BOHM extracts multi-resolution attribution trees from existing routing weights in hierarchical AI systems, providing zero-cost explanations that correlate with SHAP when routing is near-optimal.
Inter-module credit assignment in modular reinforcement learning.Neural Networks, 16(7):985–994, 2003
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A proportional weight-update rule creates implicit binary evaluation signals that propagate losslessly through hierarchical selectors while preserving algebraic market integrity and admitting unique interior equilibria.
citing papers explorer
-
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems
BOHM extracts multi-resolution attribution trees from existing routing weights in hierarchical AI systems, providing zero-cost explanations that correlate with SHAP when routing is near-optimal.
-
Implicit Evaluation Under Minimal Information: Price Formation in Hierarchical Component Selection
A proportional weight-update rule creates implicit binary evaluation signals that propagate losslessly through hierarchical selectors while preserving algebraic market integrity and admitting unique interior equilibria.