Unverified50% confidenceFactExact time
The higher the heterogeneity, the harder it is for the global model obtained through federated aggregation to behave consistently across clients, and the more inconsistent the gradient directions, which is a potential mechanism by which explanation maps may become distorted.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBehavioral drift has long lacked a unified quantitative standard, relying more on trajectory-level structured comparison.76% similarUnverifiedInferring expert overlap from tokens/sec confounds multiple variables such as acceptance rate, overlap, kernel efficiency and communication overhead, making it impossible to locate the bottleneck.75% similarVerifiedMax mode raises the lower bound of reasoning tokens rather than the upper bound, forcing the model to reach a certain amount of reasoning before it is considered complete, which often harms performance.75% similarUnverifiedGradient weighting on high-similarity negatives persistently harms downstream generalization, i.e., excessively pushing the model away from certain samples disrupts the overall structure of the embedding space, so retrieval performance drops rather than rises (termed 'gradient distortion').74% similarUnverifiedLocal models generally have weaker inference capabilities than top closed-source models, and the probability of misjudgment in complex operations and maintenance scenarios may be higher74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113991API
curl https://kongchang.com/api/v1/knowledge/claims/1113991MCP
get_claim(id=1113991)