Unverified50% confidenceSolutionExact time
NavTree's tree itself stores no summaries and is used only as a navigation skeleton; during retrieval it employs a hybrid frontier traversal strategy combining lexical and dense methods, and ultimately outputs only leaf text chunks to the reader.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedNavTree is a leaf-node-only retriever that builds a deterministic balanced segment tree on top of text chunks; the entire indexing process does not call any language model, making the indexing cost zero.76% similarUnverifiedThe tree index does not rely on vector similarity search and relies entirely on the language model's own comprehension capability to navigate the document structure.64% similarUnverifiedText chunking granularity that is too large results in retrieved text containing large amounts of irrelevant information, while granularity that is too small may lose contextual semantics.57% similarUnverifiedThe recursive character text splitter balances the contradiction between document chunks being too long to exceed the context window and too short to lose semantics by attempting to split at natural boundaries (paragraphs, sentences).56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/982958API
curl https://kongchang.com/api/v1/knowledge/claims/982958MCP
get_claim(id=982958)