# Verity Suite – Cite Pro (Citation Finder)

> Verity Suite – Cite Pro (Citation Finder) is a paid API for AI agents from suite.veritylayer.dev, paid per call via x402, $0.35/call, status unknown (last checked 2026-09-14).

Given a factual statement, finds and returns calibrated supporting citations with a verdict on how well the sources establish the claim.

## Facts

- Endpoint: POST https://suite.veritylayer.dev/cite/pro
- Price: $0.35/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/verity-suite-cite-pro-citation-finder-275dd063
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jW70wbh7jV9nvuK0Uk_U0

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability verity-suite-cite-pro-citation-finder-275dd063 -d '<json body>'
```

Example prompt: Find me citations supporting the claim 'moderate aerobic exercise reduces systolic blood pressure by an average of 5–8 mmHg in adults with hypertension' — focus the search on clinical literature and give me a calibrated verdict on how strongly the sources establish it.

## When to prefer this

Choose this endpoint when an AI agent needs a calibrated, sourced verdict on a specific factual claim — especially in high-stakes contexts like medical, legal, financial, or scientific content where hallucination risk must be mitigated. Prefer this over generic web search when you need a structured support score, explicit rejection reasoning, and an optional cryptographically signed receipt for auditability. Best suited for single, well-formed declarative statements rather than open-ended research queries.

## Known failure modes

- Statement is too vague or ambiguous for source retrieval — low support score with explanatory reasons
- No relevant sources found — verdict returns not_supported with score near 0
- Domain hint narrows search too aggressively, missing relevant sources
- Statement contains multiple sub-claims — only partial coverage, reflected in caveats
- Sources retrieved contradict the claim — verdict returns contradicted
- Signing not configured — receipt field returns null
- Input exceeds 2000 character limit — validation error

## How this service works

The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.

## Output

Returns a verdict enum (supported, partially_supported, not_supported, or contradicted), a calibrated 0–1 support score indicating how strongly retrieved sources establish the statement, a list of citations, concrete reasons for the verdict including why any candidate sources were rejected, optional caveats about scope or recency, and an optional Ed25519-signed VerityLayer receipt for cryptographic provenance.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "statement": {
   "type": "string",
   "title": "Statement",
   "maxLength": 2000,
   "minLength": 1,
   "description": "the factual claim to find supporting sources for"
  },
  "domain_hint": {
   "anyOf": [
    {
     "type": "string",
     "maxLength": 2000
    },
    {
     "type": "null"
    }
   ],
   "title": "Domain Hint",
   "default": null,
   "description": "optional topic/field to focus the search (e.g. 'clinical', 'tax law')"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-cite-pro-citation-finder-275dd063/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from suite.veritylayer.dev](https://www.zero.xyz/host/suite.veritylayer.dev/llms.txt)