Unverified50% confidenceFactExact time
Vector retrieval commonly uses cosine similarity to compute the angle between vectors; the smaller the angle, the more relevant.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCosine similarity measures the directional consistency of two vectors, has a range of [-1, 1], and is the foundation of tasks such as semantic search and clustering.76% similarVerifiedCosine similarity only cares about vector direction and not length, with values strictly falling in the range [-1, 1].75% similarUnverifiedSimilarity scores (such as cosine similarity) measure semantic relevance, but they do not mean that the fragment can answer the query.72% similarUnverifiedThe computational complexity of Total Variation similarity is of the same order as that of cosine similarity.72% similarVerifiedCosine similarity has a value range of [-1, 1]; in semantic retrieval, attention is typically focused only on the positively correlated range of 0 to 1, with values closer to 1 indicating greater semantic similarity.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1106817API
curl https://kongchang.com/api/v1/knowledge/claims/1106817MCP
get_claim(id=1106817)