# Verity Suite Faithful — Faithfulness Checker

> Verity Suite Faithful — Faithfulness Checker is a paid API for AI agents from verity-suite.onrender.com, paid per call via x402, $0.06/call, status unknown (last checked 2026-09-14).

Checks whether a candidate summary or translation faithfully preserves the meaning of a source text, returning a calibrated verdict and claim-level evidence.

## Facts

- Endpoint: POST https://verity-suite.onrender.com/faithful
- Price: $0.06/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-faithful-faithfulness-checker-1ae4f402
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_V_vpddVVFCHqCEZgNbqBr

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-faithful-faithfulness-checker-1ae4f402 -d '<json body>'
```

Example prompt: Check if this summary is faithful to the source article — mode is 'summary'. Source: 'The company reported $4.2B in revenue for Q3, up 12% year-over-year, driven by cloud services.' Candidate: 'The company posted record Q3 revenue of $5B, mostly from cloud.' Flag any hallucinations or dropped claims and give me a faithfulness score.

## When to prefer this

Use this endpoint when an AI agent needs to verify that a generated summary or translation has not hallucinated, omitted material claims, or distorted meaning relative to a known source text. Prefer this over generic LLM self-checks because it is calibrated, fail-closed, and returns structured evidence at the claim level rather than a freeform assessment.

## Known failure modes

- Empty, truncated, or gibberish inputs return verdict 'uncertain' with reasons explaining unreadability
- Texts too misaligned in topic or language to meaningfully compare return 'uncertain'
- A single confirmed factual defect drives faithfulness score well below 0.5 even if most content is accurate
- Missing required 'source' or 'candidate' fields return a 400-level error
- If 'mode' is absent, the stricter union of both summary and translation checks is applied, which may increase false-positive unfaithful verdicts

## How this service works

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

## Output

Returns a verdict ('faithful', 'minor_drift', 'unfaithful', or 'uncertain'), a calibrated faithfulness probability (0–1), and structured arrays listing specific hallucinations (claims in the candidate not supported by the source), omissions (material source claims dropped), and concrete claim-level reasons explaining the assessment. Fails closed — never returns faithful or minor_drift when uncertain.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "source",
  "candidate"
 ],
 "properties": {
  "mode": {
   "type": "string",
   "description": "'summary' or 'translation'. If absent, the checker applies the stricter union of both checks rather than guessing a mode."
  },
  "source": {
   "type": "string",
   "description": "the original source text; the sole ground truth the candidate is judged against"
  },
  "candidate": {
   "type": "string",
   "description": "the summary or translation to check against the source"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "faithful_out",
 "required": [
  "verdict",
  "faithfulness",
  "reasons"
 ],
 "properties": {
  "reasons": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Reasons",
   "description": "concrete claim-level reasons, each either citing a specific source-vs-candidate discrepancy or confirming specific support; at least one reason required"
  },
  "verdict": {
   "enum": [
    "faithful",
    "minor_drift",
    "unfaithful",
    "uncertain"
   ],
   "type": "string",
   "title": "Verdict",
   "description": "faithful=every candidate claim is supported by the source and no material source claim is dropped or distorted; minor_drift=only small non-material omissions/nuance loss that change no core claim, entity, quantity, date, or stance; unfaithful=at least one hallucination, contradiction, negation flip, wrong/invented entity-number-date, dropped material claim, or distortion; uncertain=cannot reliably compare (empty/unreadable/truncated/gibberish input or texts too misaligned to map). FAIL CLOSED: never faithful or minor_drift when unsure."
  },
  "omissions": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Omissions",
   "description": "material claims present in the source but dropped or weakened in the candidate"
  },
  "faithfulness": {
   "type": "number",
   "title": "Faithfulness",
   "maximum": 1,
   "minimum": 0,
   "description": "calibrated probability the candidate fully preserves source meaning with no hallucination, contradiction, or material distortion; 1=certainly faithful, 0=certainly unfaithful. A single confirmed defect drives this well below 0.5."
  },
  "hallucinations": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "title": "Hallucinations",
   "description": "claims asserted in the candidate that are not supported by the source (added or invented content)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/verity-suite-faithful-faithfulness-checker-1ae4f402/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from verity-suite.onrender.com](https://www.zero.xyz/host/verity-suite.onrender.com/llms.txt)