---
title: "Compute integrity score"
method: POST
path: "/ai/integrity/compute"
tags: ["AI Intelligence"]
---

# Compute integrity score

`POST /ai/integrity/compute`

## Request

- Base URL: `https://app.arkova.ai/api/v1`
- URL: `https://app.arkova.ai/api/v1/ai/integrity/compute`
- Auth: HTTP bearer

Compute a fraud/integrity score for a credential. Scores below 60 are auto-flagged for review. Gated by ENABLE_AI_FRAUD flag.

## Request body

- object
  - `anchorId` string, uuid, required

## Response `200`

Integrity score with breakdown

- IntegrityResponse
  - `anchorId` string, uuid
  - `overallScore` number: Overall integrity score (0-100)
  - `flagged` boolean: True if score < 60 (auto-flagged for review)
  - `breakdown` object
    - `duplicateScore` number: Similarity to existing credentials (lower = more unique)
    - `metadataScore` number: Metadata completeness and consistency
    - `issuerScore` number: Issuer verification confidence

## Other responses

- `401`: Authentication required
- `403`: Insufficient permissions
- `404`: Resource not found
- `503`: API not enabled (feature flag off)

---

[API](https://skmtc.dev/arkova/apis/arkova-verification-api.md) · [All operations](https://skmtc.dev/arkova/apis/arkova-verification-api/llms.txt) · [OpenAPI document](https://skmtc.dev/arkova/apis/arkova-verification-api/revisions/a14858d1efd4?raw)