Imparo is complete by inverse subsumption
This is an incremental theoretical result for inductive logic programming researchers, addressing completeness in hypothesis learning.
The paper proves that the Imparo inductive logic programming system is complete for learning correct definite hypotheses using inverse subsumption, establishing that a connected theory exists such that the hypothesis subsumes it.
In Inverse subsumption for complete explanatory induction Yamamoto et al. investigate which inductive logic programming systems can learn a correct hypothesis $H$ by using the inverse subsumption instead of inverse entailment. We prove that inductive logic programming system Imparo is complete by inverse subsumption for learning a correct definite hypothesis $H$ wrt the definite background theory $B$ and ground atomic examples $E$, by establishing that there exists a connected theory $T$ for $B$ and $E$ such that $H$ subsumes $T$.