# Citation Evidence API

> Citation Evidence API is a paid API for AI agents from dependency-truth.inboxtzdjqv.workers.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-30).

Fetches a public URL and checks whether specified phrases appear in its content, returning metadata and a content hash for citation verification

## Facts

- Endpoint: POST https://dependency-truth.inboxtzdjqv.workers.dev/v1/citation-evidence?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/citation-evidence-api-657afb29
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_y8YZ8NtQqk5blqI306YXX

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 citation-evidence-api-657afb29 -d '<json body>'
```

Example prompt: Can you check whether the page at https://example.com/paper actually contains the phrase 'statistically significant results' and the phrase 'peer reviewed' — I need to verify my citation before I publish?

## When to prefer this

Use this endpoint when an AI agent needs to deterministically verify that a cited URL actually contains specific text, especially in research, fact-checking, or automated content pipelines where provenance integrity matters. Prefer it over general web scrapers when you need both phrase-level citation checking and a content fingerprint (SHA-256) in a single pay-per-call call with no subscription required.

## Known failure modes

- URL is unreachable or returns non-200 status — status field reflects the error code
- Private or authenticated URLs return access-denied content without the expected phrases
- Page content is dynamically rendered via JavaScript and text is not present in the raw HTML fetch
- Phrase matching may be case-sensitive or whitespace-sensitive, causing false negatives for reformatted text
- Request times out for slow or large pages
- More than 10 phrases submitted — input rejected at validation

## How this service works

Deterministic package, repository, security, and citation evidence APIs payable per call with x402.

## Output

A JSON object containing the page URL, title, HTTP status code, fetch timestamp, a SHA-256 hash of the fetched content, and an array of phrase-check results each indicating whether the specified phrase was found present or absent in the page content.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public HTTP(S) URL"
  },
  "phrases": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 10
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://example.com",
  "title": "Example Domain",
  "status": 200,
  "fetchedAt": "...",
  "phraseChecks": [
   {
    "phrase": "Example Domain",
    "present": true
   }
  ],
  "contentSha256": "..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/citation-evidence-api-657afb29/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from dependency-truth.inboxtzdjqv.workers.dev](https://www.zero.xyz/host/dependency-truth.inboxtzdjqv.workers.dev/llms.txt)