Abstract
Counterfactual explanations (CFs) help users understand and act on black-box machine learning decisions by suggesting minimal changes to achieve a desired outcome. However, existing methods often ignore individual feasibility, leading to unrealistic or unactionable recommendations. We propose a personalized CF generation method based on cluster-specific fine-tuning of Generative Adversarial Networks (GANs). By grouping users with similar behavior and constraints, we adapt immutable features and cost weights per cluster, allowing GANs to generate more actionable and user-aligned counterfactuals. Experiments on the German Credit dataset show that our approach achieves a 6× improvement in prediction gain and a 30% reduction in sparsity compared to a baseline CounterGAN, while maintaining plausibility and acceptable latency for online use. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Traffic flow prediction remains a complex task due to the intricate spatial and temporal correlations in real-world traffic data. Although existing graph neural network (GNN) approaches have shown promise in capturing these relationships, their high computational requirements limit their suitability for real-time deployment. To overcome these limitations, we propose spatiotemporal adaptive refinement with knowledge distillation (STARK), a novel and efficient framework that integrates graph fusion with adaptive knowledge distillation (AKD) in a spatiotemporal graph convolutional network (STGCN). Our method leverages graph fusion to capture both localized and global traffic dynamics, enhancing adaptability across diverse traffic conditions. It further employs two dedicated teacher models that independently emphasize spatial and temporal features, guiding a lightweight student model through a distillation process that dynamically adjusts based on prediction uncertainty. This adaptive learning mechanism enables the student model to prioritize and better learn from more difficult prediction instances. Evaluations on four benchmark traffic datasets [PEMS03, PEMS04, PEMSD7(M), and PEMS08] demonstrate that STARK achieves competitive predictive performance, measured by mean absolute error (MAE) and root mean square error (RMSE), while significantly reducing computational overhead. Our approach thus offers an effective and scalable solution for real-time traffic forecasting.

Abstract
Humour poses a unique challenge for artificial intelligence, as it often relies on non-literal language, cultural references, and linguistic creativity. The JOKER Lab, now in its fourth year, aims to advance computational humour research through shared tasks on curated, multilingual datasets, with applications in education, computer-mediated communication and translation, and conversational AI. This paper provides an overview of the JOKER Lab held at CLEF 2025, detailing the setup and results of its three main tasks: (1) humour-aware information retrieval, which involves searching a document collection for humorous texts relevant to user queries in either English or Portuguese; (2) pun translation, focussed on humour-preserving translation of paronomastic jokes from English into French; and (3) onomastic wordplay translation, a task addressing the translation of name-based wordplay from English into French. The 2025 edition builds upon previous iterations by expanding datasets and emphasising nuanced, manual evaluation methods. The Task 1 results show a marked improvement this year, apparently due to participants' judicious combination of retrieval and filtering techniques. Tasks 2 and 3 remain challenging, not only in terms of system performance but also in terms of defining meaningful and reliable evaluation metrics.

Abstract
The growing availability of online data creates new opportunities to improve the timeliness and detail of official statistics, particularly in domains such as price monitoring and inflation measurement. However, leveraging web-scraped data for official use requires alignment with standardized classification frameworks such as the European Classification of Individual Consumption According to Purpose (ECOICOP). We train two natural-language models, a lightweight convolutional neural network (CNN) and a fine-tuned BERTimbau transformer, to classify Portuguese food and beverage items into ECOICOP categories. Using 100,000 product titles scraped from six national supermarket sites and labeled via a human-in-the-loop workflow, the CNN reaches a macro-F1 of 92.19 % with minimal computing cost, while the transformer attains 94.00 %, the first such result for Portuguese. Both models are published on Hugging Face, enabling reproducible inference at scale while the source data remain confidential. The study delivers the first open-source Portuguese ECOICOP classifiers for food and beverage products, a replicable low-resource labeling workflow, and a benchmark of accuracy-speed trade-offs to guide researchers in similar tasks.

Abstract
Abstract Misinformation poses one of the most urgent challenges of our society and raises the question of how to deal with it and manage its rapid spread. To address this problem, a promising approach relies on AI-based misinformation detection. This chapter of the book offers a critical analysis of the ethical implications associated with the design, deployment, and use of misinformation detectors (MDs). Designing and deploying an MD—an AI system that automatically identifies misinformation—is a complex undertaking that requires an interdisciplinary approach, as the challenges faced by MD designers and deployers encompass not only technical aspects, but also linguistic, sociological, political, and especially ethical dimensions. Our analysis is ethics-oriented and follows two main lines of inquiry: (1) Ethics by Design, which focuses on issues related to the design process of an MD, and (2) Ethics of Impact, which addresses the intended and unintended effects of MD deployment and use.

Abstract
Education 5.0 is a new paradigm in education posing many challenges and opportunities. This paper uses qualitative methods to explore students’ and teachers’ experiences with online learning to understand the challenges, benefits, and vision for a successful blended learning model, proposing a dynamic framework for blended learning. Results of in-depth interviews show the three main challenges of blended learning: pedagogical design, technological design, and environment/ setup design. Finally, the study discusses insights into future directions for developing Education 5.0, including the need for ongoing research, collaboration communities, curricula personalization, and innovation in the field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.