Abstract
Yield forecasting is of immeasurable value in modern viticulture to optimize harvest scheduling and quality management. The number of inflorescences and flowers per vine is one of the main components and their assessment serves as an early predictor, which can explain up to 85-90% of yield variability. This study introduces a sophisticated framework that integrates the benchmark of different advanced deep learning and classic image processing to automate the segmentation of grapevine inflorescences and the detection of single flowers, to achieve precise, early, and non-invasive yield predictions in viticulture. The YOLOv8n model achieved superior performance in localizing inflorescences ( F1-Score (Box) = 95.9%) and detecting individual flowers (F1-Score = 91.4%), while the YOLOv5n model excelled in the segmentation task ( F1-Score (Mask) = 98.6%). The models demonstrated a strong correlation (R-2 > 90.0%) between detected and visible flowers in inflorescences. A statistical analysis confirmed the robustness of the framework, with the YOLOv8 model once again standing out, showing no significant differences in error rates across diverse grapevine morphologies and varieties, ensuring wide applicability. The results demonstrate that these models can significantly improve the accuracy of early yield predictions, offering a noninvasive, scalable solution for Precision Viticulture. The findings underscore the potential for Computer Vision technology to enhance vineyard management practices, leading to better resource allocation and improved crop quality.

Abstract
The purpose of this study is to ascertain the hierarchical importance of a patent's characteristics to licensing. This research has a causal-exploratory purpose, in that it sought to establish relationships between variables. This research aims to identify which characteristics are influential in the licensing of Brazilian academic patents in the biotechnology and pharmaceutical technology fields, based on the mining of data contained in licensed and unlicensed patent documents. Which characteristics of Brazilian academic patents are most influential in their licensing potential? An analysis through Random Forest was performed. To the best of our knowledge, there are no studies in Brazil using machine learning to identify which characteristics are influential in licensing a particular academic patent, especially given the difficulty of gathering this information. We found that regardless of the measure used, the three most critical licensing characteristics for the Biotechnology and Pharmaceutical patents analysed are Patent Scope, Life Cycle, and Claims. At the same time, the least important is the Patent Cooperation Treaty. The relevance of this research is based on the fact that after identifying which intrinsic characteristics influence the final value and licensing probabilities of a given patent, it will be possible to develop mathematical models that provide accurate information for establishing technology transfer agreements. In practical terms, the results suggest that greater patent versatility, combined with lifecycle management and a technical effort to build strong claims, increases the licensing potential of academic biopharmaceutical patents.

Abstract
The European Health Data Space (EHDS) sets out regulations for the management of electronic health data, distinguishing between its primary use in direct healthcare and patient data portability, and its secondary use for research, innovation, and policy-making. We aim to empower individuals to take control of their health by enhancing personal health data management. In this work, we discuss the challenges in electronic personal health data access and propose developing a system that leverages personal health knowledge graphs and retrieval-augmented generation to ensure FAIR personal electronic health data representation and personalized health information delivery.

Abstract
This study investigates the characteristics of variable and invariable tag questions in monologues, comparing their usage in British English and European Portuguese. Through a corpus-based analysis, this paper provides valuable insights into the grammatical and functional properties of these linguistic constructions in spoken monologues in both languages. The findings reveal that tag questions are less frequently used in monologues than in dialogues, reflecting their interactional nature. However, their occurrence is notably higher in European Portuguese than in British English across both monologic and dialogic speech. Furthermore, tag questions in European Portuguese exhibit greater frequency and diversity in monologues, whereas in British English, they are less common and exclusively consist of variable tag questions. While some differences in the functional and grammatical features of variable and invariable tag questions were identified, these variations were not particularly pronounced. The analysis also highlights the limited availability of tag questions in the monologues dataset in English, underlining the need for further research to comprehensively explore these constructions across languages.

Abstract
In the coming years, a wide range of underwater applications, including resource mining, marine research, and military operations will play an increasingly important role. The Internet of Underwater Things (IoUT) extends IoT principles to underwater environments, enabling connectivity between underwater devices and the Internet. However, high latency, intermittent connectivity, and security risks, such as privacy breaches, data tampering, and unauthorized access, pose major challenges to IoUT adoption. Existing security mechanisms fail in Delay-Tolerant Networks (DTNs) due to their reliance on centralized trust models. Blockchain provides a decentralized, immutable, and transparent solution for securing underwater communications. This paper introduces the Blockchain-Based Underwater Messaging System (BUMS), an innovative solution that ensures message integrity, confidentiality, and resilience in DTNs. Messages are immutably stored in blockchain blocks, while malicious nodes are autonomously detected and excluded without the need for a central authority. To evaluate its feasibility, we developed the Underwater Blockchain Simulator (UBS), a custom-tailored open-source simulator designed to test blockchain algorithms in underwater networks. Simulation results demonstrate that BUMS enhances security and network reliability while maintaining efficiency in high-latency underwater environments, making it a viable solution for secure IoUT-based communications.

Abstract
Over the last three years, the JOKER Lab series at CLEF has gathered an active community of researchers in natural language processing and information retrieval to collaborate on non-literal use of language in text. Such language can be a challenge for AI systems, but also sometimes for humans, as it requires understanding implicit cultural references and unorthodox interactions between form and meaning. In this paper, we discuss the lessons learned from the previous iterations of the Lab and describe how its upcoming edition will build upon those to address new challenges. In 2025, JOKER will provide novel tasks and update some previous ones with new data and new languages. This year we provide sandbox environments for experimenting with humour-aware information retrieval (Task 1), a previously featured task now enhanced with an all-new Portuguese corpus; wordplay translation in text (Task 2), another historical task for which we provide new corpora; onomastic wordplay (Task 3), a new task focussed on humorous proper names in fiction; and controlled creativity (Task 4), another novel task that aims at identifying and avoiding hallucinations.