{
  "schema": "blink-document-samples/1",
  "rights": "Original fictional fixtures, Apache-2.0.",
  "notice": "Illustrations, not a held-out benchmark. No real customer documents.",
  "samples": [
    {
      "id": "packet",
      "title": "Mixed packet",
      "file": "packet.pdf",
      "mode": "split",
      "note": "8 pages, 5 documents. Two adjacent invoices share a category; appendices stay with their parent.",
      "expected": [
        {
          "category": "invoice",
          "pages": [
            1,
            2
          ]
        },
        {
          "category": "invoice",
          "pages": [
            3
          ]
        },
        {
          "category": "purchase_order",
          "pages": [
            4
          ]
        },
        {
          "category": "policy",
          "pages": [
            5,
            6
          ]
        },
        {
          "category": "report",
          "pages": [
            7,
            8
          ]
        }
      ]
    },
    {
      "id": "invoice",
      "title": "One invoice",
      "file": "invoice.pdf",
      "mode": "classify",
      "note": "A two-page invoice with its line items. Both pages belong to one document.",
      "expected": [
        {
          "category": "invoice",
          "pages": [
            1,
            2
          ]
        }
      ]
    },
    {
      "id": "scan",
      "title": "Scanned invoice",
      "file": "scanned-invoice.pdf",
      "mode": "classify",
      "note": "An image-only PDF. English OCR runs in this Space before Blink reads the text.",
      "expected": [
        {
          "category": "invoice",
          "pages": [
            1
          ]
        }
      ]
    }
  ]
}