# Return Reason Exact Normalised Duplicate Audit

> Return Reason Exact Normalised Duplicate Audit is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Audits up to 200 labelled return-reason text records to detect exact normalised duplicates within the supplied dataset.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-sector-ml-return-reason-duplicates?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/return-reason-exact-normalised-duplicate-audit-d35eb2c3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-CZRx-vex3q2zYUngpVqJ

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 return-reason-exact-normalised-duplicate-audit-d35eb2c3 -d '<json body>'
```

Example prompt: Can you audit my return reason dataset for exact normalised duplicates? I have about 50 labelled records — each with an ID, the customer's return text, and the actual category (damaged, wrong_item, unwanted, or other) — and I want to know which ones are exact matches after normalisation.

## When to prefer this

Choose this endpoint when you need a lightweight, deterministic exact-normalised duplicate check on a small batch (up to 200 records) of labelled return-reason text data, particularly before training a classifier or validating annotation quality. It is not a semantic similarity or fuzzy deduplication tool — it only catches exact matches after normalisation. Prefer it over general-purpose deduplication tools when your data specifically uses the return-reason label schema (damaged, wrong_item, unwanted, other) and you want a bounded, low-cost ($0.01 USDC) deliverable with no model training involved.

## Known failure modes

- Fewer than 2 records submitted — minimum record count not met
- More than 200 records submitted — exceeds maximum batch size
- Missing required fields (id, text, or actual) on one or more records
- Invalid enum value for 'actual' field (must be damaged, wrong_item, unwanted, or other)
- Record ID exceeds 80 characters or text exceeds 1000 characters
- Payment not fulfilled via x402 protocol — request rejected

## How this service works

Return reason - Exact normalised duplicate audit: Exact normalised duplicate audit for Return reason. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or foundation-model training. One of 25 profiles or calculations across 20 shared operations in this sector. 0.01 USDC includes one bounded exact normalised duplicate audit deliverable.

## Output

A duplicate audit report identifying which of the supplied labelled return-reason text records are exact normalised duplicates, including their IDs and relevant match details, bounded to the submitted batch of up to 200 records.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "records": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id",
     "text",
     "actual"
    ],
    "properties": {
     "id": {
      "type": "string",
      "default": "",
      "maxLength": 80,
      "minLength": 1
     },
     "text": {
      "type": "string",
      "default": "",
      "maxLength": 1000
     },
     "actual": {
      "enum": [
       "damaged",
       "wrong_item",
       "unwanted",
       "other"
      ],
      "type": "string"
     }
    },
    "additionalProperties": false
   },
   "default": [
    {
     "id": "example-0-0",
     "text": "damaged sample document number 0 for this supplied dataset.",
     "actual": "damaged"
    },
    {
     "id": "example-0-1",
     "text": "damaged sample document number 1 for this supplied dataset.",
     "actual": "damaged"
    },
    {
     "id": "example-0-2",
     "text": "damaged sample document number 2 for this supplied dataset.",
     "actual": "damaged"
    },
    {
     "id": "example-1-0",
     "text": "wrong_item sample document number 0 for this supplied dataset.",
     "actual": "wrong_item"
    },
    {
     "id": "example-1-1",
     "text": "wrong_item sample document number 1 for this supplied dataset.",
     "actual": "wrong_item"
    },
    {
     "id": "example-1-2",
     "text": "wrong_item sample document number 2 for this supplied dataset.",
     "actual": "wrong_item"
    },
    {
     "id": "example-2-0",
     "text": "unwanted sample document number 0 for this supplied dataset.",
     "actual": "unwanted"
    },
    {
     "id": "example-2-1",
     "text": "unwanted sample document number 1 for this supplied dataset.",
     "actual": "unwanted"
    },
    {
     "id": "example-2-2",
     "text": "unwanted sample document number 2 for this supplied dataset.",
     "actual": "unwanted"
    },
    {
     "id": "example-3-0",
     "text": "other sample document number 0 for this supplied dataset.",
     "actual": "other"
    },
    {
     "id": "example-3-1",
     "text": "other sample document number 1 for this supplied dataset.",
     "actual": "other"
    },
    {
     "id": "example-3-2",
     "text": "other sample document number 2 for this supplied dataset.",
     "actual": "other"
    }
   ],
   "maxItems": 200,
   "minItems": 2
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/return-reason-exact-normalised-duplicate-audit-d35eb2c3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from market.datapackvibe.com](https://www.zero.xyz/host/market.datapackvibe.com/llms.txt)