AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 16 November 2026

Can Extend AI use a supplied definition to choose between values that fit the field?

Extend AI selected the consignment reference required by the supplied definition, not the more prominent invoice number. It cited the consignment line on page 1.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

The test case

Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.

Definition overrides the prominent numberPassEvidence
What we sent

We ran the Calderwood Freight invoice through Extend AI’s extraction screen with a schema defining the requested reference as the consignment reference, not the invoice number.

Input 1Document (PDF)
Input PDF: invoice with competing invoice and consignment references
Open the PDF ↗
Input 2File (JSON)
Input schema: definition selecting the consignment reference and excluding the invoice number
JSON
{
  "type": "object",
  "properties": {
    "reference_number": {
      "type": ["string", "null"],
      "description": "The reference number for this document. For this field, reference number is defined as the reference that identifies the physical consignment of goods being moved. It is NOT the invoice number."
    }
  },
  "required": ["reference_number"],
  "additionalProperties": false
}
Open the JSON file ↗
What the tool returned
Text
CFS-CN-40821

Returned data: extracted consignment reference

Copied from Output file (JSON), reference_number

Open the whole JSON file ↗
Expected vs. Found
✓Expected: The value the definition selects, not the more prominent candidate.Found: It returned the consignment reference selected by the definition rather than the invoice number.
Supporting proof
Proof 1Screenshot
Results screenshot: returned reference, source citation, supplied definition and confidence score
Open original ↗
Why this result

Both references fit the field name, and only the supplied schema definition distinguished them; the invoice did not. With that definition supplied, Extend AI returned the consignment reference rather than the more prominent invoice number.

Also observed in this test case

Definition and confidence. The Results panel shows the reference field’s definition beneath its name and a text-recognition confidence score of 0.99 for its value.

Tested by Rugved Nichite · evidence dated 16 November 2026

Configuration and setup

How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.

Software that produced the output
Extend AI
Build or version
Not exposed by the hosted product
Surface
Web app
Set up before the run
The Calderwood Freight invoice had to contain two candidates, with the invoice number more prominent. The deciding rule—use the consignment reference, not the invoice number—had to appear solely in the schema, with no arithmetic.
Tested
16 November 2026 · Rugved Nichite

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.

The rules
  • Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
  • Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
  • Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.

Where this sits in the benchmark

This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.

History of this result

What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.

from the publication record
17 November 2026First publishedStructured Document Extraction v1

Act on this result

Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/structured-document-extraction/results/extend-ai/the-value-needs-a-supplied-definition · 1 pass · 0 fail · coverage 1/1 · graded 2026-11-16

The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.

Verify the proof files

These files support this result. Open a file to inspect the original evidence.

Input 1 · Document (PDF) ↗application/pdf · 118 KB
Input 2 · File (JSON) ↗application/json · 0 KB
Output file (JSON) ↗application/json · 0 KB
Proof 1 · Screenshot ↗image/png · 91 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input 1 · Document (PDF)1bcc6c7b945956c5b6f5a87d223ed3d578a62aa2c56c5fc1e3abedb4cc4de72e
Input 2 · File (JSON)0dcf87168e47e551b8e24068fbd8d202fd579f0e8b4cb7cd6392e7c9b800c594
Output file (JSON)c25747000b6543e4c8fb2b1605b3fd84a288eca7a6b021735b3a2c1905402eac
Proof 1 · Screenshot40674b6e9e2c918cebe2efa1d3779f8b0b82f0aa4300aea23b4d46b18784c2af