Unverified50% confidenceFactExact time
The neural expansion framework explains OOD samples as inputs that fall outside the ray coverage of training samples, so the model's predictions on them lack stability and may exhibit high uncertainty or random predictions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedOver-reliance on the fine-tuned part during fine-tuning may be precisely the root cause of rare-class capabilities being obscured; directing the model's computation moderately toward the pretrained components may be a more robust fine-tuning route.78% similarUnverifiedFor high-stakes or rare scenario predictions, it is recommended to reduce uncertainty through Bayesian averaging of multiple independent models rather than blindly trusting the output of a single pretrained model.77% similarVerifiedAn intermittently faulty memory module may alternately produce correct and incorrect computation results, causing sporadic deviations in gradient calculations during neural network training, affecting model convergence without triggering hardware alerts.75% similarUnverifiedAdversarial examples often lie at the edge of or outside ray coverage, while mislabeled samples may be covered within the expanded regions of training samples, causing the model to "confidently" give wrong predictions.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065871API
curl https://kongchang.com/api/v1/knowledge/claims/1065871MCP
get_claim(id=1065871)