Unverified50% confidenceFactExact time
Horizontal expansion refers to that, after semantic retrieval hits initial seed memories, the system expands along the graph structure to their neighboring nodes, bringing semantically related memories that were not directly retrieved into the candidate set.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn LExGraph, hybrid retrieval is responsible for locating seeds among memory nodes, and neighbor expansion supplements this with structural associations, forming a two-stage evidence acquisition process of "locate first, then diffuse".72% similarUnverifiedIn the layered memory strategy, shallow memory is used only to decide whether to reply, while deep memory is brought in to generate content when a reply is decided.71% similarUnverifiedTheoretical proofs show that as long as memory allocation does not depend on historical state, the statement permutation method can achieve the modeled peak memory byte-for-byte, and the output results are bit-for-bit identical to the original program.71% similarUnverifiedStructured step-by-step instructions create local contextual anchors for the model, forcing the attention mechanism to distribute more evenly across different semantic units.70% similarUnverifiedMemory entries are injected into the context window as part of the system prompt; this is essentially a form of persistent prompt engineering that changes the input the model sees rather than the model's parameters.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154536API
curl https://kongchang.com/api/v1/knowledge/claims/1154536MCP
get_claim(id=1154536)