Unverified50% confidenceFactExact time
Vector retrieval returns cosine similarity or distance scores, while BM25 returns term-frequency-based scores; the two have different units, so raw scores cannot be directly added or compared.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core mechanism of BM25 is based on three factors: term frequency (TF), inverse document frequency (IDF), and document length normalization, with parameter k1 typically set between 1.2 and 2.0 and b typically set at 0.75.67% similarUnverifiedAfter testing 30 layer combinations, the best pairing was SenseNova L32 mapped to MiniMax H3 L49, using a 4096→128→5120 projector that achieved a cosine similarity of 0.9042 on the validation set.65% similarUnverifiedUsing a 4B model to rerank the candidate shortlist filtered by BM25 outperformed BM25 alone (+0.047, confidence interval [0.020, 0.073]), even though the 4B reranker itself did not pass qualification.64% similarVerifiedBM25 (Best Matching 25) is a probabilistic ranking algorithm proposed by Stephen Robertson and others in the 1990s, scoring relevance based on three factors: term frequency, inverse document frequency, and document length normalization.62% similarUnverifiedRegardless of the encoding scheme used, 4-bit precision can only distinguish 16 different numerical levels.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976369API
curl https://kongchang.com/api/v1/knowledge/claims/976369MCP
get_claim(id=976369)