Unverified50% confidenceFactExact time
The team's first study collected about 95,000 pieces of AI-cited content and decomposed 189 factors, but it was overturned due to problems such as p > n, using in-sample data for evaluation, and using globally random negative samples; after query-level out-of-fold re-measurement, R² = −0.31.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe head-to-head comparison in this study was statistically underpowered at a sample size of n=9668% similarUnverifiedThe accuracy data in the test has an error margin of approximately ±8–10 percentage points at n=100 sample size (based on a 95% confidence-level binomial confidence interval).67% similarUnverifiedResearch published by Ahrefs in March 2026 covering 863,000 search results and 4 million AI Overview links found that only about 38% of AI Overview citations came from classic top-10 organic ranking results.67% similarUnverified在案例测试中，直接将所有原始资料塞给AI的校验分为2/100，而经过上下文编译处理后的校验分为90/10067% similarUnverifiedThe research team conducted a retrospective ablation analysis across 12 models with a total of 121,680 valid trials, of which 79,853 failed the executability check.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048787API
curl https://kongchang.com/api/v1/knowledge/claims/1048787MCP
get_claim(id=1048787)