Unverified50% confidenceFactExact time
In the vertical dimension, HiVe-Mem lets each retrieved memory retain multiple forms of evidence, including compact summaries, descriptive text, visual-grounding-based views, raw images, and interaction history.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHiVe-Mem organizes memory segments into a relational graph, with nodes connected through textual anchors and visual anchors.76% similarUnverifiedThe user profile uses a layered memory architecture divided into three layers: permanent preferences, situational physiological information and immediate conversation context.70% similarUnverifiedRepresentative tools of the knowledge graph approach, such as Mem0 and Zep, structure entities and relationships as graph nodes and edges, traversing the graph to retrieve memories during search.69% similarUnverifiedHorizontal expansion broadens the recall coverage of memories, while vertical composition optimizes how each memory's evidence contributes, and the two work in concert.68% similarUnverifiedSick Memory uses a unified hub that first distinguishes identity, drawing and the boundaries of what can be said; facts are not overwritten, but understandings can have versions.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154537API
curl https://kongchang.com/api/v1/knowledge/claims/1154537MCP
get_claim(id=1154537)