Machine learning has vast potential to improve anomaly detection in satellite telemetry which is a crucial task for spacecraft operations. This potential is currently hampered by a lack of comprehensible benchmarks for multivariate time series anomaly detection, especially for the challenging case of satellite telemetry. The European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry (ESA-ADB) aims to address this challenge and establish a new standard in the domain. It is a result of close cooperation between spacecraft operations engineers from the European Space Agency (ESA) and machine learning experts. The newly introduced ESA Anomalies Dataset contains annotated real-life telemetry from three different ESA missions, out of which two are included in ESA-ADB. Results of typical anomaly detection algorithms assessed in our novel hierarchical evaluation pipeline show that new approaches are necessary to address operators' needs. All elements of ESA-ADB are publicly available to ensure its full reproducibility.

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine unlearning. This new field seeks to selectively remove specific knowledge from a model's training data without causing a drop in its overall performance. However, it turns out that actually forgetting a given concept is an extremely difficult task. Models exposed to attacks using adversarial prompts show the ability to generate so-called unlearned concepts, which can be not only harmful but also illegal. In this paper, we present considerations regarding the ability of models to forget and recall knowledge, introducing the Memory Self-Regeneration task. Furthermore, we present MemoRa strategy, which we consider to be a regenerative approach supporting the effective recovery of previously lost knowledge. Moreover, we propose that robustness in knowledge retrieval is a crucial yet underexplored evaluation measure for developing more robust and effective unlearning techniques. Finally, we demonstrate that forgetting occurs in two distinct ways: short-term, where concepts can be quickly recalled, and long-term, where recovery is more challenging.

Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with low-resolution images obtained by degrading and downsampling high-resolution ones -- they frequently fail to generalize to real-world settings, such as document scans, which are affected by complex degradations and semantic variability. In this study, we introduce a task-driven, multi-task learning framework for training a super-resolution network specifically optimized for optical character recognition tasks. We propose to incorporate auxiliary loss functions derived from high-level vision tasks, including text detection using the connectionist text proposal network, text recognition via a convolutional recurrent neural network, keypoints localization using Key.Net, and hue consistency. To balance these diverse objectives, we employ dynamic weight averaging mechanism, which adaptively adjusts the relative importance of each loss term based on its convergence behavior. We validate our approach upon the SRResNet architecture, which is a well-established technique for single-image super-resolution. Experimental evaluations on both simulated and real-world scanned document datasets demonstrate that the proposed approach improves text detection, measured with intersection over union, while preserving overall image fidelity. These findings underscore the value of multi-objective optimization in super-resolution models for bridging the gap between simulated training regimes and practical deployment in real-world scenarios.

Super-resolution reconstruction is aimed at generating images of high spatial resolution from low-resolution observations. State-of-the-art super-resolution techniques underpinned with deep learning allow for obtaining results of outstanding visual quality, but it is seldom verified whether they constitute a valuable source for specific computer vision applications. In this paper, we investigate the possibility of employing super-resolution as a preprocessing step to improve optical character recognition from document scans. To achieve that, we propose to train deep networks for single-image super-resolution in a task-driven way to make them better adapted for the purpose of text detection. As problems limited to a specific task are heavily ill-posed, we introduce a multi-task loss function that embraces components related with text detection coupled with those guided by image similarity. The obtained results reported in this paper are encouraging and they constitute an important step towards real-world super-resolution of document images.

Detecting anomalous events in satellite telemetry is a critical task in space operations. This task, however, is extremely time-consuming, error-prone and human dependent, thus automated data-driven anomaly detection algorithms have been emerging at a steady pace. However, there are no publicly available datasets of real satellite telemetry accompanied with the ground-truth annotations that could be used to train and verify anomaly detection supervised models. In this article, we address this research gap and introduce the AI-ready benchmark dataset (OPSSAT-AD) containing the telemetry data acquired on board OPS-SAT -- a CubeSat mission which has been operated by the European Space Agency which has come to an end during the night of 22--23 May 2024 (CEST). The dataset is accompanied with the baseline results obtained using 30 supervised and unsupervised classic and deep machine learning algorithms for anomaly detection. They were trained and validated using the training-test dataset split introduced in this work, and we present a suggested set of quality metrics which should be always calculated to confront the new algorithms for anomaly detection while exploiting OPSSAT-AD. We believe that this work may become an important step toward building a fair, reproducible and objective validation procedure that can be used to quantify the capabilities of the emerging anomaly detection techniques in an unbiased and fully transparent way.

This competition hosted on Kaggle (this https URL) is the first part of a series of follow-up competitions and hackathons related to the "Assurance for Space Domain AI Applications" project funded by the European Space Agency (this https URL). The competition idea is based on one of the real-life AI security threats identified within the project -- the adversarial poisoning of continuously fine-tuned satellite telemetry forecasting models. The task is to develop methods for finding and reconstructing triggers (trojans) in advanced models for satellite telemetry forecasting used in safety-critical space operations. Participants are provided with 1) a large public dataset of real-life multivariate satellite telemetry (without triggers), 2) a reference model trained on the clean data, 3) a set of poisoned neural hierarchical interpolation (N-HiTS) models for time series forecasting trained on the dataset with injected triggers, and 4) Jupyter notebook with the training pipeline and baseline algorithm (the latter will be published in the last month of the competition). The main task of the competition is to reconstruct a set of 45 triggers (i.e., short multivariate time series segments) injected into the training data of the corresponding set of 45 poisoned models. The exact characteristics (i.e., shape, amplitude, and duration) of these triggers must be identified by participants. The popular Neural Cleanse method is adopted as a baseline, but it is not designed for time series analysis and new approaches are necessary for the task. The impact of the competition is not limited to the space domain, but also to many other safety-critical applications of advanced time series analysis where model poisoning may lead to serious consequences.

Quantum architecture Search (QAS) is a promising direction for optimization and automated design of quantum circuits towards quantum advantage. Recent techniques in QAS emphasize Multi-Layer Perceptron (MLP)-based deep Q-networks. However, their interpretability remains challenging due to the large number of learnable parameters and the complexities involved in selecting appropriate activation functions. In this work, to overcome these challenges, we utilize the Kolmogorov-Arnold Network (KAN) in the QAS algorithm, analyzing their efficiency in the task of quantum state preparation and quantum chemistry. In quantum state preparation, our results show that in a noiseless scenario, the probability of success is 2 to 5 times higher than MLPs. In noisy environments, KAN outperforms MLPs in fidelity when approximating these states, showcasing its robustness against noise. In tackling quantum chemistry problems, we enhance the recently proposed QAS algorithm by integrating curriculum reinforcement learning with a KAN structure. This facilitates a more efficient design of parameterized quantum circuits by reducing the number of required 2-qubit gates and circuit depth. Further investigation reveals that KAN requires a significantly smaller number of learnable parameters compared to MLPs; however, the average time of executing each episode for KAN is higher.

The quality of training datasets for deep neural networks is a key factor contributing to the accuracy of resulting models. This effect is amplified in difficult tasks such as object detection. Dealing with errors in datasets is often limited to accepting that some fraction of examples are incorrect, estimating their confidence, and either assigning appropriate weights or ignoring uncertain ones during training. In this work, we propose a different approach. We introduce the Confident Learning for Object Detection (CLOD) algorithm for assessing the quality of each label in object detection datasets, identifying missing, spurious, mislabeled, and mislocated bounding boxes and suggesting corrections. By focusing on finding incorrect examples in the training datasets, we can eliminate them at the root. Suspicious bounding boxes can be reviewed to improve the quality of the dataset, leading to better models without further complicating their already complex architectures. The proposed method is able to point out nearly 80% of artificially disturbed bounding boxes with a false positive rate below 0.1. Cleaning the datasets by applying the most confident automatic suggestions improved mAP scores by 16% to 46%, depending on the dataset, without any modifications to the network architectures. This approach shows promising potential in rectifying state-of-the-art object detection datasets.

Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples, leading to significant gaps in context-specific anomaly understanding. In this paper, we propose \textbf{A}daptive \textbf{P}rompt \textbf{T}uning with semantic alignment for anomaly detection (APT), a groundbreaking prior knowledge-free, few-shot framework and overcomes the limitations of traditional prompt-based approaches. APT uses self-generated anomaly samples with noise perturbations to train learnable prompts that capture context-dependent anomalies in different scenarios. To prevent overfitting to synthetic noise, we propose a Self-Optimizing Meta-prompt Guiding Scheme (SMGS) that iteratively aligns the prompts with general anomaly semantics while incorporating diverse synthetic anomaly. Our system not only advances pixel-wise anomaly detection, but also achieves state-of-the-art performance on multiple benchmark datasets without requiring prior knowledge for prompt crafting, establishing a robust and versatile solution for real-world anomaly detection.

Recent advancements in computational chemistry have leveraged the power of trans-former-based language models, such as MoLFormer, pre-trained using a vast amount of simplified molecular-input line-entry system (SMILES) sequences, to understand and predict molecular properties and activities, a critical step in fields like drug discovery and materials science. To further improve performance, researchers have introduced graph neural networks with graph-based molecular representations, such as GEM, incorporating the topology, geometry, 2D or even 3D structures of molecules into pre-training. While most of molecular graphs in existing studies were automatically converted from SMILES sequences, it is to assume that transformer-based language models might be able to implicitly learn structure-aware representations from SMILES sequences. In this paper, we propose \ours{} -- a SMILES-based \underline{\em M}olecular \underline{\em L}anguage \underline{\em M}odel, which randomly masking SMILES subsequences corresponding to specific molecular \underline{\em F}unctional \underline{\em G}roups to incorporate structure information of atoms during the pre-training phase. This technique aims to compel the model to better infer molecular structures and properties, thus enhancing its predictive capabilities. Extensive experimental evaluations across 11 benchmark classification and regression tasks in the chemical domain demonstrate the robustness and superiority of \ours{}. Our findings reveal that \ours{} outperforms existing pre-training models, either based on SMILES or graphs, in 9 out of the 11 downstream tasks, ranking as a close second in the remaining ones.

Classical novae are thermonuclear explosions that occur on the surfaces of white dwarf stars in interacting binary systems (Bode & Evans 2008). It has long been thought that the luminosity of classical novae is powered by continued nuclear burning on the surface of the white dwarf after the initial runaway (Gallaher & Starrfield 1978). However, recent observations of GeV $\gamma$-rays from classical novae have hinted that shocks internal to the nova ejecta may dominate the nova emission. Shocks have also been suggested to power the luminosity of events as diverse as stellar mergers (Metzger & Pejcha 2017), supernovae (Moriya et al. 2018), and tidal disruption events (Roth et al. 2016), but observational confirmation has been lacking. Here we report simultaneous space-based optical and $\gamma$-ray observations of the 2018 nova V906 Carinae (ASASSN-18fv), revealing a remarkable series of distinct correlated flares in both bands. The optical and $\gamma$-ray flares occur simultaneously, implying a common origin in shocks. During the flares, the nova luminosity doubles, implying that the bulk of the luminosity is shock-powered. Furthermore, we detect concurrent but weak X-ray emission from deeply embedded shocks, confirming that the shock power does not appear in the X-ray band and supporting its emergence at longer wavelengths. Our data, spanning the spectrum from radio to $\gamma$-ray, provide direct evidence that shocks can power substantial luminosity in classical novae and other optical transients.

The paper addresses challenges in storing and retrieving sequences in contexts like anomaly detection, behavior prediction, and genetic information analysis. Associative Knowledge Graphs (AKGs) offer a promising approach by leveraging sparse graph structures to encode sequences. The objective was to develop a method for sequence storage and retrieval using AKGs that maintain high memory capacity and context-based retrieval accuracy while introducing algorithms for efficient element ordering. The study utilized Sequential Structural Associative Knowledge Graphs (SSAKGs). These graphs encode sequences as transitive tournaments with nodes representing objects and edges defining the order. Four ordering algorithms were developed and tested: Simple Sort, Node Ordering, Enhanced Node Ordering, and Weighted Edges Node Ordering. The evaluation was conducted on synthetic datasets consisting of random sequences of varying lengths and distributions, and real-world datasets, including sentence-based sequences from the NLTK library and miRNA sequences mapped symbolically with a window-based approach. Metrics such as precision, sensitivity, and specificity were employed to assess performance. SSAKGs exhibited quadratic growth in memory capacity relative to graph size. This study introduces a novel structural approach for sequence storage and retrieval. Key advantages include no training requirements, flexible context-based reconstruction, and high efficiency in sparse memory graphs. With broad applications in computational neuroscience and bioinformatics, the approach offers scalable solutions for sequence-based memory tasks.

The outbreak of the SARS-CoV-2 pandemic has put healthcare systems worldwide to their limits, resulting in increased waiting time for diagnosis and required medical assistance. With chest radiographs (CXR) being one of the most common COVID-19 diagnosis methods, many artificial intelligence tools for image-based COVID-19 detection have been developed, often trained on a small number of images from COVID-19-positive patients. Thus, the need for high-quality and well-annotated CXR image databases increased. This paper introduces POLCOVID dataset, containing chest X-ray (CXR) images of patients with COVID-19 or other-type pneumonia, and healthy individuals gathered from 15 Polish hospitals. The original radiographs are accompanied by the preprocessed images limited to the lung area and the corresponding lung masks obtained with the segmentation model. Moreover, the manually created lung masks are provided for a part of POLCOVID dataset and the other four publicly available CXR image collections. POLCOVID dataset can help in pneumonia or COVID-19 diagnosis, while the set of matched images and lung masks may serve for the development of lung segmentation solutions.

Neuro-fuzzy systems are a technique of explainable artificial intelligence (XAI). They elaborate knowledge models as a set of fuzzy rules. Fuzzy sets are crucial components of fuzzy rules. They are used to model linguistic terms. In this paper, we present an automatic extraction of fuzzy rules in the natural English language. Full implementation is available free from a public repository.

Gallium oxide is a novel advanced material gaining increasing attention for its unique combination of functional properties. It forms in several phases or polymorphs - {\alpha}, {\beta}, {\gamma}, and {\kappa} - having variable properties because of different lattice symmetries. Optical properties are of particular importance as they determine specific device applications and can also be used for phase identification. However, a direct comparison of optical polymorph signatures, including such critical parameters as bandgaps, is challenging due to the scattered, limited, or even absent data for certain phases in the literature. To address this issue, in the present work we systematically cross-correlate optical emission and absorption features of {\alpha}, {\beta}, {\gamma}, and {\kappa} thin films, as well as differently oriented {\beta}-phase bulk crystals and {\gamma}/{\beta} double polymorph structures. We demonstrate that the optical bandgap and emission features scale consistently across these polymorphs upon minimization of the methodological uncertainties. As a result, this work provides a comparative library of near- and far-field optical signatures of the polymorphs for use by the multidisciplinary research community working with gallium oxide.

Dusty disks around planets in outer reaches of exo-planetary systems can be detected as long-lasting occultations, provided the observer is close to the planet's orbital plane. Here we report follow-up observations of ASASSN-24fw (Gaia 07:05:18.97+06:12:19.4), a 4-magnitude dimming event of a main-sequence star which lasted 8.5 months. Using optical spectroscopy with KOSMOS (APO), MagE (Magellan) and GHOST (Gemini-S), we find strong Na I D absorption indicating that the occulter is gas rich. We detect multiple low-ionization metal emission lines with velocity dispersion <10 km/s blue-shifted by 27 km/s with respect to the system, which likely originate in the occulter, as well as blue-shifted and broad (200 km/s) Halpha line, which likely originates in the inner circumstellar disk. We confirm the previously reported occultations in 1981 and 1937 seen in historic data, yielding a semi-major axis of the occulter's orbital motion around the star of 14 AU. Assuming that the occulter is a circumplanetary disk filling 30-100% of the Hill radius, we derive the planet's mass of 0.5-19 MJupiter and a circumplanetary disk mass of 1% of the mass of the Moon. Given the age of the star (>2 Gyr), the disk is unlikely to be a survivor of the planet formation stage and is more likely to be a result of a planetary collision. If Na D absorption and metal emission lines originate in the circumplanetary disk, the observations presented here are the first discovery of a planet-driven wind or of circumsecondary disk rotation.

Medical image segmentation methods generally assume that the process from medical image to segmentation is unbiased, and use neural networks to establish conditional probability models to complete the segmentation task. This assumption does not consider confusion factors, which can affect medical images, such as complex anatomical variations and imaging modality limitations. Confusion factors obfuscate the relevance and causality of medical image segmentation, leading to unsatisfactory segmentation results. To address this issue, we propose a multi-causal aware modeling backdoor-intervention optimization (MAMBO-NET) network for medical image segmentation. Drawing insights from causal inference, MAMBO-NET utilizes self-modeling with multi-Gaussian distributions to fit the confusion factors and introduce causal intervention into the segmentation process. Moreover, we design appropriate posterior probability constraints to effectively train the distributions of confusion factors. For the distributions to effectively guide the segmentation and mitigate and eliminate the Impact of confusion factors on the segmentation, we introduce classical backdoor intervention techniques and analyze their feasibility in the segmentation task. To evaluate the effectiveness of our approach, we conducted extensive experiments on five medical image datasets. The results demonstrate that our method significantly reduces the influence of confusion factors, leading to enhanced segmentation accuracy.

The Pencil Code is a highly modular physics-oriented simulation code that can be adapted to a wide range of applications. It is primarily designed to solve partial differential equations (PDEs) of compressible hydrodynamics and has lots of add-ons ranging from astrophysical magnetohydrodynamics (MHD) to meteorological cloud microphysics and engineering applications in combustion. Nevertheless, the framework is general and can also be applied to situations not related to hydrodynamics or even PDEs, for example when just the message passing interface or input/output strategies of the code are to be used. The code can also evolve Lagrangian (inertial and noninertial) particles, their coagulation and condensation, as well as their interaction with the fluid.