Unverified50% confidenceFactExact time
For the quadratic form behind each class probability, its BEM is equivalent to Integrated Gradients from a zero baseline, and a closed-form solution exists.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn nonparametric regression, if the true regression function belongs to the s-order Hölder ball, then the worst-case mean squared error of any estimator has a lower bound c n^{-2s/(2s+D)}, where the constant c does not depend on n.67% similarUnverifiedThe congruence coefficient (Tucker's φ) is computed by standardizing the loading vectors of the same factor in the two solutions and then taking their inner product; its value theoretically ranges from -1 to 1, where 1 indicates that the two sets of loadings point in exactly the same direction, 0 indicates no relation, and a negative value indicates opposite directions.66% similarUnverifiedRETD achieves a certified negative Lyapunov exponent on both the two-state counterexample and a Baird point, while the positive exponent sign of ETD on the Baird counterexample remains at the numerical level.65% similarUnverified如果所有零点都在临界线上，素数分布与对数积分Li(x)的偏差不超过O(√x·log x)的量级65% similarUnverifiedWhen d≤2n, the upper bound and lower bound also match in the confidence dependence, differing only by a logarithmic factor in accuracy.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129534API
curl https://kongchang.com/api/v1/knowledge/claims/1129534MCP
get_claim(id=1129534)