Episodic & semantic memory
"I met her on Tuesday" slowly becomes "I know her" — the event fades, the meaning stays.
Contested — Whether gist is compressed episodic detail or an independent multi-trace abstraction is unresolved.
the episode
- whenTuesday, 3:14 pm
- detailshe ordered an oat-milk flat white
- whereCafé Luna, 2nd Ave
- topictalked about the Montana trip
- eventcoffee with Sarah
the gist
- Sarah — a friend.
- You get coffee together.
- She's easy to talk to.
In the brain
Two systems, first distinguished by Tulving: episodic memory holds specific events (“I met her Tuesday”); semantic memory holds general knowledge (“I know her”)Tulving 1972. Over time, repeated episodes shed their verbatim detail and leave gist — Fuzzy-Trace Theory holds the two as parallel traces, the verbatim one fading fasterBrainerd 2002.
Whether semantic memory is just compressed episodes or a separate abstraction is unsettled.
The model
Verbatim-to-gist degradation: detailed traces decay quickly while the extracted meaning persists. You keep “we argued about consciousness” long after the exact words are gone. Consolidation is the process that does the distilling.
In AI
engram tagged each memory episodic or semantic and, during consolidation, compressed aging episodics into semantic gist with a small model; Counterparts keeps the split but promotes a memory to the semantic band on strength alone, with no model in the loop, and merged memories are born semantic. Microsoft’s layered working/episodic/collective memory and Alai Vault’s episodic/semantic tiers cover the split. One honest caveat: real semantic memory is gist across many episodes, not one old episode squeezed down.
The map
Episodic→semantic degradation — §103 exposed (Alai Vault, US20250371317A1).
7 prior-art references
- ServiceNow2018Focused conversation context management; overlay context from stored episodespatentGoogle Patents ↗
- Alai Vault LLC (Smith Lewis, Harlow)2023Biologically-inspired memory: power decay of salience, episodic/semantic tiers, agent memory toolpatentGoogle Patents ↗
- Shinn, et al.2023Reflexion: Language Agents with Verbal Reinforcement LearningpaperarXiv ↗
- Packer, et al.2023MemGPT: Towards LLMs as Operating SystemspaperarXiv ↗
- Navinfo Europe~2024Catastrophic forgetting + episodic/semantic (neural-net training)patentGoogle Patents ↗
- Microsoft2024Layered working/episodic/collective memory; embedding-compressed historypatentGoogle Patents ↗
- Microsoft~2024Semantic memory vector-DB consolidation; DBSCAN clustering; age/effectiveness selectionpatentGoogle Patents ↗
2 post-priority (field context, not prior art)
- HeLa-Mem~2026HeLa-Mem — Hebbian episodic→semantic distillationpaperarXiv ↗
- Mike LaPeter2026CounterpartsossSite ↗
The tiered split is §103-occupied. Distilling gist across many episodes — rather than compressing a single old one — is far less trodden.