Unverified50% confidenceFactExact time
Recursive character chunking traverses separators according to a priority list—paragraphs, line breaks, sentences, words, characters—and splits using the highest-priority separator under the premise that chunks do not exceed the limit.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the hypergraph setting, the greedy algorithm at each step preferentially selects the sentence node participating in the greatest number of hyperedges, which is equivalent to preferentially selecting the sentence covering the most key topics.71% similarUnverifiedThe Top-K pruning strategy is essentially a branch-and-bound algorithm based on a priority queue (min-heap).66% similarUnverifiedPlacing the most relevant chunks at the beginning or end of the prompt rather than arranging them in order of retrieval score often improves generation quality.66% similarVerifiedReranking 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.66% similarUnverified序列化的规范化处理需要字典键值按字典序排序、浮点数截断至固定精度、列表元素保持顺序一致，否则语义等价的状态可能生成不同哈希值62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048034API
curl https://kongchang.com/api/v1/knowledge/claims/1048034MCP
get_claim(id=1048034)