Temporal context & association
Recalling one thing pulls its neighbors with it — everything you learned in the same hour.
In the brain
Memories formed close together in time get linked. Recalling one tends to drag its neighbors along — the contiguity effectHoward 2002. A slowly drifting internal “context” is bound to each memory as it forms; reinstating that context reactivates everything you encoded in the same stretch. It’s why a smell can return an entire afternoon.
The model
The Temporal Context Model: a drifting context vector is associated with each item, and retrieval reinstates that context, which in turn cues temporally-nearby itemsHoward 2002. Association falls off smoothly with temporal distance.
In AI
engram returned “temporal siblings” — memories formed in the same session — alongside direct recall matches, and boosted the current project’s memories at session start (context-dependent retrieval by working directory); Counterparts generalizes this: memories that come to mind together get a typed edge, and recall spreads activation across those edges. Zep/Graphiti build an explicit temporal knowledge graph; PAM retrieves through temporal co-occurrence.
The map
Temporal association — §103 obvious (Temporal Context Model; PAM).
5 prior-art references
- Howard, Kahana~2002Temporal Context ModelpaperReference ↗
- Park, et al.~2023Generative Agents: Interactive Simulacra of Human BehaviorpaperarXiv ↗
- Samsung~2025KV-cache compression; frequency + recency importance scoringpatentGoogle Patents ↗
- Rasmussen, et al.2025Zep / Graphiti — temporal knowledge-graph memoryossarXiv ↗
- PAM~2026PAM — retrieval through temporal co-occurrencepaperarXiv ↗
1 post-priority (field context, not prior art)
- Mike LaPeter2026CounterpartsossSite ↗
§103-occupied through the Temporal Context Model and graph systems. Rich context reinstatement — reconstructing a whole prior context, not just same-session tagging — is under-built.