Moose compiles OWL 2 EL ontologies into a Lean-verified differentiable weighted-model-counting layer and uses it to learn latent concept labels under partial supervision, beating propositional neuro-symbolic baselines on relational and role-chain MNIST regimes.
In: Proceedings of the OWLED 2008 DC Workshop on OWL: Experiences and Directions (2008)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
Moose compiles OWL 2 EL ontologies into a Lean-verified differentiable weighted-model-counting layer and uses it to learn latent concept labels under partial supervision, beating propositional neuro-symbolic baselines on relational and role-chain MNIST regimes.