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

Abstract
Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula images to predict DR and sensitive attributes (SAs) (e.g., age and gender/sex). Fairness was assessed between subgroups of SAs, and disentanglement was applied to reduce bias. All models achieved high DR prediction performance in diagnosing (up to 94% AUROC) and could reasonably predict age and gender/sex (91% and 77% AUROC, respectively). Fairness assessment suggests disparities, such as a 10% AUROC gap between age groups in DINOv2. Disentangling SAs from DR prediction had varying results, depending on the model selected. Disentanglement improved DINOv2 performance (2% AUROC gain), but led to performance drops in ConvNeXt V2 and Swin V2 (7% and 3%, respectively). These findings highlight the complexity of disentangling fine-grained features in fundus imaging and emphasize the importance of fairness in medical imaging AI to ensure equitable and reliable healthcare solutions.

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.

Abstract
We present Keigo, a concurrency-and workload-aware storage middleware that enhances the performance of log-structured merge key-value stores (LSM KVS) when they are deployed on a hierarchy of storage devices. The key observation behind Keigo is that there is no one-size-fits-all placement of data across the storage hierarchy that optimizes for all workloads. Hence, to leverage the benefits of combining different storage devices, Keigo places files across different devices based on their parallelism, I/O bandwidth, and capacity. We introduce three techniques-concurrency-aware data placement, persistent read-only caching, and context-based I/O differentiation. Keigo is portable across different LSMs, is adaptable to dynamic workloads, and does not require extensive profiling. Our system enables established production KVS such as RocksDB, LevelDB, and Speedb to benefit from heterogeneous storage setups. We evaluate Keigo using synthetic and realistic workloads, showing that it improves the throughput of production-grade LSMs up to 4x for write-and 18x for read-heavy workloads when compared to general-purpose storage systems and specialized LSM KVS.