Unverified50% confidenceDecision RuleExact time
The rules derived from the audit: pass rates should be reported per goal rather than only aggregated; and '≥20 rows and 100% pass' should be treated as suspicious rather than successful.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen reporting success rates, the sample size must be included, because 19/20 and 950/1000 represent different levels of evidential strength.76% similarUnverifiedResearch shows that in certain tasks, simply changing '请判断' to '请分析' in a prompt can cause accuracy fluctuations of 5–10 percentage points.71% similarUnverifiedSetting an absolute failure count ceiling for small-sample slices is more robust than setting a percentage threshold and is insensitive to sample size70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018814API
curl https://kongchang.com/api/v1/knowledge/claims/1018814MCP
get_claim(id=1018814)