Abstract
This paper presents a novel approach to the computational representation of cellular lines using transformer-based embeddings. By leveraging state-of-the-art natural language processing techniques, we generate context-aware embeddings from biomedical literature from the PubMed database, offering a more nuanced and biologically relevant representation of cellular lines compared to traditional methods like TF-IDF and SVDD. We applied these embeddings to cluster cellular lines, using the elbow method to identify a set of distinct clusters that reflect biologically meaningful relationships. To evaluate the quality of these clusters, we employed the Topic Coherence metric, achieving a coherence score of 0.395, indicative of moderate consistency across clusters. The results demonstrate the potential of transformer-based models to improve drug discovery by identifying shared characteristics between cellular lines, enabling more accurate drug response predictions and advancing personalized medicine. This method offers an interesting improvement in the precision of cellular line modeling, paving the way for more efficient drug repositioning and targeted therapies in cancer research.

Abstract
The present work proposes a two-stage optimization approach for flexibility services provided by battery energy storage systems (BESS) in distribution networks with photovoltaic (PV) generation and electric vehicles (EV). The considered flexibility services include reserve allocation and voltage regulation to support network operation. The first stage optimizes the day-ahead (DA) scheduling of distributed BESS to minimize overall costs, including energy, BESS usage, and reserve, while accounting for stochastic variations in load, PV generation, and EV penetration. The second stage simulates the real-time (RT) operation of the electrical distribution network, evaluating system behavior under different scenarios based on DA decisions. A coordinated control strategy is applied, integrating DA scheduling with network voltage levels. Deviations between BESS outputs in DA and RT stages are fed back into a new DA run to adjust outputs and reduce costs. Results on a medium-voltage distribution system with 157 nodes (based on a reduced version of the EPRI CKT5 feeder) demonstrate that the proposed scenario-based model provides feasible solutions under uncertainty, with BESS playing a key role while strictly adhering to planned operational modes from DA to RT, as typically enforced in energy market participation.

Abstract
With the advent of Information and Communication Technologies in recent decades, organizations face several challenges today. Adopting Digital Transformation (DT) offers numerous opportunities for Small and Medium Enterprises (SMEs) to improve their efficiency and operations, reaching new markets, shareholders, and customers. However, there are potential risks associated with this process. With Digital Transformation (DT), the radius of connectivity and interconnection between devices and systems increases in Mozambique and worldwide, creating more significant space cyberattacks. As Small and Medium-sized Enterprises (SMEs) connect to the digital world and move forward with adopting innovative digital technologies, they become more vulnerable to digital security risks. Hence, managing digital security risks effectively is crucial to realizing the benefits of Digital Transformation (DT). This position paper proposes to present the research work that will culminate in the proposal to develop a framework that fits Mozambican Small and Medium Enterprises (SMEs) through a Design Science Research (DSR) methodology, which can help to assist Mozambican Small and Medium Enterprises (SMEs) in the Digital Transformation (DT) process.

Abstract
Forecasting the covariance matrix of asset returns is central to portfolio construction, risk management, and asset pricing. However, most existing models struggle at medium-term horizons, several weeks to months, where shifting market regimes and slower dynamics prevail. We propose a novel deep learning framework that integrates three-dimensional convolutional neural networks, bidirectional long short-term memory, and multihead attention to capture complex spatiotemporal patterns in asset return dynamics. Using daily data on 14 exchange-traded funds from 2017 to 2023, we demonstrate that our model improves out-of-sample covariance forecasts by reducing Euclidean and Frobenius distance metrics by up to 20% compared with classical benchmarks such as shrinkage estimators and GARCH-type models. These gains persist across distinct market regimes, including bull and bear periods, and remain robust across various forecast horizons and under both raw and excess return specifications. Portfolio simulations based on global minimum variance strategies reveal that the proposed model consistently delivers lower volatility and moderate turnover, even under no-short-selling constraints. This balance between risk reduction and trading efficiency underscores the economic relevance of the forecasts, particularly for institutional investors managing portfolios at medium-term horizons.

Abstract
Debugging and repairing faults when programs fail to formally verify can be complex and time-consuming. Automated Program Repair (APR) can ease this burden by automatically identifying and fixing faults. However, traditional APR techniques often rely on test suites for validation, but these may not capture all possible scenarios. In contrast, formal specifications provide strong correctness criteria, enabling more effective automated repair. In this paper, we present an APR tool for Dafny, a verification-aware programming language that uses formal specifications - including preconditions, post-conditions, and invariants - as oracles for fault localization and repair. Assuming the correctness of the specifications and focusing on arithmetic bugs, we localize faults through a series of steps, which include using Hoare logic to determine the state of each statement within the program, and applying Large Language Models (LLMs) to synthesize candidate fixes. The models considered are GPT-4o mini, Llama 3, Mistral 7B, and Llemma 7B. We evaluate our approach using DafnyBench, a benchmark of realworld Dafny programs. Our tool achieves 89.7% fault localization success rate and GPT-4o mini yields the highest repair success rate of 74.18%. These results highlight the potential of combining formal reasoning with LLM-based program synthesis for automated program repair.

Abstract
Seaport cranes operate continuously and consume large amounts of energy while aiming to minimise containerships' berthing time. Although previous studies have contributed to addressing the crane scheduling problem, most have focused exclusively on loading time, often overlooking the aspect of energy consumption. Furthermore, crane activity is typically modelled in a simplified manner-commonly assuming a fixed cycle duration or constant energy usage when handling a container-without accounting for the impact of variable container masses. In this study, an energy-aware quay crane scheduling formulation for container terminals is proposed, highlighting the importance of integrating an energy model into the scheduling problem. The optimisation problem is formulated as a Mixed Integer Linear Programming (MILP) model. The objective is to minimise total energy costs by reordering the sequence in which containers are handled, while respecting precedence constraints defined by the ship's stowage plan. Two solution methods-a MILP approach solved using CPLEX and a genetic algorithm (GA)-are compared. The results indicate that, for larger containerships, the genetic algorithm provides a more efficient solution method. Moreover, incorporating detailed energy consumption models for electric cranes may significantly reduce energy costs during containership handling operations.