Abductive forgetting
This addresses a theoretical limitation in logic and AI for researchers in automated reasoning, but it is incremental as it builds on existing concepts of forgetting and abduction.
The paper tackles the problem of removing variables from logical formulas while preserving abductive explanations, showing that this may not be expressible in propositional logic and providing conditions and alternatives to ensure expressibility.
Abductive forgetting is removing variables from a logical formula while maintaining its abductive explanations. It is carried in two alternative ways depending on its intended application. Both differ from the usual forgetting, which maintains consequences rather than explanations. Differently from that, abductive forgetting from a propositional formula may not be expressed by any propositional formula. A necessary and sufficient condition tells when it is. Checking it is $Π^p_3$-complete. A way to guarantee expressibility of abductive forgetting is to switch from propositional to default logic. Another is to introduce new variables.