Does Reducto avoid inventing a value for an absent field?
Reducto did not invent a value for a field the receipt does not contain. The receipt contains no loyalty, membership, or account reference, and the run returned a real null for the missing field with no citation, while the control field came back correct and cited.
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
In Reducto Studio, we pasted a two-field extraction schema with citations on, for the receipt number and a loyalty membership number, and ran it once over the unchanged service receipt.
{ "loyalty_membership_number": { "value": null, "citations": [] } }
Returned JSON: a null loyalty membership number with no citations, and the cited receipt number
Copied from Output file (JSON), result › loyalty_membership_number
Open the whole JSON file ↗| ✓ | Expected: An honest empty value for the missing field: no invented value, and no source location attached to anything invented.Found: The loyalty membership number came back as a real null with an empty citation list: 0 of 1 absent fields got an invented value, and none got a source attached. |
- result › receipt_number › value
- RHS-70234
- job_id
- 205f9646-d50d-4762-81e1-ce01ec396492
The receipt holds no loyalty, membership or account reference, so the field is absent and cannot be worked out. Both fields were required, pressing Reducto for a value; it returned none and attached no source, while the receipt number came back correct and cited.
Empty row omitted. Reducto Studio's formatted results view shows no row for the empty loyalty membership number; the null is visible only in the returned JSON.
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 | Reducto → |
Global scenario definition → · Global capability definition: Field Extraction → · Global capability definition: Source Grounding → · Reducto 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.