ABSTRACT. AI planning is a central problem in Knowledge Representation (KR), as it requires expressive action theories, structured domain models, and formal reasoning mechanisms. With the increase of domain complexity, manually building planning models becomes a tedious and error-prone task, highlighting the need for methods that can learn symbolic knowledge from unstructured data while preserving formal semantics. Recent advances in language processing, especially large language models (LLMs), promise great potential for model extraction from text. They, however, are prone to hallucination and lack the ability to validate the extracted knowledge required for formal planning and reasoning. To address the above challenges, we introduce a novel methodology for automatic extraction of formal models expressed in the Planning Domain Definition Language (PDDL) from textual instructions. Our methodology combines linguistic, statistical, symbolic and LLM-based techniques within a knowledge-driven framework. In doing so, it enables the learning of symbolic abstractions such as action schemas, type hierarchies, preconditions, and effects, while also providing an explicit mechanism for explainability by making the derivation of the final formal representation transparent and traceable. As an intermediate representation, we construct a language-independent knowledge graph, called a Situation Model (SM), which captures relational dependencies and domain constraints in a structured and reusable form. We evaluate the proposed hybrid approach by investigating syntactic and semantic correctness via AI planning, as well as validation against manually created plans from everyday-life domains, demonstrating the benefits of integrating KR techniques with LLM-based extraction.

ABSTRACT. Building image classification models remains cumbersome in data-scarce domains, where collecting large labeled datasets is impractical. In-context learning (ICL) is a promising paradigm for few-shot image classification (FSIC), but prior work has underexplored the relative importance of encoder pretraining versus fusion-layer training data. We present PictSure, a vision-only ICL family of models that demonstrates the potential of easy-to-use fusion transformer architectures, as well as the need for better embedding representations across a wider range of image domains. In both in-domain and out-of-domain evaluations, we find that encoder pretraining is the dominant determinant of performance. Crucially, varying the training dataset for the fusion transformer, from ImageNet alone to diverse multi-domain mixtures, provides negligible performance gains, demonstrating that the fusion layer quickly learns to read any well-structured embedding space regardless of task variety. These results show that the bottleneck in visual ICL is representation quality, not fusion-module training diversity. To facilitate adoption and reproducibility, we release all model weights as open-source artifacts and provide an MCP server that exposes PictSure as a callable tool for LLM-based agentic systems, enabling few-shot image classification to be invoked directly within AI pipelines without integration overhead. Code can be found at <GitHub Placeholder> and models at <Huggingface Placeholder>.

ABSTRACT. The Ride-Hailing Problem is an online optimization challenge that coordinates a fleet of vehicles to serve requests revealed over time. The problem is NP-hard, and many solution approaches use stochastic or machine-learning algorithms, which perform well but are difficult to interpret. We study the trade-offs between performance and explainability. Our results show that greedy assignment consistently outperforms more complex methods, indicating that explainability need not come at the cost of efficiency. We also find that the effectiveness of repositioning strategies strongly depends on demand patterns, highlighting the value of context-aware policies.

ABSTRACT. Abstract. Artificial neural networks are one of the key technologies in machine learning. In particular, networks using the ReLU-activation function are widely used in the community of formal verification and theoretical machine learning. Such networks can be represented by their linear decomposition, which consists of a set of convex polytopes together with associated linear functions that capture the network’s behavior. This representation provides detailed insights into the learned structure of the model and enables the quantitative analysis of both linear and nonlinear verification problems. However, obtaining the linear decomposition poses a computational challenge. To date, only two algorithms have been proposed for this task, yet a systematic and objective comparison between them is still missing. In this work, we implemented both approaches and conducted a comprehensive empirical evaluation of their runtime across a range of benchmark settings. Our results show that while one algorithm outperforms the other in many scenarios, both exhibit distinct strengths and weaknesses. Consequently, no single algorithm emerges as the clear winner, highlighting that performance is fundamentally shaped by the network’s structural properties.

ABSTRACT. Neural Networks (NN) are recognized as universal approximators, yet the reasons behind their remarkable generalization capabilities remain partially unresolved. One potential explanation is the manifold hypothesis, which suggests that NNs identify low-dimensional manifolds within the high-dimensional real-world data. In each layer of a NN, the data lies on/near a manifold, a so-called representation manifold, which gets progressively flatter as the layer's depth increases. Since NNs function on these data manifolds rather than isolated points, generalization becomes feasible. Notably, manifolds in the deeper layers of trained NNs tend to be flatter, while at the same time, deeper networks generally achieve higher accuracy. This leads to the following hypothesis: There is a correlation between the accuracy of a NN and the flatness of manifolds in the final layer of the NN. To investigate this, we empirically test the hypothesis by training a CNN with various hyperparameter sets. We assess both the flatness of the manifold and the accuracy on a test set, exploring their connection. We use correlation analysis, plots, statistical tests and examine whether flatness can be predicted from the hyperparameters.

ABSTRACT. We present a neurosymbolic approach, i.e., combining symbolic and subsymbolic artificial intelligence, to validating offer documents in regulated public institutions. We employ a language model to extract information and then aggregate with a Logic Tensor Network to make an auditable decision. In regulated public institutions, decisions must be made in a manner that is both factually correct and legally verifiable. Our neurosymbolic approach allows existing domain-specific knowledge to be linked to the semantic text understanding of language models. The decisions resulting from our pipeline can be justified by predicate values, rule truth values and corresponding text passages, which enables rule checking based on a real corpus of offer documents. Our experiments on a real corpus show that the proposed pipeline achieves performance comparable to existing models, while its key advantage lies in its interpretability, modular predicate extraction, and explicit support for XAI (Explainable AI).

ABSTRACT. The development of systems that allocate resources among stakeholders in a manner aligned with societal objectives is of paramount importance in both static decision problems and dynamic settings involving repeated interactions. In scenarios where these systems interact with human individuals or groups of people, reliance on efficiency- or cost-based evaluation criteria is inadequate. Consequently, allocation models should explicitly incorporate fairness requirements to ensure outcomes that remain consistent with normative social considerations. While SocialCOP enables the integration of fairness constraints into MiniZinc models for shared decision and fair division problems, these approaches primarily address single allocations. Repeated application of such models may systematically favor or disadvantage the same agents, leading to unfair long-term outcomes. We propose a framework for fairness-aware repeated resource allocation in which agent priorities are dynamically reweighted across iterations. A Deep Reinforcement Learning (DRL) policy maps historical utility values, fairness statistics (e.g., the Gini index), and problem parameters to priority weights for subsequent allocations. Hard feasibility requirements are enforced through Constraint Optimization in the underlying MiniZinc model, while fairness considerations are incorporated in the reward function as well as in the underlying MiniZinc environment. The approach is integrated into the SocialCOP environment and evaluated on repeated allocation scenarios such as weekly table assignments. Experimental results indicate that the learned policies achieve lower inequality while maintaining or improving overall allocation efficiency compared to deterministic baselines, demonstrating the effectiveness of learning-based reweighting for repeated fair allocation problems.

ABSTRACT. Passive Acoustic Monitoring (PAM) is increasingly used for biodiversity monitoring, but training sound event detectors for PAM remains difficult because strong temporal annotations are expensive to obtain. Archival sound libraries provide weakly labelled focal recordings at scale, yet these recordings differ substantially from PAM soundscapes. Focal recordings typically contain one dominant species under relatively clean conditions, whereas PAM recordings often contain overlapping vocalisations from multiple species together with environmental noise. This mismatch limits the transferability of weakly supervised models trained on sound libraries. This paper investigates whether synthetic multi-species training augmentation can reduce this transfer gap. We build on a weakly supervised sound event detection pipeline using BirdNET embeddings and a linear classifier, and augment the training data by synthetically mixing focal recordings into artificial multi-species soundscapes with randomized temporal overlap and mixture weights. The PAM evaluation data remain unchanged. Experiments on five anuran species show improvements in transfer performance. Compared with training on original focal recordings only, synthetic augmentation increases recall and F1-score at both bag and segment level, while causing a moderate reduction in precision. The best bag-level micro-F1 improves from 0.6792 to 0.7687, and the best segment-level micro-F1 improves from 0.5473 to 0.6120. These results indicate that simulating multi-species co-occurrence during training is a practical way to improve weakly supervised transfer from sound libraries to PAM data.

ABSTRACT. The integration of Artificial Intelligence (AI) techniques in e-learning ecosystems is expanding, although the algorithms used and decision steps often remain a mystery to its users. Potential privacy risks, fairness issues, lack of transparency and trust are major concerns for the adoption of AI in digital education, related, for example, to personalized teaching and learning recommendations, feedback, interventions and e-assessment. The aim of this work-in-progress is to explore the importance of integrating explainable AI (xAI) methods in Digital Ecosystems in Research and Education (DERE) for Education 4.0 (E4.0) and present a framework structuring the main stakeholders and xAI use scenarios constructed following a design-science approach.