Unverified50% confidenceFactExact time
In the example, using equal-weight RRF with k=60, chunk B (generic login troubleshooting advice) ranks first, even though chunk A contains the specific fix.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedReciprocal Rank Fusion (RRF) computes the final score for each document by summing the reciprocal of its rank in each ranked list plus a smoothing constant k (typically set to 60).69% similarUnverifiedFor Gaussian arms with a common variance, SR's worst-case error exponent (after normalization by H₁(P)) is already optimal up to a constant factor.67% similarVerifiedThe core formula of RRF is RRF_score(d) = Σ 1 / (k + rank_i(d)), where k is a smoothing constant commonly set to 60.66% similarUnverifiedIn the task of completing the last Token of an FP8 quantization function, after DeepSeek-V4-Flash-Base adds equal-sign decorations before the code, when the number of equal signs modulo 4 is 0 or 1 the error rate is as high as 71.3%, and when the remainder is 2 or 3 the accuracy returns to 91.5%.64% similarUnverifiedRRF uses only ranks rather than raw scores, avoiding the problem that the dimensions of dense vectors and sparse BM25 are not comparable.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063937API
curl https://kongchang.com/api/v1/knowledge/claims/1063937MCP
get_claim(id=1063937)