A Survey on Quantitative Possibility Theory in Artificial Intelligence: A Convenient Epistemic Uncertainty Model

Destercke, Sébastien; Dubois, Didier; Prade, Henri

doi:10.24963/ijcai.2026/869

A Survey on Quantitative Possibility Theory in Artificial Intelligence: A Convenient Epistemic Uncertainty Model

Sébastien Destercke, Didier Dubois, Henri Prade

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Survey Track. Pages 7826-7834.

https://doi.org/10.24963/ijcai.2026/869

Keywords

Uncertainty in AI: Graphical models
Uncertainty in AI: Nonprobabilistic models
Uncertainty in AI: Uncertainty representations

Abstract

Quantitative (or numerical) possibility theory offers a simple but yet very expressive setting for handling higher-order uncertainty and in particular imprecise probabilities. The paper surveys the basic ideas and notions underlying numerical possibility theory, its relation to the other uncertainty settings and its use in AI-related issues. Numerical possibility theory looks of interest for coping with imperfect statistical information, especially non-Bayesian statistics relying on likelihood functions and confidence intervals. Quantitative possibility theory can be used in inference, machine learning, tracking and information fusion, and finally preference modeling.

Sébastien Destercke, Didier Dubois, and Henri Prade. 2026. A Survey on Quantitative Possibility Theory in Artificial Intelligence: A Convenient Epistemic Uncertainty Model. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7826–7834. https://doi.org/10.24963/ijcai.2026/869

@inproceedings{ijcai2026p869,
  title     = {A Survey on Quantitative Possibility Theory in Artificial Intelligence: A Convenient Epistemic Uncertainty Model},
  author    = {Destercke, Sébastien and Dubois, Didier and Prade, Henri},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7826--7834},
  year      = {2026},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2026/869},
  url       = {https://doi.org/10.24963/ijcai.2026/869},
}

TY  - CPAPER
TI  - A Survey on Quantitative Possibility Theory in Artificial Intelligence: A Convenient Epistemic Uncertainty Model
AU  - Destercke, Sébastien
AU  - Dubois, Didier
AU  - Prade, Henri
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7826
EP  - 7834
DO  - 10.24963/ijcai.2026/869
UR  - https://doi.org/10.24963/ijcai.2026/869
ER  -