactions. We observe a significant enhancement in efficiency and power when using a Bose-condensed working fluid, compared to the case of a non-degenerate thermal gas. We demonstrate reversibility, and measure power and efficiency as a function of engine parameters including compression ratio and cycle time. Results agree quantitatively with interacting finite temperature field-theoretic simulations that closely replicate the length and energy scales of the working fluid., Comment: 8 pages, 6 figures

In this paper, we propose an assertion-based approach to capture software evolution, through the notion of commit-relevant specification. A commit-relevant specification summarises the program properties that have changed as a consequence of a commit (understood as a specific software modification), via two sets of assertions, the delta-added assertions, properties that did not hold in the pre-commit version but hold on the post-commit, and the delta-removed assertions, those that were valid in the pre-commit, but no longer hold after the code change. We also present DeltaSpec, an approach that combines test generation and dynamic specification inference to automatically compute commit-relevant specifications from given commits. We evaluate DeltaSpec on two datasets that include a total of 57 commits (63 classes and 797 methods). We show that commit-relevant assertions can precisely describe the semantic deltas of code changes, providing a useful mechanism for validating the behavioural evolution of software. We also show that DeltaSpec can infer 88% of the manually written commit-relevant assertions expressible in the language supported by the tool. Moreover, our experiments demonstrate that DeltaSpec's inferred assertions are effective to detect regression faults. More precisely, we show that commit-relevant assertions can detect, on average, 78.3% of the artificially seeded faults that interact with the code changes. We also show that assertions in the delta are 58.3% more effective in detecting commit-relevant mutants than assertions outside the delta, and that it takes on average 169% fewer assertions when these are commit-relevant, compared to using general valid assertions, to achieve a same commit-relevant mutation score.

Few-shot sound event detection is the task of detecting sound events, despite having only a few labelled examples of the class of interest. This framework is particularly useful in bioacoustics, where often there is a need to annotate very long recordings but the expert annotator time is limited. This paper presents an overview of the second edition of the few-shot bioacoustic sound event detection task included in the DCASE 2022 challenge. A detailed description of the task objectives, dataset, and baselines is presented, together with the main results obtained and characteristics of the submitted systems. This task received submissions from 15 different teams from which 13 scored higher than the baselines. The highest F-score was of 60% on the evaluation set, which leads to a huge improvement over last year's edition. Highly-performing methods made use of prototypical networks, transductive learning, and addressed the variable length of events from all target classes. Furthermore, by analysing results on each of the subsets we can identify the main difficulties that the systems face, and conclude that few-show bioacoustic sound event detection remains an open challenge., Comment: submitted to DCASE2022 workshop

A graph is intrinsically projectively linked (IPL) if its every embedding in projective space contains a nonsplit link. Some minor-minimal IPL graphs have been found previously. We determine that no minor-minimal IPL graphs on 16 edges exists and identify new minor-minimal IPL graphs by applying $\Delta-Y$ exchanges to $K_{7}-2e$. We prove that for a nonouter-projective-planar graph $G$, $G+\bar{K}_{2}$ is IPL and describe the necessary and sufficient conditions on a projective planar graph $G$ such that $G+\bar{K}_{2}$ is IPL. Lastly, we deduce conditions for $f(G + \bar{K_{2}})$ to have no nonsplit link, where $G$ is projective planar, $\bar{K_{2}} = \{w_{0},w_{1}\}$, and $f(G + \bar{K_{2}})$ is the embedding onto $\mathbb{R}P^{3}$ with $f(G)$ in $z=0$, $w_{0}$ above $z=0$, and $w_{1}$ below $z=0$ such that every edge connecting ${w_{0},w_{1}}$ to $G$ avoids the boundary of the 3-ball, whose antipodal points are identified to obtain projective space.

A graph $G$ is nonseparating projective planar if $G$ has a projective planar embedding without a nonsplit link. Nonseparating projective planar graphs are closed under taking minors and are a superclass of projective outerplanar graphs. We partially characterize the minor-minimal separating projective planar graphs by proving that given a minor-minimal nonouter-projective-planar graph $G$, either $G$ is minor-minimal separating projective planar or $G \dot\cup K_{1}$ is minor-minimal weakly separating projective planar, a necessary condition for $G$ to be separating projective planar. One way to generalize separating projective planar graphs is to consider type I 3-links consisting of two cycles and a pair of vertices. A graph is intrinsically projective planar type I 3-linked (IPPI3L) if its every projective planar embedding contains a nonsplit type I 3-link. We partially characterize minor-minimal IPPI3L graphs by classifying all minor-minimal IPPI3L graphs with three or more components, and finding many others with fewer components.

We prove the existence of a stationary solution for the system describing the interaction between an electron coupled with a massless scalar field (a photon). We find a solution, with fixed $L^{2}$-norm, by variational methods, as a critical point of an energy functional.