Defines meta-attributions as directional second-order Shapley values on attribution methods, proves hierarchical decomposition of attributions, and demonstrates applications in language models, vision-language encoders, and diffusion transformers.
5.Is this loop correct? for i inrange(len(arr)– 1): if arr[i] > arr[i+1]: swap(arr, i, i+1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attributions All the Way Down? The Metagame of Interpretability
Defines meta-attributions as directional second-order Shapley values on attribution methods, proves hierarchical decomposition of attributions, and demonstrates applications in language models, vision-language encoders, and diffusion transformers.