Abstract
In recent years, the task of person re-identification (Re-ID) has improved considerably with the advances in deep learning methodologies. However, occluded person Re-ID remains a challenging task, as parts of the body of the individual are frequently hidden by various objects, obstacles, or other people, making the identification process more difficult. To address these issues, we introduce a novel data augmentation strategy using artificial occlusions, consisting of random shapes and objects from a small image dataset that was created. We also propose an end-to-end methodology for occluded person Re-ID, which consists of three branches: a global branch, a feature dropping branch, and an occlusion detection branch. Experimental results show that the use of random shape occlusions is superior to random erasing using our architecture. Results on six datasets consisting of three tasks (holistic, partial and occluded person Re-ID) demonstrate that our method performs favourably against state-of-the-art methodologies.

Abstract
We present Caos: a programming framework for computer-aided design of structural operational semantics for formal models. This framework includes a set of Scala libraries and a workflow to produce visual and interactive diagrams that animate and provide insights over the structure and the semantics of a given abstract model with operational rules. Caos follows an approach where theoretical foundations and a practical tool are built together, as an alternative to foundations-first design (tool justifies theory) or tool-first design (foundations justify practice). The advantage of Caos is that the tool-under-development can immediately be used to automatically run numerous and sizeable examples in order to identify subtle mistakes, unexpected outcomes, and unforeseen limitations in the foundations-under-development, as early as possible. More concretely, Caos supports the quick creation of interactive websites that help the end-users better understand a new language, structure, or analysis. End-users can be research colleagues trying to understand a companion paper or students learning about a new simple language or operational semantics. We include a list of open-source projects with a web frontend supported by Caos that are used both in research and teaching contexts.

Abstract
The need for more flexible and robust models to reason about systems in the presence of conflicting information is becoming more and more relevant in different contexts. This has prompted the introduction of paraconsistent transition systems, where transitions are characterized by two pairs of weights: one representing the evidence that the transition effectively occurs and the other its absence. Such a pair of weights can express scenarios of vagueness and inconsistency. . This paper establishes a foundation for a compositional and structured specification approach of paraconsistent transition systems, framed as paraconsistent institution. . The proposed methodology follows the stepwise implementation process outlined by Sannella and Tarlecki.

Abstract
In streaming scenarios, models must learn continuously, adapting to concept drifts without erasing previously acquired knowledge. However, existing research communities address these challenges in isolation. Continual Learning (CL) focuses on long-term retention and mitigating catastrophic forgetting, often without strict real-time constraints. Stream Learning (SL) emphasizes rapid, efficient adaptation to high-frequency data streams, but typically neglects forgetting. Recent efforts have tried to combine these paradigms, yet no clear algorithmic overlap exists. We argue that large in-context tabular models (LTMs) provide a natural bridge for Streaming Continual Learning (SCL). In our view, unbounded streams should be summarized on-the-fly into compact sketches that can be consumed by LTMs. This recovers the classical SL motivation of compressing massive streams with fixed-size guarantees, while simultaneously aligning with the experience-replay desiderata of CL. To clarify this bridge, we show how the SL and CL communities implicitly adopt a divide-to-conquer strategy to manage the tension between plasticity (performing well on the current distribution) and stability (retaining past knowledge), while also imposing a minimal complexity constraint that motivates diversification (avoiding redundancy in what is stored) and retrieval (re-prioritizing past information when needed). Within this perspective, we propose structuring SCL with LTMs around two core principles of data selection for in-context learning: (1) distribution matching, which balances plasticity and stability, and (2) distribution compression, which controls memory size through diversification and retrieval mechanisms. © 2026 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Abstract

Abstract
Fighting the propagation of misinformation within a social media group or community by focusing on identifying dishonest members who deliberately try to quash any constructive social movement is very challenging because such people use advanced tactics to create division and doubt by manipulating information. The present research aims to develop a hybrid heuristic model to identify those who intentionally spread misleading information on social media to jeopardize a social movement. We frame this issue under the heading of Graph Semi-supervised Learning (GSSL), and we propose a hybrid model that falls under the heuristic approach, called Label Propagation-Gated Recurrent Unit (LP-GRU). LP-GRU can effectively identify perpetrators of disinformation within social communities by fusing community structure from the Label Propagation algorithm with behavioral patterns identified by GRU. Compared to previous heuristic approaches, we achieve up to 76% accuracy when using the LP-GRU model on augmented semi-synthetic social network data. © 2025 IEEE.