Unverified50% confidenceFactExact time
The similarity measure is changed from cosine similarity to Total Variation similarity to suit probability distribution comparison on the simplex.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPaired comparison is more reliable than independent evaluation because it eliminates randomness introduced by sample selection.63% similarUnverifiedThe rankings provided by vector retrieval are generally trustworthy, but their absolute similarity values are not, unless they have been calibrated.62% similarUnverifiedThe inconsistency score in the study is calculated as follows: compute pairwise similarities between baseline IPA transcriptions, compute pairwise similarities between corresponding phonetic codes, and take the absolute difference between the two, using normalized edit distance as the similarity measure.61% similarUnverifiedCross-grader differences in compliance rates manifest as multiplicative (ratios can reach tens of times), whereas differences in non-refusal rates manifest as additive (percentage-point differences), so non-refusal rate is more robust to grader disagreement but coarser-grained.61% similarUnverifiedThe statistical premise of drift detection is that the two sets of observations being compared must be comparable samples from the same distribution; directly comparing raw counts across versions produces false positives.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098270API
curl https://kongchang.com/api/v1/knowledge/claims/1098270MCP
get_claim(id=1098270)