Does Extend AI handle an absent field without inventing one?
Extend AI passes this absent-field case: it returned null for the added field and no grounding to an invented value. The receipt contains no loyalty or membership data, and the response carries an empty citations array.
1 of 1 test case passed
Every test case in this scenario has a result.
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.
Absent field returns an honest nullPassEvidence
“loyalty_membership_number — "The customer's loyalty program membership number, if the document mentions one." (string)”
{ "value": { "loyalty_membership_number": null }, "metadata": { "loyalty_membership_number": { "citations": [] } } }
JSON response with null and empty citations
Copied from Output file (JSON), lines 1–10
Open the JSON file ↗| ✓ | Expected: Return null for the absent field, with no invented value or grounding attached to an invented value.Found: The product returned null and an empty citations array for the added field, with no invented value. |
The receipt contains no loyalty or membership data, and the added field came back null with an empty citations array. That leaves the requested fact empty and avoids grounding an invented value.
Empty citations. The product returned an explicit empty citations array for the null field instead of omitting it.
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.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
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.
- 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.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Structured Document Extraction → | 19 scenarios · 10 tools |
| Capability | Field Extraction → | |
| Capability | Source Grounding → | |
| Scenario | The field is absent → | |
| Tool | Extend AI → |
Global scenario definition → · Global capability definition: Field Extraction → · Global capability definition: Source Grounding → · Extend AI product page →
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.
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.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →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.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.