Unverified50% confidenceFactExact time
Dataset shift primarily includes three subtypes: covariate shift (changes in the distribution of input features while the conditional label distribution remains unchanged), prior probability shift (changes in the marginal distribution of labels), and concept drift (changes in the mapping relationship between inputs and outputs)
1
Sources
50%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified等价类划分法将输入数据划分为有效等价类（对应正向流程）和无效等价类（对应反向异常）63% similarUnverified分层采样（stratified sampling）先将用户查询按意图类型分类或通过embedding聚类，再从每个类别按比例或等量采样，比纯随机采样更能确保评估集代表性60% similarUnverified查询路由的实现方式分为三个层次：基于规则的正则匹配、基于轻量分类模型的意图预测、基于LLM的动态路由60% similarUnverifiedIntent data is generally divided into three categories—first-party, second-party, and third-party—with representative vendors including Bombora, 6sense, and TechTarget.60% similarUnverifiedReranking is typically implemented using cross-encoders, which concatenate the query and candidate documents before feeding them in together; it usually reranks only the Top-50 to Top-100 candidates and finally selects Top-3 to Top-5 to pass to the generative model.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/870153API
curl https://kongchang.com/api/v1/knowledge/claims/870153MCP
get_claim(id=870153)