# SourceMint Claim Verification

> SourceMint Claim Verification is a paid API for AI agents from sourcemint-api.nap6281.chatgpt.site, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Verifies whether a textual claim is consistent with the content of one or more provided source URLs, returning a verdict, confidence score, and cryptographic proof bundle.

## Facts

- Endpoint: POST https://sourcemint-api.nap6281.chatgpt.site/api/verify-claim
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sourcemint-claim-verification-a458a31f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FOc7U4eRr9nDR7NRWxW5h

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 sourcemint-claim-verification-a458a31f -d '<json body>'
```

Example prompt: Can you verify whether the claim 'Renewable energy accounted for over 30% of global electricity in 2023' is actually supported by the content at these two URLs: https://iea.org/reports/renewables-2023 and https://ourworldindata.org/renewable-energy? Give me a verdict and confidence score.

## When to prefer this

Choose this endpoint when you need to programmatically verify whether a specific textual claim is supported or contradicted by the actual content of one or more web pages, especially when you require a cryptographic proof bundle (SHA-256) for auditability. Prefer it over generic web scraping when the goal is claim-level consistency checking rather than raw content extraction, and when you need a structured verdict with a confidence score rather than raw text. It is especially valuable for citation auditing in research, journalism, or compliance workflows where provenance must be demonstrated.

## Known failure modes

- Source URL is inaccessible or returns a non-200 status — sources array may be empty and verdict may be 'unverifiable'
- Claim is ambiguous or too vague for meaningful comparison — low confidence score returned
- Source page content is behind a login or paywall — extraction fails, source omitted from proof
- Malformed or missing required fields (urls or claim) — HTTP 4xx validation error
- Network timeout on source fetch — partial results or error response
- Confidence score near 0.5 indicates insufficient evidence either way

## How this service works

Wallet-native x402 APIs for web extraction, claim verification, and citation auditing.

## Output

Returns a JSON object containing: the original claim, a verdict string (e.g. 'consistent', 'inconsistent', 'unverifiable'), a confidence score between 0 and 1, a list of source entries analyzed, and a proof bundle with a SHA-256 hash for cryptographic auditability.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "urls",
  "claim"
 ],
 "properties": {
  "urls": {
   "type": "array",
   "description": "Public source URLs"
  },
  "claim": {
   "type": "string",
   "description": "Claim to compare with the supplied sources"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "claim": "Example claim",
  "proof": {
   "bundleSha256": "0000000000000000000000000000000000000000000000000000000000000000"
  },
  "sources": [],
  "verdict": "consistent",
  "confidence": 0.75
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sourcemint-claim-verification-a458a31f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sourcemint-api.nap6281.chatgpt.site](https://www.zero.xyz/host/sourcemint-api.nap6281.chatgpt.site/llms.txt)