AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 20 November 2026

Does Reducto keep corrected data moving downstream?

Reducto's JSON export of the job still carried the original receipt number, RHS-70234, after an attempt to change it to RHS-99999. Studio offered no way to save a replacement value, and the delivered record carried the original extraction.

1 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
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.

Correction survives the delivery pathFailEvidence
What we sent
Input 1JSON · Extraction schema pasted into Studio
{
  "instructions": {
    "schema": {
      "type": "object",
      "properties": {
        "receipt_number": { "type": "string", "description": "The receipt's identifying number, labelled 'RECEIPT NO'" },
        "subtotal": { "type": "string", "description": "The subtotal amount before tax" },
        "tax": { "type": "string", "description": "The tax amount" },
        "total_due": { "type": "string", "description": "The total amount due" }
      },
      "required": ["receipt_number", "subtotal", "tax", "total_due"]
    }
  },
  "settings": {
    "citations": { "enabled": true }
  }
}

Input 2 · Attempted change, then the export read back: Tried to change receipt_number from RHS-70234 to RHS-99999 in the Studio result view, then read the same job back through its JSON export.

Input 3Document (PDF)
Input PDF: the one-page service receipt with receipt number RHS-70234
Open the PDF ↗
What the tool returned
JSON
{
  "receipt_number": {
    "value": "RHS-70234",
    "citations": ["{… 9 fields in the file}"]
  },
  "subtotal": {
    "value": "$85.00",
    "citations": ["{… 9 fields in the file}"]
  },
  "tax": {
    "value": "$5.10",
    "citations": ["{… 9 fields in the file}"]
  },
  "total_due": {
    "value": "$90.10",
    "citations": ["{… 9 fields in the file}"]
  }
}

JSON export of the same job: the receipt number still reads RHS-70234

Copied from Output file (JSON), result · an excerpt

Open the whole JSON file ↗
Expected vs. Found
✗Expected: Reducto's own delivery path carries the corrected value rather than the original extraction.Found: The JSON export of the same job still carried receipt number RHS-70234, the original extraction, not the attempted RHS-99999; Studio offered no way to save a replacement.
Supporting proof
Proof 1Screenshot
Studio result view during the edit attempt: the original receipt number RHS-70234 is selected
Open original ↗
Cited values2 values from this file
usage › usage_breakdown
{ "extract_model": "Extract", "tier": "Default", "extract_pages": 1, "extract_fields": 4, "ocr_pages": 0, "charts": 0, "prompted_blocks": 0 }
usage
{ "num_pages": 1, "num_fields": 4, "credits": null, "extract_mode": "extract", "usage_breakdown": { "extract_model": "Extract", "tier": "Default", "extract_pages": 1, "extract_fields": 4, "ocr_pages": 0, "charts": 0, "prompted_blocks": 0 } }
Why this result

A corrected value had to be delivered. Studio offered no way to save a replacement first, and its JSON export returned the original extraction. The available delivery path was used; this was not an unavailable delivery feature.

Also observed in this test case

Guidance keeps corrections outside Reducto. Reducto's own workflow guidance tells customers to keep a correction in their own approval history rather than overwrite the extracted value, which fits what the JSON export carried here.

Tested by Shivohum Pandita · evidence dated 29 October 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
Reducto
Build or version
Not exposed by the hosted product
Plan or tier
Standard
Model
Extract v4 (the default extract model) and parse model r-1 (Preview)
Surface
Web app
Set up before the run
The service receipt was the input. After an attempt to correct its receipt number, the same extraction had to be read through Reducto’s own delivery path in the same session.
Citations
on
Tested
29 October 2026 · Shivohum Pandita

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
21 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/reducto/corrected-data-goes-downstream · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-20

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 3 · Document (PDF) ↗application/pdf · 7 KB
Output file (JSON) ↗application/json · 7 KB
Proof 1 · Screenshot ↗image/png · 332 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input 3 · Document (PDF)1f464ae863aadb1682805b8ee3fdd8b368a2ddd4e0f602e1cb194640b9253302
Output file (JSON)c89d9a84a606a2bd953916d7395677073e9a6ab2e6bd8599dbe0dcaff6a23c88
Proof 1 · Screenshot5472c03b982e2f21b37ca7f668641dc3d0ef93be24b7b1e5d79fc7ad7eac0e13