PUBLICACIONES

Green AI aims to develop accurate AI models that are also sustainable without compromising the environment, especially in terms of carbon emissions. There are few studies on this topic in recommender systems, so we analyzed the trade-offs between recommendation performance and carbon footprint in session-based recommender systems. We use five public e-commerce datasets to predict the next item a user will interact with based solely on their past click events. The GRU4Rec algorithm and five unofficial reimplementations in different deep learning frameworks (Theano, PyTorch, TensorFlow, Keras, and Reckpack) are evaluated. The results indicate a strong effect of the loss function and dataset size on the carbon footprint without significantly affecting the accuracy metrics. We show evidence that the implementation choice for the same algorithm strongly affects the CO emitted, and optimized implementations do not sacrifice recommendation efficiency, which should be considered when choosing a framework or implementation for an algorithm.

Recent advances in deep learning have significantly transformed the field of 3D shape generation, enabling the synthesis of complex, diverse, and semantically meaningful 3D objects. This survey provides a comprehensive overview of the current state-of-the-art in 3D shape generation, organizing the discussion around three core components: shape representations, generative modeling approaches, and evaluation protocols. We begin by categorizing 3D representations into explicit, implicit, and hybrid setups, highlighting their structural properties, advantages, and limitations. Next, we review a wide range of generation methods, focusing on feedforward architectures. We further summarize commonly used datasets and evaluation metrics that assess fidelity, diversity, and realism of generated shapes. Finally, we identify open challenges and outline future research directions that could drive progress in controllable, efficient, and high-quality 3D shape generation. This survey aims to serve as a valuable reference for researchers and practitioners seeking a structured and in-depth understanding of this rapidly evolving field.

We introduce the Bias Network Approach (BNA) as a sociotechnical method for AI developers to identify, map, and relate biases across the AI development process. This approach addresses the limitations of what we call the "isolationist approach to AI bias," a trend in AI literature where biases are seen as separate occurrences linked to specific stages in an AI pipeline. Dealing with these multiple biases can trigger a sense of excessive overload in managing each potential bias individually or promote the adoption of an uncritical approach to understanding the influence of biases in developers’ decision-making. The BNA fosters dialogue and a critical stance among developers, guided by external experts, using graphical representations to depict biased connections. To test the BNA, we conducted a pilot case study on the "waiting list” project, involving a small AI developer team creating a healthcare waiting list NPL model in Chile. The analysis showed promising findings: (i) the BNA aids in visualizing interconnected biases and their impacts, facilitating ethical reflection in a more accessible way; (ii) it promotes transparency in decision-making throughout AI development; and (iii) more focus is necessary on professional biases and material limitations as sources of bias in AI development.

A current problem in the philosophy of neuroscience consists in determining how to individuate cognitive capacities using neurobiological evidence. One recent proposal grounded on fundamental insights from mechanistic philosophy is an iterative strategy that cycles between neural mechanisms and cognitive capacities, using the former to individuate the latter and vice versa (Francken et al. Synthese, 200(5):378, 2022). However, this view cannot be applied to a fundamental aspect of research on cognitive capacities. Understanding a capacity requires delineating its behavioral profile by identifying the different effects or phenomena associated with it in different task settings. If mechanisms are necessary for integrating these phenomena into a single capacity in a bottom-up way, the iterative cyclic strategy requires a criterion for assessing the across-context identity of the mechanism, which is missing from this view. However, we argue that introducing this criterion turns the strategy into something else. It requires substituting its bottom-up phase with a bi-dimensional stage in which the capacity and its mechanism are individuated simultaneously through the identification of the generalization that connects them and the assessment of how the generalization behaves across contexts.

Participatory society has often been regarded positively, frequently associated with the ideals of a more democratic and equitable civilization. Nevertheless, the idea of participation may act as a two-sided phenomenon in terms of empowerment, especially in the realm of social media platforms. This dichotomy is evident as increased participation often leads to a rise in offensive and divisive language, reflecting the challenging balance between open dialogue and the maintenance of respectful discourse on these platforms. In this work, we comprehensively examine the use of offensive language during a highly polarizing event on two online platforms, Twitter and Whatsapp. In our study, we focus in the 2021 Chilean Presidential Elections, a political event where candidates from two opposing parties faced each other. Using a state-of-the-art model and all available labeled data in literature, we determine the level of offensive language across platforms and parties. Our results show that Twitter messages contain, on average, up to 15% more of offensive language than Whatsapp.

Numerous studies have shown that mindfulness is positively associated with relationship and sexual satisfaction. However, most have examined the benefits of intrapersonal or trait mindfulness, rather than directly investigating interpersonal mindfulness or considering polyvagal theory. Our main objective was to determine the variable importance of interpersonal mindfulness and psychological safety for relationship and sexual satisfaction using random forests and regression trees and to explore the importance of demographics, social and couple‐related factors, and emotional wellbeing in this analysis. 356 adults in committed romantic relationships were recruited for a self‐report survey. Results suggested that mindfulness in couple relationships, psychological safety, conflict strategies, and depression symptoms were of top importance for relationship and sexual satisfaction. Limitations and future directions involving dyadic data and physiological measures were discussed. The findings will inform the development of interpersonal mindfulness‐ and polyvagal‐based interventions aimed at promoting safety and stability in relationships while enhancing personal wellbeing.

Understanding the behavior of microbial consortia is crucial for predicting metabolite production by microorganisms. Genome-scale network reconstructions enable the computation of metabolic interactions and specific associations within microbial consortia underpinning the production of different metabolites. In the context of the human gut, butyrate is a central metabolite produced by bacteria that plays a key role within the gut microbiome impacting human health. Despite its importance, there is a lack of computational methods capable of predicting its production as a function of the consortium composition. Here, we present a novel machine-learning approach leveraging automatically generated genome-scale metabolic models to tackle this limitation. Briefly, all consortia made of two up to 13 members from a pool of 19 bacteria with known genomes, including at least one butyrate producer from a pool of three known producer species, were built and their (maximum) in silico butyrate production simulated. Using network-derived descriptors from each bacteria, butyrate production by the above consortia was used as training data for various machine learning models. The performance of the algorithms was evaluated using k-fold cross-validation and new experimental data, displaying a Pearson correlation coefficient exceeding 0.75 for the predicted and observed butyrate production in two bacteria consortia. While consortia with more than two bacteria showed generally worse predictions, the best machine-learning models still outperformed predictions from genome-scale metabolic models alone. Overall, this approach provides a valuable tool and framework for probing promising butyrate-producing consortia on a large scale, guiding experimentation, and more importantly, predicting metabolic production by consortia.

The integration of artificial intelligence into dermatological research has underscored the need for robust and well-structured dermatological datasets. However, these datasets vary widely in their development processes, and there is currently no standard methodology to create such datasets. This work identifies three pressing needs for the building of dermatological datasets focus on skin tumor classification: the need for multimodal datasets, the definition of minimum metadata requirements, and the inclusion of underrepresented populations to address the scarcity of health data. We propose a practical methodology to create dermatological datasets from clinical records, incorporating both images and patient metadata. The process consists of four key stages: getting the institutional review board approval and analysis of clinical information sources, data recording and structuring, processing of clinical data and images, and quality assessment. This methodology was derived from hands-on experience in building two datasets from Chilean and Mexican populations, respectively. The methodology allows the creation of well-structured datasets by simplifying data organization and enabling replication. Each step includes practical guidance for dealing with typical challenges, such as image metadata categorization and technical validation by dermatologists and computer scientists. Our contribution offers a reproducible, scalable, and interdisciplinary framework for creating dermatological datasets, especially useful for countries initiating dataset creation. In addition to the methodological proposal, we highlight common pitfalls and offer recommendations to mitigate them.

This article presents a numerical scheme for the variational model formulated by Calderer et al. [J. Elast., 141 (2020), pp. 51–73] for the debonding of a hydrogel film from a rigid substrate upon exposure to solvent, in the two-dimensional case of a film placed between two parallel walls. It builds upon the scheme introduced by Song et al. [J. Elast., 153 (2023), pp. 651–679] for completely bonded gels, which fails to be robust in the case of gels that are already debonded. The new scheme is used to compute the energy release rate function, based on which predictions are offered for the threshold thickness below which the gel/substrate system is stable against debonding. This study, in turn, makes it possible to validate a theoretical estimate for the energy release rate obtained in the cited works, which is based on a thin-film asymptotic analysis and which, due to its explicit nature, is potentially valuable in medical device development. An existence theorem and rigorous justifications of some approximations made in our numerical scheme are also provided.

The affective scaffolding framework underlies differing perspectives on how griefbots affect the grieving process. While some researchers are optimistic, others draw more cautious conclusions. We endorse the view that griefbots are affective scaffolds. However, we draw a pessimistic conclusion about human-griefbot interaction. There are two main views on successful grief: the “Freudian view” and the continuing bonds view. The “Freudian view” paves the way to the pessimistic conclusion. In this paper, we propose a free-energy approach of the “Freudian view”. Predictive processing is often regarded as providing a process theory for the free-energy principle. In this framework, model evidence must be maximised by updating and optimising models. Griefbots are not recommendable since they are scaffolds that obstruct and lengthen the maximisation of model evidence, making models more rigid and poorly adaptable to changing dynamics. Building on this approach, we examine the ethical dimensions of griefbot’s use and design. We argue that there is something inherently morally wrong in the very conception of griefbots. Their functionality predisposes them to cause harm by disrupting the grief process.