Unverified50% confidenceFactExact time
The paper proves that the distance corresponding to the representation induced by log-odds is exactly equal to the ℓ1 distance between analytical Shapley value vectors.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper proves that there exist networks of constant depth and size Õ_{n,d}(p^{-9}ε^{-max{d/n,2}}log(1/δ)) that satisfy the probabilistic uniform approximation requirement with probability at least 1-δ.65% similarUnverifiedThe error bound in this paper holds for all Wasserstein-p distances with p ≥ 1, rather than being limited to a specific metric.65% similarUnverifiedCosine similarity and Euclidean distance may give diametrically opposite judgments about which two vectors are more similar.64% similarUnverifiedThe 2-Wasserstein distance is more sensitive to the geometric shape of the support sets of distributions than KL divergence, and can yield meaningful finite distance values even when the support sets of two distributions do not overlap.64% similarUnverifiedOverall accuracy that mixes all distances will be dominated by the large number of easily recognizable nearby samples, thereby masking true performance deficiencies at greater distances.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990775API
curl https://kongchang.com/api/v1/knowledge/claims/990775MCP
get_claim(id=990775)