Unverified50% confidenceFactExact time
Spurious correlation is a common failure mode in machine learning: the model captures features that are statistically correlated with labels but not causally related, and makes predictions based on them.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
Unverified对抗性机器学习研究已证明通过对抗性样本可以欺骗计算机视觉模型做出错误分类75% similarUnverifiedInference methods based on model internal features face a trade-off between false positives and false negatives74% similarUnverifiedThe tested models exhibited critical failures in judging image authenticity, representing a fatal weakness in their detection capability.71% similarUnverifiedThe stronger error correlation among frontier models is attributed to highly overlapping training data and the shared fitting of human preference data through RLHF, resulting in homogenization of error patterns.71% similarUnverifiedData from failure cases has unique value in telling models which paths do not work, and this type of negative information is severely lacking in public literature.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138458API
curl https://kongchang.com/api/v1/knowledge/claims/1138458MCP
get_claim(id=1138458)