What's Semantic Memory?

The distinction that changes everything.

In 1972, cognitive psychologist Endel Tulving proposed two types of memory. This distinction is the foundation for everything we build.

See the Architecture →

Explore

↓

The Distinction That Changes Everything

In 1972, cognitive psychologist Endel Tulving proposed a distinction that would reshape our understanding of human memory. He argued that we don't have one memory system—we have at least two: episodic memory (events) and semantic memory (meaning).

Endel Tulving, 1972

Semantic memory remembers meaning, not events, knowledge detached from the episode of learning it. You know that Paris is in France, but you don't remember the moment you learned it. The fact is just... known.

Tulving, 1972

episodic_memory:

what: Remembers events, episodes, specific experiences

example: I remember learning about Paris in third grade

storage: Timestamped records of experiences

semantic_memory:

what: Remembers meaning, knowledge detached from episodes

example: Paris is in France

storage: Verified facts, independent of when learned

Episodic memory is "I remember when I learned this." Semantic memory is "I just know this."

Most AI systems have only episodic memory. They store documents with timestamps. They retrieve based on similarity. They have no concept of what's true—only what was stored.

The Irony of "Semantic" Search

The AI industry is obsessed with 'semantic search,' 'semantic similarity,' 'semantic embeddings.' But most AI memory systems are episodic, not semantic. They use semantic similarity for retrieval while operating as episodic storage. They find things that sound like what you asked for. They don't know what's true.

Tulving/Quillian parallel, 1972

Most AI systems have only episodic memory. They store documents with timestamps. They retrieve based on similarity to stored records. They have no concept of what's true, only what was stored.

The AI industry is obsessed with "semantic search," "semantic similarity," "semantic embeddings." But most AI memory systems are episodic, not semantic.

They use semantic similarity for retrieval while operating as episodic storage. They find things that sound like what you asked for. They don't know what's true.

RAG doesn't fix this. Retrieval-Augmented Generation finds documents. It doesn't verify claims. It doesn't know which document is current.

It just finds things.

Organizations Don't Have Semantic Memory

Truth fragments when stored in multiple systems. When your sepsis protocol was updated but your nursing manual wasn't, your organization doesn't know the current protocol. It has two conflicting episodic records, and no semantic memory to resolve them.

AI can generate unlimited content from your knowledge base. If your knowledge base is wrong, AI generates unlimited wrong content. The verification bottleneck that slowed human authors now paralyzes AI-assisted workflows.

Your organization's knowledge lives in documents. Documents are episodic records—they capture what was written, when it was written, not what's true.

Your sepsis protocol was updated last quarter. The nursing manual wasn't. Both exist. Both get retrieved.

Which one is current?

The system doesn't know. It can't know. Documents don't carry expiration dates.

AI amplifies this problem. AI can generate unlimited content from your knowledge base. If your knowledge base is wrong, AI generates unlimited wrong content. The verification bottleneck that slowed human authors now paralyzes AI-assisted workflows.

What Semantic Memory Systems Actually Build

semantic_memory_architecture:

canonical_claims:

what: Verified assertions with ownership

example: Return policy: 30 days apparel, 60 days electronics

verification_upstream:

what: Human verification happens once, at the source

example: Operations Manager verifies return policy claim

derivation:

what: Documents generate from claims, not authored independently

example: Receipts, website, training materials all derive from return policy claim

knowing_boundaries:

what: Systems distinguish what they know vs don't know

example: AI says 'I don't know' instead of hallucinating

Four principles. One architecture. Systems that remember meaning, not episodes.

The Consciousness Parallel

There's a parallel in consciousness research. Tulving called it noetic consciousness—the awareness that you know something, independent of remembering when you learned it.

Organizations need this shift. From "I remember storing this document" to "I know this claim is true."

From episodic records to semantic knowledge.

This Site Is Built This Way

This site is built this way. The claims on this site aren't scattered across independent pages. They exist as canonical assertions in a structured knowledge base. The pages you see are derived from those claims. When we update a canonical claim, every page that references it can update.

The claims on this site aren't scattered across independent pages. They exist as canonical assertions in canonical/SMS-CLAIMS.json. The pages you see are derived from those claims.

When we update a canonical claim, every page that references it can update. This page demonstrates the methodology it describes.

Who Needs This?

Not every organization needs semantic memory architecture.

You need it if:

Truth matters (compliance, safety, accuracy)
You generate multiple outputs from the same knowledge (policies, training, chatbots, FAQs)
Verification is worth the upfront cost (because downstream maintenance disappears)

You don't need it if:

Content is disposable (marketing copy, blog posts)
Single output (one document, never reused)
Verification cost exceeds drift cost (rare, but possible)

The Claim Beneath the Claim

Semantic Memory Systems establish canonical truth, verify at the source, generate from verified claims, and stop when they are uncertain. They don't chase perfect recall. They remember what matters.

Start a Conversation →