Abstract
In healthcare, diagnoses usually rely on physician expertise. However, complex cases may benefit from consulting similar past clinical reports cases. In this paper, we present MedLink (http://medlink.inesctec.pt), a tool that given a free-text medical report, retrieves and ranks relevant clinical case reports published in health conferences and journals, aiming to support clinical decision-making, particularly in challenging or complex diagnoses. To this regard, we trained two BERT models on the sentence similarity task: a bi-encoder for retrieval and a cross-encoder for reranking. To evaluate our approach, we used 10 medical reports and asked a physician to rank the top 10 most relevant published case reports for each one. Our results show that MedLink’s ranking model achieved NDCG@10 of 0.747. Our demo also includes the visualization of clinical entities (using a NER model) and the production of a textual explanation (using a LLM) to ease comparison and contrasting between reports. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
In the spring of 2023, a team of European Project Semester (EPS) students enrolled at the Instituto Superior de Engenharia do Porto (ISEP) chose to foster socialisation in urban spaces. Public spaces are ideal sites to promote social interaction and community involvement. The aim of this project is then to use such places to divert attention from smartphones by promoting physical social interaction. In recent years, the combination of interactive games and technology has emerged as a potential strategy to increase the use and allure of public areas. The proposed solution, named Shift it, is a puzzle game that combines technology with old school gaming, providing a fun and unique socialising experience. The game, to be installed in public areas, has as key features inclusiveness (invites all people to play), fun (creates a healthy competitive setup) and empathy (creates puzzles by taking and scrambling user pictures). This paper presents the proposed design, which was based on state-of-the-art, ethics, market and sustainability analyses, followed by the development and testing of a proof-of-concept prototype. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Abstract
Social media platforms, increasingly used as news sources for varied data analytics, have transformed how information is generated and disseminated. However, the unverified nature of this content raises concerns about trustworthiness and accuracy, potentially negatively impacting readers' critical judgment due to disinformation. This work aims to contribute to the automatic data quality validation field, addressing the rapid growth of online content on wiki pages. Our scalable solution includes stream-based data processing with feature engineering, feature analysis and selection, stream-based classification, and real-time explanation of prediction outcomes. The explainability dashboard is designed for the general public, who may need more specialized knowledge to interpret the model's prediction. Experimental results on two datasets attain approximately 90% values across all evaluation metrics, demonstrating robust and competitive performance compared to works in the literature. In summary, the system assists editors by reducing their effort and time in detecting disinformation.

Abstract
Motivation The validity of epidemiologic findings can be increased using triangulation, i.e. comparison of findings across contexts, and by having sufficiently large amounts of relevant data to analyse. However, access to data is often constrained by practical considerations and by ethico-legal and data governance restrictions. Gaining access to such data can be time-consuming due to the governance requirements associated with data access requests to institutions in different jurisdictions.Results DataSHIELD is a software solution that enables remote analysis without the need for data transfer (federated analysis). DataSHIELD is a scientifically mature, open-source data access and analysis platform aligned with the 'Five Safes' framework, the international framework governing safe research access to data. It allows real-time analysis while mitigating disclosure risk through an active multi-layer system of disclosure-preventing mechanisms. This combination of real-time remote statistical analysis, disclosure prevention mechanisms, and federation capabilities makes DataSHIELD a solution for addressing many of the technical and regulatory challenges in performing the large-scale statistical analysis of health and biomedical data. This paper describes the key components that comprise the disclosure protection system of DataSHIELD. These broadly fall into three classes: (i) system protection elements, (ii) analysis protection elements, and (iii) governance protection elements.Availability and implementation Information about the DataSHIELD software is available in https://datashield.org/ and https://github.com/datashield.

Abstract
This work introduces Gen-JEMA, a generative approach based on joint embedding with multimodal alignment (JEMA), to enhance feature extraction in the embedding space and improve the explainability of its predictions. Gen-JEMA addresses these challenges by leveraging multimodal data, including multi-view images and metadata such as process parameters, to learn transferable semantic representations. Gen-JEMA enables more explainable and enriched predictions by learning a decoder from the embedding. This novel co-learning framework, tailored for directed energy deposition (DED), integrates multiple data sources to learn a unified data representation and predict melt pool images from the primary sensor. The proposed approach enables real-time process monitoring using only the primary modality, simplifying hardware requirements and reducing computational overhead. The effectiveness of Gen-JEMA for DED process monitoring was evaluated, focusing on its generalization to downstream tasks such as melt pool geometry prediction and the generation of external melt pool representations using off-axis sensor data. To generate these external representations, autoencoder (AE) and variational autoencoder (VAE) architectures were optimized using Bayesian optimization. The AE outperformed other approaches achieving a 38% improvement in melt pool geometry prediction compared to the baseline and 88% in data generation compared with the VAE. The proposed framework establishes the foundation for integrating multisensor data with metadata through a generative approach, enabling various downstream tasks within the DED domain and achieving a small embedding, allowing efficient process control based on model predictions and embeddings. © The Author(s) 2025.

Abstract
Text simplification converts complex text into simpler language, improving readability and comprehension. This study evaluates the effectiveness of open-source large language models for text simplification across various categories. We created a dataset of 66, 620 lead section pairs from English and Simple English Wikipedia, spanning nine categories, and tested Llama 3 for text simplification. We assessed its output for readability, simplicity, and meaning preservation. Results show improved readability, with simplification varying by category. Texts on Time were the most shortened, while Leisure-related texts had the greatest reduction of words/characters and syllables per sentence. Meaning preservation was most effective for the Objects and Education categories. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.