ABSTRACT. As digital technologies are increasingly used in creative professions, the evolution of the relationship between the designer and the machine is growing in interest. Such topic is part of a broad debate on how cognitive processes and human intelligence development coevolve in parallel with technology advancements in a process of technogenesis. In a complex socio-economic system, Artificial Intelligence-based technologies are both providing new tools and challenging the idea of creativity itself. We discuss how the creative process in the field of industrial design is commonly intended and we argue that the adoption of AI-based technologies is part of an ongoing process of symbiotic co-evolution between human and machine embedded in the creative process itself and, therefore, designers ought to develop synergic strategies to foster future innovation.

ABSTRACT. We present Erato, a framework designed to facilitate the automated evaluation of poetry, including that generated by poetry generation systems. Our framework employs a diverse set of features, and we offer a brief overview of Erato's capabilities and its potential for expansion. Using Erato, we compare and contrast human-authored poetry with automatically-generated poetry, demonstrating its effectiveness in identifying key differences. Our implementation code and software are freely available under the GNU GPLv3 license.

ABSTRACT. We present a new large-scale emotion-labeled symbolic music dataset consisting of 12k MIDI songs. To create this dataset, we first trained emotion classification models on the GoEmotions dataset, achieving state-of-the-art results with a model half the size of the baseline. We then applied these models to lyrics from two large-scale MIDI datasets. Our dataset covers a wide range of fine-grained emotions, providing a valuable resource to explore the connection between music and emotions and, especially, to develop models that can generate music based on specific emotions. Our code for inference, trained models, and datasets are available online.

ABSTRACT. Recent advances in AI are captivating, and their outputs are creative. However, there is a tradition of defining creativity in terms of, not external products, but internal transformation through immersion in a creative task. Human creativity entails agency not just at the somatic (body) level, but at the level of one's thoughts, beliefs, and ideas. We suggest that selfhood emerges in self-organizing, self-preserving structures that can be modeled using autocatalytic networks. The autocatalytic framework is ideal for modeling systems that exhibit emergent network growth such that the whole can be reconstituted through interactions amongst the parts. The approach readily scales up, and it can analyze and detect phase transitions in vastly complex networks that have proven intractable with other approaches. We explore how selfhood, as well as beneficial transformation as a result of creative tasks, could be achieved in a machine based on the principles of autocatalytic networks.

ABSTRACT. In this paper, I discuss AI-creativity. I argue that AI-produced artworks can display signs of creativity, but that the processes leading to the creative product are not creative. I distinguish between and describe the creative processes of humans and the generation processes of AI. I offer two proper-ties of the former, that enables me to distinguish it from the latter: creative processes are instances of self-expression, and they can be retold in a self-narrative.

ABSTRACT. In this article, we explore the potential of ChatGPT to pass the Brazilian Bar Association exam, which consists of two parts. The first part includes 80 multiple-choice, single-answer, questions, with a maximum score of 80 points. The second part comprises a procedural document, worth 5 points, and 4 open-ended questions, each worth 1.25 points each, and a human expert evaluates ChatGPT’s responses, in different domains of law. All three versions of ChatGPT performed well in the multiple-choice, single-answer, questions. ChatGPT 4 ranks the highest, achieving a score of 70% of correct answers, followed by ChatGPT 3.5 Default with 55%, then ChatGPT 3.5 Legacy with 53%. However, when it comes to the second part the results are not as good. In the criminal exam, GPT 4 performs the worst, while GPT 3.5 Default performs the best, which GPT 3.5 Legacy coming in a close second. Regarding the business exam, GPT 3.5 Legacy had the worst performance, while GPT 4 achieved the highest score: 5.02. Overall, all ChatGPT versions performed well in the multiple-choice questions, but their responses to open-ended questions were underwhelming.

ABSTRACT. A large amount of legal and legislative documents are generated every year with highly specialized content and significant repercussions on society. Besides technical, the produced information is not semantically standardized or format structured. Automating the document analysis, categorization, search, and summarization is essential. The Named Entity Recognition (NER) task is one of the tools that have the potential to extract information from legal documents with efficiency. This paper evaluates the state-of-the-art NER models BiLSTM+CRF and BERT+Fine-Tunning trained on Portuguese corpora through finetuning in the legal and legislative domains. The obtained results (F1-scores of 83.17% and 88.27%) suggest that the BERT model is superior, achieving better average results.

ABSTRACT. Legal Analytics techniques performed on judicial rulings are a useful tool in the process of digitisation of the judicial system. Beyond the advantages, these tech-niques may imply processing of the personal data contained in the rulings, requir-ing an assessment of the impact that such technologies generate on the rights and freedoms of individuals. What happens if personal data contained in judgments are processed, with Legal Analytics techniques and AI systems, for research pur-poses, such as prediction? Should additional technical and organisational measures for the protection of individuals, such as anonymisation or pseudony-misation, be taken in such a case? As regards the EU legal framework, neither the GDPR nor the Directive EU 2016/680 interfere with data processing of courts acting in their judicial capacity, in order to safeguard the independence of the ju-diciary. Therefore, the decision to anonymise judgments is normally taken by the Court’s rules or procedures. The paper provides an overview of the different poli-cy options adopted by the different EU countries, investigating whether such rules should apply to researchers performing Legal Analytics of judicial rulings. The paper also illustrates how such issues have been dealt with in the Legal Ana-lytics for Italian LAw (LAILA) project, funded by the Italian Ministry of Educa-tion and Research’s PRIN programme.

ABSTRACT. For the rule of law to work well, citizens should know their rights and obligations, especially in a day to day context such as when posing as a consumers. Despite being available online, the Portuguese Consumer law was not accessible to the point of being able easy to insert a sentence written in natural language in a search engine and getting a clear response without first having to scroll through multiple little applicable search results. To solve this issue, we introduce Legal Semantic Search Engine (LeSSE), an information retrieval system that uses a hybrid approach of semantic and lexical information retrieval techniques. The new system performed better than the lexical search system in production.

ABSTRACT. Many information retrieval systems use lexical approaches to retrieve information. Such approaches have multiple limitations, and these constraints are exacerbated when tied to specific domains, such as the legal one. Large language models, such as BERT, deeply understand a language and may overcome the limitations of older methodologies, such as BM25.

This work investigated and developed a prototype of a Semantic Search System to assist the Supremo Tribunal de Justiça (Portuguese Supreme Court of Justice) in its decision-making process.

We built a Semantic Search System that uses specially trained BERT models (Legal-BERTimbau variants) and a Hybrid Search System that incorporates both lexical and semantic techniques by combining the capabilities of BM25 and the potential of Legal-BERTimbau. In this context, we obtained a $335\%$ increase on the discovery metric when compared to BM25 for the first query result. This work also provides information on the most relevant techniques for training a Large Language Model adapted to Portuguese jurisprudence and introduces a new technique of Metadata Knowledge Distillation.

ABSTRACT. The General approach of the Draft of AI Act (December 2022) expanded the scope to include General Purpose Artificial Intelligence. The following paper present an overview of the new proposals and analyze its implications. Although the proposed regulation has the merit of regulating an expanding field which, due to its dynamic context can be applied in different domains and on a large scale, it has some flaws. It is fundamental to clarify if we are faced with a general-risk category or a specific category of high-risk. Moreover, we need to clarify the allocation of responsibilities and promote cooperation between differ- ent actors. Furthermore, exemption to regulation should be properly balanced to avoid liability gaps. More than balance innovation and trustworthiness or fear the new developments, what is at stake is the type of AI that we want or, in other words, stop the development of untrusty Artificial Intelligence.

ABSTRACT. The depiction of a city's facade can have various purposes, from purely decorative use to documentation for future restoration. This representation is often a manual and time-consuming process. This paper describes the co-creative system Evolving Urban Landscapes, which uses evolutionary computation to produce images that represent the landscape of an input city. In order to evaluate the creativity of the system, we conducted a study with 23 users. The results show that the system we created can be considered creative and, above all, that it generates diverse results, allowing the users to evolve landscapes according to their tastes.

ABSTRACT. Inspired by cognitive theories of creativity, this paper introduces a computational model (AIGenC) that lays down the necessary components to enable artificial agents to learn, use and generate transferable representations. Unlike machine representations, which rely exclusively on raw sensory data, biological representations incorporate relational and associative information that embed a rich and structured concept space. The AIGenC model poses a hierarchical graph architecture with various levels and types of representations procured by different components. The first component, Concept Processing, extracts objects and affordances from sensory input and encodes them into a concept space. The resulting representations are stored in a dual memory system and enriched with goal-directed and temporal information acquired through reinforcement learning, creating a higher-level of abstraction. Two additional and complementary components work in parallel to detect and recover relevant concepts through a matching process and create new ones, respectively, in a process akin to cognitive Reflective Reasoning and Blending. If Reflective Reasoning fails to offer a suitable solution, a blending operation creates new concepts by combining past information. We discuss the model's capability to yield better out-of-distribution generalisation in artificial agents, thus advancing toward Artificial General Intelligence.

ABSTRACT. Within the medical image analysis, the lack of extensive and well-balanced datasets has posed a significant challenge to traditional machine learning approaches, resulting in poor generalization ability of the models. In light of this, we propose a novel approach to evaluate the efficacy of neural network learning on imbalanced datasets. Our methodology uncovers the relationships between model generalization ability, neural network properties, model complexity, and dataset resizing. Our research highlights several key findings: (1) data augmentation techniques effectively enhance the generalization ability of neural network models; (2) a neural network model with a minimal number of each layer type can achieve superior generalization ability; (3) regularization layers prove to be a crucial factor in achieving higher generalization ability; (4) the number of epochs is not a determining factor in enhancing generalization ability; (5) complexity measures exhibit no significant correlation with generalization ability in the described scenarios. The findings from this study offer a practical roadmap for model selection, architecture search, and evaluation of the methods' effectiveness in medical image analysis.

ABSTRACT. Predicting post-discharge complications in cardiothoracic surgery is of utmost importance to improve clinical outcomes. Machine Learning (ML) techniques have been successfully applied in similar tasks, aiming at short time windows and in specific surgical conditions. However, as the target horizon is extended and the impact of unpredictable external factors rises, the complexity of the task increases, and traditional predictive models struggle to reproduce good performances. This study presents a two-step hybrid learning methodology to address this problem. Building up from identifying unique sub-groups of patients with shared characteristics, we then train individual supervised classification models for each sub-group, aiming at improved prediction accuracy and a more granular understanding of each decision. Our results show that specific sub-groups demonstrate substantially better performance when compared to the baseline model without sub-divisions, while others do not benefit from specialised models. Strategies such as the one presented may catalyse the success of applied ML solutions by contributing to a better understanding of their behaviour in different regions of the data space, leading to an informed decision-making process.

ABSTRACT. Atrial fibrillation (AF) is frequently asymptomatic and at the same time a relevant risk factor for stroke and heart failure. Thus, the identification of patients at high risk of future development of AF from rapid and low-cost exams such as the electrocardiogram (ECG) is of great interest. In this work we trained a deep learning model to predict the risk to develop AF from ECG signals and EHR data, integrating time-to-event in the model and accounting for death as a competing risk. We showed that our model outperforms the CHARGE-AF clinical risk score and we verified that training the model with both ECGs and EHR data led to better performances with respect to training on single modalities. Models were evaluated both in terms of discrimination and calibration.

ABSTRACT. Glioma is a family of brain tumors with three main types exhibiting different progressions. Discovering molecular biomarkers for each glioma type is essential for improving therapeutic approaches. In this work, we propose a pipeline for multi-omics integrated analysis aimed at identifying features that could impact the development of different gliomas. We estimate networks of genes and proteins based on human data, via the graphical lasso, as a network-based step towards variable selection. The glioma networks were compared to disclose molecular relations characteristic of a certain tumor type. Our outcomes were validated both mathematically and through principal component analysis to determine if the selected subset of variables carries enough biological information to distinguish the three glioma types in a reduced dimensional subspace. The results highlight an overall agreement in variable selection across the two omics. Features exclusively selected by each glioma type appear as more representative of the pathological condition, making them suitable as potential diagnostic biomarkers. The comparison between glioma-type networks and with known protein-protein interactions reveals the presence of molecular relations that could be associated to a pathological condition, which would deserve further biological investigation.