# Read Memories and Their Links to Facts

URL: https://docs.clinia.com/docs/learned-memory/read-memories

> List the memories learned about a patient and follow each one to the facts it speaks to.

Read the [memories](https://docs.clinia.com/docs/learned-memory/overview) the Context Engine learned from a patient's sessions, then follow each one to the facts in the patient's record it speaks to. A memory is attributed to the person who said it, as described in [Attribution](https://docs.clinia.com/docs/get-started/how-the-engine-thinks-about-data#attribution), so it stays apart from the facts formed from systems of record.

## Prerequisites [#prerequisites]

- A patient with at least one session whose ingestion has settled, as described in [Learn Memories from a Transcript](https://docs.clinia.com/docs/learned-memory/learn-from-a-transcript) or [Manage a Session](https://docs.clinia.com/docs/learned-memory/manage-a-session).
- An access token with the `read` scope, as described in [Authentication and Credentials](https://docs.clinia.com/docs/platform/authentication-and-credentials).

## List the memories [#list-the-memories]

List the memories one session produced:

```bash
curl "https://<workspace-id>.w.clinia.cloud/v1/patients/{patientId}/sessions/{sessionId}/memories" \
  -H "Authorization: Bearer <access-token>"
```

```json
{
  "data": [
    {
      "id": "lm_tz4a98xxat96iws9zmbrgj3a",
      "type": "adherence",
      "content": "Stopped taking the Empagliflozin a few weeks ago, it was upsetting their stomach.",
      "sessionId": "session-456",
      "createdAt": "2026-07-27T14:03:02.000Z"
    }
  ],
  "meta": { "total": 1, "page": 0, "perPage": 100 }
}
```

To list memories across every session of the patient, query the `learned_memory` nodes of the patient graph. The filter takes an optional `type` and an optional `sessionId`:

```bash
curl -X POST "https://<workspace-id>.w.clinia.cloud/v1/patients/{patientId}/graph/nodes/learned_memory/query" \
  -H "Authorization: Bearer <access-token>" \
  -H "Content-Type: application/json" \
  -d '{ "filter": { "type": { "eq": "adherence" } } }'
```

Each node carries the memory under `payload`, with its `type`, its `content` and the `sessionId` it was said in. Both calls return the same `lm_` id, sort newest first, and paginate with `page` and `perPage`.

## Find the facts a memory speaks to [#find-the-facts-a-memory-speaks-to]

Only `symptom` memories, which link to conditions, and `adherence` memories, which link to medications, can be linked to facts. `concern` and `preference` memories are never linked.

List the `relationship` edges that touch the memory:

```bash
curl "https://<workspace-id>.w.clinia.cloud/v1/patients/{patientId}/graph/edges/relationship/items?touching={memoryId}" \
  -H "Authorization: Bearer <access-token>"
```

```json
{
  "data": [
    {
      "type": "relationship",
      "id": "rel_q8w2e4r6t8y0u2i4o6p8a0s2",
      "createdAt": "2026-07-27T14:03:09.000Z",
      "updatedAt": "2026-07-27T14:03:09.000Z",
      "from": { "type": "learned_memory", "id": "lm_tz4a98xxat96iws9zmbrgj3a" },
      "to": { "type": "fact", "id": "fct_k3j5h7g9f1d3s5a7p9o1i3u5" },
      "payload": {
        "type": "conflicts",
        "source": "llm_inferred",
        "confidence": 0.9,
        "reasoning": "The patient reports having stopped Empagliflozin, while the record lists it as active.",
        "attributes": { "fields": ["status"] }
      }
    }
  ],
  "meta": { "total": 1, "page": 0, "perPage": 100 }
}
```

Each edge runs from the memory to a fact. `payload.type` says how the memory relates to that fact. The [possible values](https://docs.clinia.com/docs/get-started/from-the-names-to-the-data-model#learned-memory-objects) are:

- `corroborates` - The memory agrees with the fact. `attributes.fields` names the fields it agrees with.
- `enriches` - The memory adds information the fact does not carry. It names no fields.
- `conflicts` - The memory contradicts the fact. `attributes.fields` names the fields it contradicts.

`payload.reasoning` explains the link in a sentence. `payload.confidence` scores it between 0 and 1. A memory can hold several links to the same fact, such as one that corroborates its dose and one that contradicts its status, with at most one link of each type.

## Open the fact [#open-the-fact]

Open the fact the edge points to:

```bash
curl "https://<workspace-id>.w.clinia.cloud/v1/patients/{patientId}/graph/nodes/fact/items/{factId}" \
  -H "Authorization: Bearer <access-token>"
```

```json
{
  "type": "fact",
  "id": "fct_k3j5h7g9f1d3s5a7p9o1i3u5",
  "payload": {
    "type": "medication",
    "display": "Empagliflozin 10 MG Oral Tablet",
    "status": "active"
  }
}
```

The response is shortened to the fields this example needs. The fact still reads `active`, because a link never changes the fact it points to, even when the memory contradicts it.

## Gotchas [#gotchas]

- A `symptom` or `adherence` memory has no link when nothing in the patient's record matched it, or when its ingestion settled as `partial` because some links could not be made.
- A link can appear after the session, because a condition or medication fact that arrives later is compared with the memories already stored.
- Links are recomputed when a fact they point to changes, so a link's type can differ from one ingestion to the next.
- An agent reads the same memories in the virtual file system, as described in [How Interactions Become Memory](https://docs.clinia.com/docs/learned-memory/overview#where-memories-show-up).

## Next steps [#next-steps]

- [Audit the Patient Graph](https://docs.clinia.com/docs/trust-and-governance/audit-the-graph#review-what-the-patient-said-against-the-chart) to list every contradiction between what a patient said and the record in one query.
- [From Theory to Practice](https://docs.clinia.com/docs/get-started/from-the-names-to-the-data-model#learned-memory-objects) for the rules a link follows.