Effective human-AI interaction relies on AI's ability to accurately perceive and interpret human emotions. Current benchmarks for vision and vision-language models are severely limited, offering a narrow emotional spectrum that overlooks nuanced states (e.g., bitterness, intoxication) and fails to distinguish subtle differences between related feelings (e.g., shame vs. embarrassment). Existing datasets also often use uncontrolled imagery with occluded faces and lack demographic diversity, risking significant bias. To address these critical gaps, we introduce EmoNet Face, a comprehensive benchmark suite. EmoNet Face features: (1) A novel 40-category emotion taxonomy, meticulously derived from foundational research to capture finer details of human emotional experiences. (2) Three large-scale, AI-generated datasets (EmoNet HQ, Binary, and Big) with explicit, full-face expressions and controlled demographic balance across ethnicity, age, and gender. (3) Rigorous, multi-expert annotations for training and high-fidelity evaluation. (4) We built EmpathicInsight-Face, a model achieving human-expert-level performance on our benchmark. The publicly released EmoNet Face suite - taxonomy, datasets, and model - provides a robust foundation for developing and evaluating AI systems with a deeper understanding of human emotions.

The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (Task, Dataset, Metric, Score) quadruples from research papers. The findings reveal significant insights into the strengths and limitations of each model and context type, providing valuable guidance for future AI research automation efforts.

State-of-the-art AI models largely lack an understanding of the cause-effect relationship that governs human understanding of the real world. Consequently, these models do not generalize to unseen data, often produce unfair results, and are difficult to interpret. This has led to efforts to improve the trustworthiness aspects of AI models. Recently, causal modeling and inference methods have emerged as powerful tools. This review aims to provide the reader with an overview of causal methods that have been developed to improve the trustworthiness of AI models. We hope that our contribution will motivate future research on causality-based solutions for trustworthy AI.

RDF knowledge graphs (KG) are powerful data structures to represent factual statements created from heterogeneous data sources. KG creation is laborious and demands data management techniques to be executed efficiently. This paper tackles the problem of the automatic generation of KG creation processes declaratively specified; it proposes techniques for planning and transforming heterogeneous data into RDF triples following mapping assertions specified in the RDF Mapping Language (RML). Given a set of mapping assertions, the planner provides an optimized execution plan by partitioning and scheduling the execution of the assertions. First, the planner assesses an optimized number of partitions considering the number of data sources, type of mapping assertions, and the associations between different assertions. After providing a list of partitions and assertions that belong to each partition, the planner determines their execution order. A greedy algorithm is implemented to generate the partitions' bushy tree execution plan. Bushy tree plans are translated into operating system commands that guide the execution of the partitions of the mapping assertions in the order indicated by the bushy tree. The proposed optimization approach is evaluated over state-of-the-art RML-compliant engines, and existing benchmarks of data sources and RML triples maps. Our experimental results suggest that the performance of the studied engines can be considerably improved, particularly in a complex setting with numerous triples maps and large data sources. As a result, engines that time out in complex cases are enabled to produce at least a portion of the KG applying the planner.

Organic Computing is an initiative in the field of systems engineering that proposed to make use of concepts such as self-adaptation and self-organisation to increase the robustness of technical systems. Based on the observation that traditional design and operation concepts reach their limits, transferring more autonomy to the systems themselves should result in a reduction of complexity for users, administrators, and developers. However, there seems to be a need for an updated definition of the term "Organic Computing", of desired properties of technical, organic systems, and the objectives of the Organic Computing initiative. With this article, we will address these points.

Entity linking (EL) is the task of automatically identifying entity mentions in text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. Throughout the past decade, a plethora of EL systems and pipelines have become available, where performance of individual systems varies heavily across corpora, languages or domains. Linking performance varies even between different mentions in the same text corpus, where, for instance, some EL approaches are better able to deal with short surface forms while others may perform better when more context information is available. To this end, we argue that performance may be optimised by exploiting results from distinct EL systems on the same corpus, thereby leveraging their individual strengths on a per-mention basis. In this paper, we introduce a supervised approach which exploits the output of multiple ready-made EL systems by predicting the correct link on a per-mention basis. Experimental results obtained on existing ground truth datasets and exploiting three state-of-the-art EL systems show the effectiveness of our approach and its capacity to significantly outperform the individual EL systems as well as a set of baseline methods.

Knowledge graphs have become popular over the past decade and frequently rely on the Resource Description Framework (RDF) or Property Graph (PG) databases as data models. However, the query languages for these two data models -- SPARQL for RDF and the PG traversal language Gremlin -- are lacking interoperability. We present Gremlinator, the first translator from SPARQL -- the W3C standardized language for RDF -- and Gremlin -- a popular property graph traversal language. Gremlinator translates SPARQL queries to Gremlin path traversals for executing graph pattern matching queries over graph databases. This allows a user, who is well versed in SPARQL, to access and query a wide variety of Graph Data Management Systems (DMSs) avoiding the steep learning curve for adapting to a new Graph Query Language (GQL). Gremlin is a graph computing system-agnostic traversal language (covering both OLTP graph database or OLAP graph processors), making it a desirable choice for supporting interoperability for querying Graph DMSs. Gremlinator currently supports the translation of a subset of SPARQL 1.0, specifically the SPARQL SELECT queries.

Graph data management (also called NoSQL) has revealed beneficial characteristics in terms of flexibility and scalability by differently balancing between query expressivity and schema flexibility. This peculiar advantage has resulted into an unforeseen race of developing new task-specific graph systems, query languages and data models, such as property graphs, key-value, wide column, resource description framework (RDF), etc. Present-day graph query languages are focused towards flexible graph pattern matching (aka sub-graph matching), whereas graph computing frameworks aim towards providing fast parallel (distributed) execution of instructions. The consequence of this rapid growth in the variety of graph-based data management systems has resulted in a lack of standardization. Gremlin, a graph traversal language, and machine provides a common platform for supporting any graph computing system (such as an OLTP graph database or OLAP graph processors). We present a formalization of graph pattern matching for Gremlin queries. We also study, discuss and consolidate various existing graph algebra operators into an integrated graph algebra.

The Lunar Laser Ranging (LLR) experiment has accumulated 50 years of range data of improving accuracy from ground stations to the laser retroreflector arrays (LRAs) on the lunar surface. The upcoming decade offers several opportunities to break new ground in data precision through the deployment of the next generation of single corner-cube lunar retroreflectors and active laser transponders. This is likely to expand the LLR station network. Lunar dynamical models and analysis tools have the potential to improve and fully exploit the long temporal baseline and precision allowed by millimetric LLR data. Some of the model limitations are outlined for future efforts. Differential observation techniques will help mitigate some of the primary limiting factors and reach unprecedented accuracy. Such observations and techniques may enable the detection of several subtle signatures required to understand the dynamics of the Earth-Moon system and the deep lunar interior. LLR model improvements would impact multi-disciplinary fields that include lunar and planetary science, Earth science, fundamental physics, celestial mechanics and ephemerides.

Occurrences of catastrophes such as natural or man-made disasters trigger the spread of rumours over social media at a rapid pace. Presenting a trustworthy and summarized account of the unfolding event in near real-time to the consumers of such potentially unreliable information thus becomes an important task. In this work, we propose MTLTS, the first end-to-end solution for the task that jointly determines the credibility and summary-worthiness of tweets. Our credibility verifier is designed to recursively learn the structural properties of a Twitter conversation cascade, along with the stances of replies towards the source tweet. We then take a hierarchical multi-task learning approach, where the verifier is trained at a lower layer, and the summarizer is trained at a deeper layer where it utilizes the verifier predictions to determine the salience of a tweet. Different from existing disaster-specific summarizers, we model tweet summarization as a supervised task. Such an approach can automatically learn summary-worthy features, and can therefore generalize well across domains. When trained on the PHEME dataset [29], not only do we outperform the strongest baselines for the auxiliary task of verification/rumour detection, we also achieve 21 - 35% gains in the verified ratio of summary tweets, and 16 - 20% gains in ROUGE1-F1 scores over the existing state-of-the-art solutions for the primary task of trustworthy summarization.

Fairness-aware mining of massive data streams is a growing and challenging concern in the contemporary domain of machine learning. Many stream learning algorithms are used to replace humans at critical decision-making points e.g., hiring staff, assessing credit risk, etc. This calls for handling massive incoming information with minimum response delay while ensuring fair and high quality decisions. Recent discrimination-aware learning methods are optimized based on overall accuracy. However, the overall accuracy is biased in favor of the majority class; therefore, state-of-the-art methods mainly diminish discrimination by partially or completely ignoring the minority class. In this context, we propose a novel adaptation of Na\"ive Bayes to mitigate discrimination embedded in the streams while maintaining high predictive performance for both the majority and minority classes. Our proposed algorithm is simple, fast, and attains multi-objective optimization goals. To handle class imbalance and concept drifts, a dynamic instance weighting module is proposed, which gives more importance to recent instances and less importance to obsolete instances based on their membership in minority or majority class. We conducted experiments on a range of streaming and static datasets and deduced that our proposed methodology outperforms existing state-of-the-art fairness-aware methods in terms of both discrimination score and balanced accuracy.

In recent years, graph neural network (GNN) based approaches have emerged as a powerful technique to encode complex topological structure of crystal materials in an enriched representation space. These models are often supervised in nature and using the property-specific training data, learn relationship between crystal structure and different properties like formation energy, bandgap, bulk modulus, etc. Most of these methods require a huge amount of property-tagged data to train the system which may not be available for different properties. However, there is an availability of a huge amount of crystal data with its chemical composition and structural bonds. To leverage these untapped data, this paper presents CrysGNN, a new pre-trained GNN framework for crystalline materials, which captures both node and graph level structural information of crystal graphs using a huge amount of unlabelled material data. Further, we extract distilled knowledge from CrysGNN and inject into different state of the art property predictors to enhance their property prediction accuracy. We conduct extensive experiments to show that with distilled knowledge from the pre-trained model, all the SOTA algorithms are able to outperform their own vanilla version with good margins. We also observe that the distillation process provides a significant improvement over the conventional approach of finetuning the pre-trained model. We have released the pre-trained model along with the large dataset of 800K crystal graph which we carefully curated; so that the pretrained model can be plugged into any existing and upcoming models to enhance their prediction accuracy.

Ever since the vision was formulated, the Semantic Web has inspired many generations of innovations. Semantic technologies have been used to share vast amounts of information on the Web, enhance them with semantics to give them meaning, and enable inference and reasoning on them. Throughout the years, semantic technologies, and in particular knowledge graphs, have been used in search engines, data integration, enterprise settings, and machine learning. In this paper, we recap the classical concepts and foundations of the Semantic Web as well as modern and recent concepts and applications, building upon these foundations. The classical topics we cover include knowledge representation, creating and validating knowledge on the Web, reasoning and linking, and distributed querying. We enhance this classical view of the so-called ``Semantic Web Layer Cake'' with an update of recent concepts that include provenance, security and trust, as well as a discussion of practical impacts from industry-led contributions. We conclude with an outlook on the future directions of the Semantic Web.

We reconsider velocity addition/subtraction in Special Relativity and re-derive its well-known non-commutative and non-associative algebraic properties in a self contained way, including various explicit expressions for the Thomas angle, the derivation of which will be seen to be not as challenging as often suggested. All this is based on the polar-decomposition theorem in the traditional component language, in which Lorentz transformations are ordinary matrices. In the second part of this paper we offer a less familiar alternative geometric view, that leads to an invariant definition of the concept of relative velocity between two states of motion, which is based on the boost-link-theorem, of which we also offer an elementary proof that does not seem to be widely known in the relativity literature. Finally we compare this to the corresponding geometric definitions in Galilei-Newton spacetime, emphasising similarities and differences.

Knowledge graphs have emerged as expressive data structures for Web data. Knowledge graph potential and the demand for ecosystems to facilitate their creation, curation, and understanding, is testified in diverse domains, e.g., biomedicine. The Shapes Constraint Language (SHACL) is the W3C recommendation language for integrity constraints over RDF knowledge graphs. Enabling quality assements of knowledge graphs, SHACL is rapidly gaining attention in real-world scenarios. SHACL models integrity constraints as a network of shapes, where a shape contains the constraints to be fullfiled by the same entities. The validation of a SHACL shape schema can face the issue of tractability during validation. To facilitate full adoption, efficient computational methods are required. We present Trav-SHACL, a SHACL engine capable of planning the traversal and execution of a shape schema in a way that invalid entities are detected early and needless validations are minimized. Trav-SHACL reorders the shapes in a shape schema for efficient validation and rewrites target and constraint queries for the fast detection of invalid entities. Trav-SHACL is empirically evaluated on 27 testbeds executed against knowledge graphs of up to 34M triples. Our experimental results suggest that Trav-SHACL exhibits high performance gradually and reduces validation time by a factor of up to 28.93 compared to the state of the art.

Whereas the availability of data has seen a manyfold increase in past years, its value can be only shown if the data variety is effectively tackled ---one of the prominent Big Data challenges. The lack of data interoperability limits the potential of its collective use for novel applications. Achieving interoperability through the full transformation and integration of diverse data structures remains an ideal that is hard, if not impossible, to achieve. Instead, methods that can simultaneously interpret different types of data available in different data structures and formats have been explored. On the other hand, many query languages have been designed to enable users to interact with the data, from relational, to object-oriented, to hierarchical, to the multitude emerging NoSQL languages. Therefore, the interoperability issue could be solved not by enforcing physical data transformation, but by looking at techniques that are able to query heterogeneous sources using one uniform language. Both industry and research communities have been keen to develop such techniques, which require the translation of a chosen 'universal' query language to the various data model specific query languages that make the underlying data accessible. In this article, we survey more than forty query translation methods and tools for popular query languages, and classify them according to eight criteria. In particular, we study which query language is a most suitable candidate for that 'universal' query language. Further, the results enable us to discover the weakly addressed and unexplored translation paths, to discover gaps and to learn lessons that can benefit future research in the area.

Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where the lack of precision on particularly ambiguous mentions often spoils the usefulness of automated disambiguation results in real applications. A priori approximations of the difficulty to link a particular entity mention can facilitate flagging of critical cases as part of semi-automated EL systems, while detecting latent factors that affect the EL performance, like corpus-specific features, can provide insights on how to improve a system based on the special characteristics of the underlying corpus. In this paper, we first introduce a consensus-based method to generate difficulty labels for entity mentions on arbitrary corpora. The difficulty labels are then exploited as training data for a supervised classification task able to predict the EL difficulty of entity mentions using a variety of features. Experiments over a corpus of news articles show that EL difficulty can be estimated with high accuracy, revealing also latent features that affect EL performance. Finally, evaluation results demonstrate the effectiveness of the proposed method to inform semi-automated EL pipelines.

Asymptotic symmetries are a general and important feature of theories with long-ranging fields, such as gravity, electromagnetism, and Yang-Mills. They appear in the formalism once the analytic behaviour of fields near infinity is specified and have received a renewed interest in the last years after a possible connection with the information-loss paradox has been conjectured. One of the various methods used to study the asymptotic symmetries of field theories relies on the Hamiltonian formalism and was introduced in the seminal work of Henneaux and Troessaert, who successfully applied it to the case of gravity and electrodynamics. The main advantage of this approach is that the study of the asymptotic symmetries ensues from clear-cut first principles. After an extensive review of how the Hamiltonian approach to study asymptotic symmetries of gauge theories works, we apply these methods to two specific situations of physical interest. First, we deal with the non-abelian Yang-Mills case and we show that the above principles lead to trivial asymptotic symmetries (nothing else than the Poincar\'e group) and, as a consequence, to a vanishing total colour charge. This is a new and somewhat unexpected result. It implies that no globally colour-charged states exist in classical non-abelian Yang-Mills theory. The second situation considered is a scalar field minimally-coupled to an abelian gauge field, which can be used to study, at the same time, two specific cases: scalar electrodynamics and the abelian Higgs model. We show that the situation in scalar electrodynamics amply depends on whether the scalar field is massive or massless, insofar as, in the latter case, one cannot canonically implement asymptotic symmetries. Furthermore, we illustrate that, in the abelian Higgs model, the asymptotic canonical symmetries reduce to the Poincar\'e group in an unproblematic fashion.

Knowledge Graphs (KGs) have emerged as fundamental platforms for powering intelligent decision-making and a wide range of Artificial Intelligence (AI) services across major corporations such as Google, Walmart, and AirBnb. KGs complement Machine Learning (ML) algorithms by providing data context and semantics, thereby enabling further inference and question-answering capabilities. The integration of KGs with neuronal learning (e.g., Large Language Models (LLMs)) is currently a topic of active research, commonly named neuro-symbolic AI. Despite the numerous benefits that can be accomplished with KG-based AI, its growing ubiquity within online services may result in the loss of self-determination for citizens as a fundamental societal issue. The more we rely on these technologies, which are often centralised, the less citizens will be able to determine their own destinies. To counter this threat, AI regulation, such as the European Union (EU) AI Act, is being proposed in certain regions. The regulation sets what technologists need to do, leading to questions concerning: How can the output of AI systems be trusted? What is needed to ensure that the data fuelling and the inner workings of these artefacts are transparent? How can AI be made accountable for its decision-making? This paper conceptualises the foundational topics and research pillars to support KG-based AI for self-determination. Drawing upon this conceptual framework, challenges and opportunities for citizen self-determination are illustrated and analysed in a real-world scenario. As a result, we propose a research agenda aimed at accomplishing the recommended objectives.