Abstract
BackgroundBreast cancer therapy improved significantly, allowing for different surgical approaches for the same disease stage, therefore offering patients different aesthetic outcomes with similar locoregional control. The purpose of the CINDERELLA trial is to evaluate an artificial-intelligence (AI) cloud-based platform (CINDERELLA platform) vs the standard approach for patient education prior to therapy. MethodsA prospective randomized international multicentre trial comparing two methods for patient education prior to therapy. After institutional ethics approval and a written informed consent, patients planned for locoregional treatment will be randomized to the intervention (CINDERELLA platform) or controls. The patients in the intervention arm will use the newly designed web-application (CINDERELLA platform, CINDERELLA APProach) to access the information related to surgery and/or radiotherapy. Using an AI system, the platform will provide the patient with a picture of her own aesthetic outcome resulting from the surgical procedure she chooses, and an objective evaluation of this aesthetic outcome (e.g., good/fair). The control group will have access to the standard approach. The primary objectives of the trial will be i) to examine the differences between the treatment arms with regards to patients' pre-treatment expectations and the final aesthetic outcomes and ii) in the experimental arm only, the agreement of the pre-treatment AI-evaluation (output) and patient's post-therapy self-evaluation. DiscussionThe project aims to develop an easy-to-use cost-effective AI-powered tool that improves shared decision-making processes. We assume that the CINDERELLA APProach will lead to higher satisfaction, better psychosocial status, and wellbeing of breast cancer patients, and reduce the need for additional surgeries to improve aesthetic outcome.

Abstract
Type systems and type inference systems can be used to help text and code generation models like GPT-3 produce more accurate and appropriate results. These systems provide information about the types of variables, functions, and other elements in a program or codebase, which can be used to guide the generation of new code or text. For example, a code generation model that is aware of the types of variables and functions being used in a program can generate code that is more likely to be syntactically correct and semantically meaningful. We argue for the specialization of language models such as GPT-3 for automatic program repair tasks, incorporating type information in the model's learning process. A trained language model is expected to perform better by understanding the nuances of type systems and using them for program repair, instead of just relying on the general structure of programs.

Abstract
The European Union (EU) established through the Common Agricultural Policy (CAP) an aid system and subsidies for farmers that cultivate vineyards. Eligible areas should be controlled and registered in Geographic Information Systems. The agencies paying this support must check that the parcels have an agricultural activity through an on-the-spot check or the analysis of aerial or satellite images. Abandonment situations lead to the cancellation of aid payments. In the Douro Demarcated Region of Portugal, inspections are conducted according to EU-defined methods. However, due to the vast size of the region, which spans approximately 250,000 hectares with vineyard cultures occupying 43,843 hectares, the analysis time and specialized human resources required for these inspections are significant. In this study, we curated a new dataset for training convolutional neural networks (CNNs) and fine-tuned pre-trained VGG models to classify vineyards as abandoned or non-abandoned. The baseline model achieved an accuracy of 95.1% on the test dataset, while the top-performing model achieved an impressive overall accuracy and F1-score of 99% for both classes.

Abstract
Although electric vehicle (EV) sales have been increasing over the years, worldwide EV adoption is still low. In Brazil, the key factors influencing this are the EV high acquisition cost and the reduced charging infrastructure. Therefore, traditional business models may not be adequate for Brazil and stagnate EV diffusion. Thus, designing innovative business models can be crucial to accelerate the transition to electric mobility in the region. In this way, this article aims to critically review business models for EV adoption and charging stations worldwide and discuss its application in Brazil. Then, the challenges and opportunities for some business model options are highlighted through the SWOT matrix. One can conclude that EV sharing is a promising business model for Brazil, given the series of advantages such as access to cutting-edge technology at an affordable price, reduction of vehicles on the streets, and given convenience for users (no concern with charging, EV degradation, and parking). However, public policies, subsidies, and coordination between different agents are crucial for the proliferation of this model. On the other hand, for the proposed CS models, the more traditional option is the less risky for investors in Brazil until the number of EVs increase.

Abstract
Many service jobs are carried out in modern offices, with individual offices being increasingly replaced by open-plan settings. The high number of adult people working in office buildings, in most situations sharing the work-place with many others during a considerable part of their daily time, highlights the importance of providing adequate guidance to ensure the quality of office environments. This paper aims to summarize existing data on modern offices' indoor environmental quality (IEQ) conditions in terms of air pollution (volatile organic compounds (VOC), particulate matter and inorganic pollutants), thermal comfort, lighting and acoustics and the respective associations with health and productivity-related outcomes in workers. Evidence shows that al-though many offices present acceptable IEQ, some office settings can have levels of air pollutants, hygrothermal conditions/thermal comfort and illuminance that do not comply with the existing international standards and recommendations. In addition, findings suggest the existence of significant associations between the assessed IEQ indicators and the risk of detrimental effects on health and productivity of office workers. In particular, airborne particles, CO2, O 3 and thermal comfort were linked with the prevalence of sick building syndrome symptoms. Poor lighting and acoustical quality have also been associated with malaise and physiological stress among office workers. Similarly, better productivity levels have been registered for good indoor air quality conditions, in terms of VOC, airborne particles and CO2. Overall, the evidence revised in this work suggests that for promoting health and productivity recommendations for office building managers include actions to ensure that: i) all relevant IEQ indicators are periodically controlled to ensure that levels comply with recommended limit values; ii) declared in-door pollution sources are avoided; iii) adequate ventilation and acclimatization strategies are implemented; and iv) there is the possibility of conduct personalized adjustments to environmental conditions (following workers' preferences).

Abstract
Data crowdsourcing is a data acquisition process where groups of voluntary contributors feed platforms with highly relevant data ranging from news, comments, and media to knowledge and classifications. It typically processes user-generated data streams to provide and refine popular services such as wikis, collaborative maps, e-commerce sites, and social networks. Nevertheless, this modus operandi raises severe concerns regarding ill-intentioned data manipulation in adver-sarial environments. This paper presents a simulation, modelling, and classification approach to automatically identify human and non-human (bots) as well as benign and malign contributors by using data fabrication to balance classes within experimental data sets, data stream modelling to build and update contributor profiles and, finally, autonomic data stream classification. By employing WikiVoyage - a free worldwide wiki travel guide open to contribution from the general public - as a testbed, our approach proves to significantly boost the confidence and quality of the classifier by using a class-balanced data stream, comprising both real and synthetic data. Our empirical results show that the proposed method distinguishes between benign and malign bots as well as human contributors with a classification accuracy of up to 92%.