Abstract
The growing deployment of artificial intelligence in critical domains exposes a pressing challenge: how reliably models make predictions for ambiguous data without exhibiting overconfidence. We introduce hubris benchmarking, a methodology to evaluate overconfidence in machine learning models. The benchmark is based on a novel architecture, ambiguous generative adversarial networks (AmbiGANs), which are trained to synthesize realistic yet ambiguous datasets. We also propose the hubris metric to quantitatively measure the extent of model overconfidence when faced with these ambiguous images. We illustrate the usage of the methodology by estimating the hubris of state-of-the-art pre-trained models (ConvNext and ViT) on binarized versions of public datasets, including MNIST, Fashion-MNIST, and Pneumonia Chest X-ray. We found that, while ConvNext is on average 3% more accurate than ViT, it often makes excessively confident predictions, on average by 10% points higher than ViT. These results illustrate the usefulness of hubris benchmarking in high-stakes decision processes. © 2025 Elsevier B.V., All rights reserved.

Abstract
Rebeca is 20+ years old. Introduced by Marjan Sirjani and colleagues for modelling and analysing actor-based systems, it comes with a variety of tool support, including dedicated model checkers, simulators, and code generators. When encountering Rebeca for the first time, either as a student, as a researcher, or as a practitioner from industry, one needs to grasp the subtleties of Rebeca ’s semantics, which includes variants with probabilities and time. This paper presents a user-friendly web-based front-end, based on the Caos library for Scala, to animate different operational semantics of (timed) Rebeca. This can facilitate the dissemination and awareness of Rebeca, provide insights into the differences among existing semantics, and support quick experimentation of new variants (e.g., when the order of received messages is preserved). The tool is illustrated by means of a ticket service use case from the literature. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
Local flexibility markets are a promising solution to aid system operators in managing the network as it faces the growth of distributed resources and the resulting impacts on voltage control, among other factors. This paper presents and simulates a proposal for an intra-day local flexibility market based on grid segmentation. The design provides a market-based solution for distribution system operators (DSOs) to address near-real-time grid issues. The grid segmentation computes the virtual buses that represent each zone and the sensitivity indices that approximate the impact of activating active power flexibility in the buses within the zone. This approach allows DSOs to manage and publish their flexibility needs per zone and enables aggregators to offer flexibility by optimizing their resource portfolios per zone. The simulation outcomes allow for the assessment of market performance according to the number of zones computed and show that addressing overloading and voltage control through zonal approaches can be cost-effective and counterbalance minor errors compared to node-based approaches.

Abstract

Abstract
A subgroup discovery-based method has recently been proposed to understand the behavior of models in the (original) feature space. The subgroups identified represent areas of feature space where the model obtains better or worse predictive performance when compared to the average test performance. For instance, in the marketing domain, the approach extracts subgroups such as: in groups of customers with higher income and who are younger, the random forest achieves higher accuracy than on average. Here, we propose a complementary method, Meta Subspace Analysis (MSA), MSA uses metalearning to analyze these subgroups in the metafeature space. We use association rules to relate metafeatures of the feature space represented by the subgroups to the improvement or degradation of the performance of models. For instance, in the same domain, the approach extracts rules such as: when the class entropy decreases and the mutual information increases in the subgroup data, the random forest achieves lower accuracy. While the subgroups in the original feature space are useful for the end user and the data scientist developing the corresponding model, the meta-level rules provide a domain-independent perspective on the behavior of the model that is suitable for the same data scientist but also for ML researchers, to understand the behavior of algorithms. We illustrate the approach with the results of two well-known algorithms, naive Bayes and random forest, on the Adult dataset. The results confirm some expected behavior of algorithms. However, and most interestingly, some unexpected behaviors are also obtained, requiring additional investigation. In general, the empirical study demonstrates the usefulness of the approach to obtain additional knowledge about the behavior of models. © 2025 Elsevier B.V., All rights reserved.

Abstract