Unverified50% confidenceFactExact time
Unit sphere embedding maps reasoning segment vectors onto a sphere of radius 1 via L2 normalization, so that similarity can be measured directly by inner product or cosine distance.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedWhen feature vectors are L2-normalized, cosine similarity is equivalent to the dot product operation.77% similarUnverifiedBefore clustering, L2 normalization can be applied, or the Spherical K-Means variant using cosine distance as the metric can be adopted to address the magnitude-dominance problem.74% similarUnverifiedCosine similarity measures the cosine of the angle between two vectors, normalizes by the magnitude of the vectors in the denominator, and completely ignores vector magnitude while only caring about direction.68% similarUnverifiedIn the L×L lattice model, only a single one-dimensional model is needed, replicated L×L times at inference with quadratic interactions injected, and the algorithm correctly captures phase transition behavior67% similarUnverifiedFor L2-normalized embeddings, cosine distance and Euclidean distance yield completely identical ranking results66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074053API
curl https://kongchang.com/api/v1/knowledge/claims/1074053MCP
get_claim(id=1074053)