CC BY-NC-ND 4.0Shariatmadar, KeivanKeivanShariatmadarOsman, AhmadAhmadOsmanRay, RaminRaminRayKim, KisamKisamKim2025-11-252025-11-252025https://publica.fraunhofer.de/handle/publica/499710https://doi.org/10.24406/publica-654810.48550/arXiv.2510.1819310.24406/publica-6548Fair, transparent, and explainable decision-making remains a critical challenge in Olympic and Paralympic combat sports. This paper presents \emph{this http URL 2.0}, an explainable AI ecosystem designed to support referees, coaches, and athletes in real time during Taekwondo competitions and training. The system integrates {pose-based action recognition} using graph convolutional networks (GCNs), {epistemic uncertainty modeling} through credal sets, and {explainability overlays} for visual decision support. A set of {interactive dashboards} enables human--AI collaboration in referee evaluation, athlete performance analysis, and Para-Taekwondo classification. Beyond automated scoring, this http URL~2.0 incorporates modules for referee training, fairness monitoring, and policy-level analytics within the World Taekwondo ecosystem. Experimental validation on competition data demonstrates an {85\% reduction in decision review time} and {93\% referee trust} in AI-assisted decisions. The framework thus establishes a transparent and extensible pipeline for trustworthy, data-driven officiating and athlete assessment. By bridging real-time perception, explainable inference, and governance-aware design, this http URL~2.0 represents a step toward equitable, accountable, and human-aligned AI in sports.enExplainable AIComputer VisionOlympicParaolympicTaekwondoReferee TrainingAthlete PerformanceBigdata AnalyticsHuman-AI Interaction600 Technik, Medizin, angewandte Wissenschaftenpaper