Unverified50% confidenceDecision RuleExact time
To discuss p95 you need at least dozens of samples, and p99 requires hundreds; twelve runs can only provide existence evidence (missing usage field, 429, whether the tail is two seconds or twenty) and cannot precisely estimate quantiles.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedComputing p95 from twelve samples actually lands between the 11th and 12th samples—essentially the second-slowest run—and is extremely unstable.73% similarUnverified若单帧误检率为p，连续8帧独立误检的概率为p^8，即使单帧误检率高达10%，8帧连续误检概率也只有10^-869% similarUnverifiedPerformance benchmark results are subject to statistical fluctuation, requiring multiple runs to take the median or P95/P99 percentiles for evaluation.66% similarUnverifiedWhen the sample size is small (e.g., only 5–10 successful requests), quantile estimation errors can be large; numpy.percentile or a larger sample size can be used to improve reliability.66% similarUnverifiedThis study points out that empirical results on the approximation quality of PFNs are surprisingly scarce.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1067317API
curl https://kongchang.com/api/v1/knowledge/claims/1067317MCP
get_claim(id=1067317)