# 402oracle Claim Verifier

> 402oracle Claim Verifier is a paid API for AI agents from 402oracle.com, paid per call via x402, $0.25/call, status unknown (last checked 2026-09-13).

Fact-checks a single factual claim against live web evidence and returns a signed verdict (supported/contradicted/insufficient), confidence score, and citations.

## Facts

- Endpoint: POST https://402oracle.com/verify/claim
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/402oracle-claim-verifier-a022bb6f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bQga6DxhuI-SNz5kr9UyZ

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 402oracle-claim-verifier-a022bb6f -d '<json body>'
```

Example prompt: Before we use this in the report, can you fact-check the claim 'The global electric vehicle market surpassed 10 million units sold in 2022' against current web evidence and tell me whether it's supported, contradicted, or inconclusive — with a confidence score and sources?

## When to prefer this

Choose this endpoint when your agent needs a signed, auditable fact-check of a specific textual claim before acting on it — especially before making payments, publishing content, or relying on a statistic. Prefer it over general-purpose web search when you need a structured verdict plus citations in a single atomic call, and when the attestation (signed output) matters for downstream trust or audit trails.

## Known failure modes

- Claim text is too vague or ambiguous for the system to locate relevant evidence — returns insufficient verdict
- Claim is about highly recent events with no indexed web evidence yet — may return insufficient
- Conflicting web sources may yield a low confidence score with a supported or contradicted verdict
- Malformed or empty claim text returns a validation error
- Payment failure (insufficient USDC) blocks the request entirely
- Rate limiting or service unavailability returns a 5xx error

## How this service works

Fact-check a single factual claim against web evidence before your agent relies on it. A fact-checking oracle and hallucination guard: returns a verdict (supported / contradicted / insufficient), a confidence score, and citations, as a signed attestation.

## Output

A signed attestation object containing: a verdict string (supported, contradicted, or insufficient), a numeric confidence score (0–1), and an array of citations (URLs and excerpts) from web evidence that informed the verdict.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "claim": {
   "type": "string",
   "description": "A single factual claim, 8-600 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "signature": {
   "alg": "ES256",
   "jwks": "/.well-known/jwks.json"
  },
  "attestation": {
   "type": "claim_verification",
   "result": {
    "verdict": "supported",
    "citations": [
     "https://example.com/about"
    ]
   },
   "subject": {
    "claim": "Company X was founded in 2019."
   },
   "confidence": 0.8
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/402oracle-claim-verifier-a022bb6f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 402oracle.com](https://www.zero.xyz/host/402oracle.com/llms.txt)