HCA combines knowledge graphs, KKT multipliers, and PCMCI to explain nonlinear MPC decisions, achieving 53% higher accuracy than LIME across three domains with a single parameter set.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control
HCA combines knowledge graphs, KKT multipliers, and PCMCI to explain nonlinear MPC decisions, achieving 53% higher accuracy than LIME across three domains with a single parameter set.