Unverified50% confidenceFactExact time
OOD samples may fall outside the coverage, thereby exhibiting high uncertainty.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedWhen all sampled outputs in a group are incorrect, the group-relative advantage collapses to zero, causing the model to receive no effective gradient feedback in high-uncertainty scenarios.71% similarUnverifiedThe 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.71% similarUnverifiedWhen the geometry of the ambiguity set does not match the true structure of prediction errors, a very large radius is needed to cover the uncertainty, leading to overly conservative decisions.70% similarUnverifiedThe margin of error only reflects the uncertainty introduced by sampling and cannot encompass non-sampling errors, such as question wording bias, non-response bias, coverage bias, and social desirability bias.70% similarUnverifiedIn the presence of external rules, more informative data may instead be harmful, which means that usage risk in general cannot be expressed as an expected reduction in uncertainty, and standard BED is merely a special case of the usage-aware framework.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065870API
curl https://kongchang.com/api/v1/knowledge/claims/1065870MCP
get_claim(id=1065870)