---
title: "Get Calibration"
method: GET
path: "/calibration"
---

# Get Calibration

`GET /calibration`

## Request

- Base URL: `https://mcp.physea.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://mcp.physea.ai/calibration`
- Auth: none declared

AAEL Phase-1 gate, made measurable (Constitution §4 rung 9 / §14 row 1): Brier + ECE
over the logged (prediction → independent-verdict) pairs in the sm_records ledger, plus
the per-bin reliability map (the persisted-as-reference calibration map). Reads the
ledger; never fires the model. n=0 until rows accrue.

`qtype` selects which prediction class to score: "route" = execution/research rows
(world:spine / world:web verdicts); "answer" = the proposer+grader learn-loop rows
(verdict_source=grader:<model>), where the grader's pass/fail IS the `actual` and the
proposer's stated confidence is the forecast — so the learn loop's grades show up here.

## Query parameters

- `qtype` string

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/physea/apis/liminality-router-service.md) · [All operations](https://skmtc.dev/physea/apis/liminality-router-service/llms.txt) · [OpenAPI document](https://skmtc.dev/physea/apis/liminality-router-service/revisions/5f60ddd97544?raw)