MCCHE Precision Convergence Webinar Series with Giancarlo Guizzardi
Beyond Explainable AI: Explanation, Semantics, Ontology
By Giancarlo Guizzardi
Professor University of Twente
Date: Thursday, April 23, 2026
Time: 4:00 p.m. to 6:00 p.m.
Location: Online
Abstract
We live much of our lives immersed in the world of socially constructed entities such as money, property deeds, employments, marriages, legal liabilities, and derivative transactions, which is increasingly grounded in the symbolic manipulation of digital representations. In this scenario, institutional facts are made true by scattered pieces of information that reside in independent information silos and that were created by different organizational cultures, through independent engineering processes, in different moments in space and time. How can we safely create a unified, transparent and consistent view of social reality by putting together these scattered and concurrently developed information structures, each of which carve out reality in potentially different ways? Properly addressing this question became even more critical with the diffusion of modern AI technologies that, contra the EU AI Act, are inherently opaque w.r.t. their reasoning and decision-making processes, the digital representations they manipulate and, hence, how they create these institutional facts. In this talk, I will present a method for engineering semantic transparency, interoperability and contestability by design in systems via explaining their information structures. Finally, I will argue that the current trend in XAI (Explainable AI) in which 鈥渢o explain is to produce a symbolic artifact鈥� is an incomplete project as these artifacts are not 鈥渋nherently interpretable鈥�, and that they should be taken as the beginning of the road to explanation, not the end.
In summary, this talk offers a unified vision of foundational AI for time-series and multimodal sensors, combining robust temporal modeling, cross-modal alignment, and scalable representation learning to unlock new capabilities in dynamic, real-world environments.
