List Ground Truth Datasets

List Ground Truth datasets with GET /v1/validation/ground-truth. Each holds verified document-field pairs that benchmark runs score extraction accuracy against.

This namespace is Benchmarks (the /v1/validation namespace): measuring how accurately a completed job run extracted data, by comparing its output against manually verified expected values. It is not the in-pipeline validation checks (see the Structuring API) that gate individual results before delivery — those keep the Validation name. GET /v1/validation/ground-truth lists the Ground Truth datasets those accuracy measurements run against.

A Ground Truth dataset is a collection of manually verified document-field value pairs that serve as the benchmark for accuracy measurement. API payloads reference it through the legacy golden_sample_id field name. Each dataset can be scoped to a specific schema via user_schema_id, or left unscoped for cross-schema benchmarking. Datasets are curated in the Talonic platform; through the public API you list them, inspect their expected values, delete them, and run benchmarks against them.

Response

{
  "data": [
    {
      "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "name": "Invoice Validation Set",
      "user_schema_id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
      "entry_count": 50,
      "created_at": "2024-08-01T00:00:00.000Z",
      "updated_at": "2024-08-01T00:00:00.000Z",
      "links": {
        "self": "/v1/validation/ground-truth/a1b2c3d4-e5f6-7890-abcd-ef1234567890"
      }
    }
  ]
}

Errors