Unverified50% confidenceFactExact time
Out-of-distribution samples refer to inputs whose distribution differs markedly from the data seen during training or compilation; local logic consisting of rules or small classifiers often fails near the boundaries.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedContext confusion produces narrow misalignment, where misalignment is concentrated in specific domains semantically close to the training data, rather than a broad degradation of the model's overall behavior.76% similarVerifiedBehavioral cloning simplifies the problem to supervised learning, but suffers from distribution shift, where differences between the state distributions at training time and execution time lead to error accumulation.76% similarUnverifiedStandardized benchmarks have the limitation of out-of-distribution generalization, where agents may score by memorizing training set patterns rather than truly possessing reasoning ability.74% similarUnverified小模型在分布内高性能的同时存在分布外脆弱性，一旦推理时的工具描述措辞、参数命名或用户查询风格偏离训练集，成功率可能显著下滑74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065472API
curl https://kongchang.com/api/v1/knowledge/claims/1065472MCP
get_claim(id=1065472)