Signed pairwise interaction scores conflate U/R/S; Stochastic Hi-Fi uses interventional masked inference to recover per-feature uniqueness, redundancy, and synergy profiles.
An axiomatic approach to the concept of interaction among play- ers in cooperative games.International Journal of Game Theory, 28(4):547–565, Nov 1999
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
WoodelfHD reduces Background SHAP preprocessing for decision trees from 3^D to 2^D complexity, enabling exact computation on depths up to 21 with reported speedups of 33x to 162x.
Derives an interaction measure between crosscoder features from reconstruction error in compact proofs and applies it to produce computationally sparse crosscoders retaining 60% MLP performance with single-feature selection versus 10% for standard crosscoders.
CUDAnalyst enables generation-level attribution of heterogeneous feedback effects on planning in self-evolving LLM agents for CUDA kernel generation via controlled trajectory freezing and injection experiments.
ProxySHAP approximates higher-order Shapley and Banzhaf interactions via tree proxies plus residual correction and a polynomial-time interventional TreeSHAP generalization for tree ensembles.
citing papers explorer
-
The Representational Limit of Scalar Interactions: An Interventional Decomposition
Signed pairwise interaction scores conflate U/R/S; Stochastic Hi-Fi uses interventional masked inference to recover per-feature uniqueness, redundancy, and synergy profiles.
-
WOODELF-HD: Efficient Background SHAP for High-Depth Decision Trees
WoodelfHD reduces Background SHAP preprocessing for decision trees from 3^D to 2^D complexity, enabling exact computation on depths up to 21 with reported speedups of 33x to 162x.
-
Interactions Between Crosscoder Features: A Compact Proofs Perspective
Derives an interaction measure between crosscoder features from reconstruction error in compact proofs and applies it to produce computationally sparse crosscoders retaining 60% MLP performance with single-feature selection versus 10% for standard crosscoders.
-
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
CUDAnalyst enables generation-level attribution of heterogeneous feedback effects on planning in self-evolving LLM agents for CUDA kernel generation via controlled trajectory freezing and injection experiments.
-
Proxy-Based Approximation of Shapley and Banzhaf Interactions
ProxySHAP approximates higher-order Shapley and Banzhaf interactions via tree proxies plus residual correction and a polynomial-time interventional TreeSHAP generalization for tree ensembles.