Get Started
Research questionHow can abductive explanations for Boolean classifiers be computed efficiently despite hardness in OBDDs?Abductive explanations can clarify why a Boolean classifier makes a decision, but shorter and preference-aware explanations remain hard to compute even when the classifier is compiled into an Ordered Binary Decision Diagram.
AI
Machine Learning
Research Paper
Latest papersRecent research connected to this question, newest first.Solving Hard XAI Queries Based on a Compiled Dual-Rail EncodingThe problem concerns Boolean classifiers and abductive explanations computed from compiled Ordered Binary Decision Diagram representations. The source specifically discusses shorter explanations and explanations incorporating the explainee’s preferences, and presents dual-rail encoding as the relevant representation for recovering efficient computation.research paper · Sep 4, 2026
Related questions
How can we explain interacting reasons behind classifier predictions fast enough for repeated local use?How can BDD variable ordering minimize quantum circuit cost when BDD size is a poor proxy?How can unsupervised tabular anomaly detectors provide faithful feature-level explanations without costly post-hoc queries?How can extracted rules from tree ensembles retain calibrated probabilities while simplifying predictions?
Home
Topics
Search
Library