Publications
- Do Graph Neural Network States Contain Graph Properties?Tom Pelletreau-Duris, Ruud van Bakel, Michael Cochez — Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning ·
Presents a model-agnostic explainability pipeline that uses diagnostic classifiers to probe graph neural network embeddings for structural graph properties, clarifying what information their hidden states retain across architectures and datasets.
- Development and validation of a quantitative instrument for measuring temporal and social disorientation in the Covid-19 crisisPablo Fernandez Velasco, Umer Gurchani, Bastien Perroy, Tom Pelletreau-Duris, Roberto Casati — PLOS ONE ·
Validated the Instrument for Temporal and Social Disorientation (ITSD) across more than 3,300 participants, offering a quantitative way to capture the temporal and social disruption experienced during the Covid-19 crisis.