Unverified90% confidenceFactTime unknown
该项目采用配对McNemar检验作为统计显著性验证方法
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMcNemar's test is a non-parametric test method specifically designed for paired binary classification data79% similarUnverifiedThe majority of Link CC MCP's 78 tools passed verification smoothly in tests with advanced models.72% similarUnverified多种子实验中检验对象从单样本预测分歧变为多次运行的准确率序列时，通常已不再适用McNemar检验72% similarUnverifiedR中的mcnemar.test()函数可以自动处理卡方近似与精确检验之间的切换68% similarUnverifiedThe MCP tool demonstration was verified in AWS Kuro coding assistant, IntelliJ IDE, and MCP Inspector.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/29798API
curl https://kongchang.com/api/v1/knowledge/claims/29798MCP
get_claim(id=29798)