> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ndi.nace.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Extract response format

> data, fields, citations, and not_found

```json theme={"dark"}
{
  "result_type": "extract",
  "data": { "invoice_number": "INV-1042", "total": null },
  "fields": [
    {
      "path": "/invoice_number",
      "value": "INV-1042",
      "status": "found",
      "confidence": null,
      "citations": [
        {
          "location": { "kind": "page_region", "page": 1, "polygons": [] },
          "source_text": "Invoice INV-1042"
        }
      ]
    },
    {
      "path": "/total",
      "value": null,
      "status": "not_found",
      "citations": []
    }
  ],
  "schema_id": null,
  "schema_version": null,
  "units": 1,
  "warnings": []
}
```

* **`data`** — object shaped by your schema.
* **`fields`** — one entry per schema field. Status is `found`, `not_found`, or `ambiguous`. A missing value is `not_found`, never omitted.
* **`fields[*].citations`** — locations and a short quote. PDF/image citations include a polygon when Parse matched the quote to a layout block.
* **`schema_id` / `schema_version`** — set when you used the registry.
* **`warnings`** — non-fatal notes, such as instructions that no declared field can satisfy.

`instructions` on the request cannot add undeclared result fields.