Unverified50% confidenceFactExact time
The computational complexity of cross-encoders is O(n²); document representations cannot be precomputed and scoring must be done online pair by pair, so cross-encoders are typically only used to rerank the top-k results returned by an initial retrieval stage.
1
Sources
50%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBinary search locates an element in a sorted array in only O(log n) comparisons, and the search and insertion operations of a balanced binary search tree also have O(log n) time complexity.68% similarUnverified非原生图数据库需通过全局索引查找相邻节点，时间复杂度随图规模增长为O(log n)甚至O(n)66% similarVerifiedThe Hungarian algorithm has a time complexity of O(n³) and can find the globally optimal assignment in bipartite graph matching problems.66% similarVerified重排序（Re-ranking）机制在初步检索后引入交叉编码器（Cross-Encoder）对候选文档重新打分，提升输入大模型的上下文质量65% similarUnverified标准多头注意力中每个Token需与序列中所有其他Token计算相关性权重，计算复杂度为O(N²)65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/848734API
curl https://kongchang.com/api/v1/knowledge/claims/848734MCP
get_claim(id=848734)