Unverified50% confidenceFactExact time
A document evidence model agreed with the reference labels on 36 out of 40 observations, for an accuracy of 90%.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe reference distribution of the 40 observations is: 1 recorded evidence, 33 not localized, 0 explicitly missing, and 6 ambiguous.77% similarUnverifiedThe 4 dimensions within the same document share text, format, extraction quality, and source context, and the observations are correlated, so describing these 40 observations as 40 independent cases would be misleading.74% similarUnverifiedThe two reviewers agreed on 35 of 40 items, and in the end both passed 32 of the 40 signatures (80%, 95% interval 65–90%).72% similarUnverifiedWhen reporting success rates, the sample size must be included, because 19/20 and 950/1000 represent different levels of evidential strength.72% similarUnverified41个完整测试套件中有20个拿到满分100%，该基准已无法区分这些领先模型71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1044445API
curl https://kongchang.com/api/v1/knowledge/claims/1044445MCP
get_claim(id=1044445)