Field Extraction
Returns the scalar fields the schema asks for — present, interpreted, derived, absent or differently laid out — correctly typed.
What this capability means
Given a user-defined schema, the tool must return the requested scalar field value from the document correctly typed. That includes values that are directly present, need the schema’s definition, must be derived from other values, or appear in a different layout. If the field is absent, it should not invent one.
Boundary: This does not judge transcription quality or scan reading; those are separate concerns.
Scenarios that test this capability
A scenario is a real-world situation used to test a capability.
The value is directly available
Scenario
The value must be derived
Scenario
The same field across layouts
Scenario
The field is absent
Scenario
Benchmarks that include this capability
A capability has global identity and may be used by more than one benchmark.
Structured Document Extraction
Which document extraction platform turns a user-defined schema into correct structured records — across layouts, scans and repeated sets — and is honest about what it could not find?