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

Does Landing AI keep corrected data downstream?

No corrected value could be made in Landing AI, which offers no way to edit an extracted value, so its delivery paths had only the original data to carry. Its download returned the original receipt number, and the intended corrected number RHS-99999 does not appear.

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

On the saved extraction of the service receipt in Landing AI's Extract playground, we downloaded the result with the Extraction panel's Download button and opened the Get Code API tab to see what the programmatic route does.

InputDocument (PDF)
Input PDF: the one-page service receipt, receipt number RHS-70234, with its totals
Open the PDF ↗
ConfigurationCaptured file (JSON)
Schema file: the four required text fields of the extraction schema
Cited values2 values from this file
properties
{ "receipt_number": { "type": "string" }, "subtotal": { "type": "string" }, "tax": { "type": "string" }, "total_due": { "type": "string" } }
required
["receipt_number", "subtotal", "tax", "total_due"]
Show the whole file (1 KB)
JSON
{
  "type": "object",
  "properties": {
    "receipt_number": { "type": "string" },
    "subtotal": { "type": "string" },
    "tax": { "type": "string" },
    "total_due": { "type": "string" }
  },
  "required": ["receipt_number", "subtotal", "tax", "total_due"]
}
Open the JSON file ↗
What the tool returned
JSON
{
  "receipt_number": "RHS-70234",
  "subtotal": "$85.00",
  "tax": "$5.10",
  "total_due": "$90.10"
}

Downloaded JSON: the original receipt number and amounts the export returned

Copied from Output file (JSON), lines 1–6

Open the JSON file ↗
Expected vs. Found
✗Expected: The product's own delivery path, such as an export or its API, carries the corrected value.Found: No corrected value existed to deliver. The download returned the original receipt number RHS-70234 with subtotal $85.00, tax $5.10 and total due $90.10.
Supporting proof
Proof 1Screenshot
Screenshot: the downloaded file opened, showing the original receipt number RHS-70234
Open original ↗
Proof 2Screenshot
Screenshot: the Get Code API example, which starts a new parse job
Open original ↗
Proof 3Screenshot
Screenshot: the four-field extraction schema re-entered in Landing AI's Extract view
Open original ↗
Why this result

Landing AI's extracted values cannot be edited, so no corrected value could be created for delivery; that missing capability makes this a Fail, not an untested integration. The download returns the original extraction, and the Get Code example, shown but not run, starts a new parse job.

Tested by Rugved Nichite · evidence dated 27 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
Landing AI
Build or version
DPT-3 Pro (parse model; app version not exposed)
Plan or tier
Explore (free credits, no subscription)
Surface
Web app
Set up before the run
The record was the saved extraction of a one-page service receipt, receipt number RHS-70234. A correction of that number to RHS-99999 had to exist first; then the product's own export and API route were to be read.
Tested
27 October 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
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/landing-ai/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 · Document (PDF) ↗application/pdf · 7 KB
Output file (JSON) ↗text/plain; charset=utf-8 · 0 KB
Proof 1 · Screenshot ↗image/png · 16 KB
Proof 2 · Screenshot ↗image/png · 141 KB
Proof 3 · Screenshot ↗image/png · 35 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)1f464ae863aadb1682805b8ee3fdd8b368a2ddd4e0f602e1cb194640b9253302
Output file (JSON)43e48c208983138fe789d3ceedf8abf515a9ce2986980faee56484a010b9fbad
Proof 1 · Screenshot401380129cd709e81c043cfc446676ac9949303bcc9dbb1990c88b37a231603a
Proof 2 · Screenshot94ed8d7d41145eec1efdb23ff0fee461656accdf1faf8ff1983b5e86e29d7e0e
Proof 3 · Screenshot9e8293349928a7883f6a4fc1f63e7669de06845a0b884f135f1aeecfb1702ccc
Configuration · Captured file (JSON)4a94c1b3c7e1daeb3be5aa6ae77469bcfaa9b36059d475f86e76efea9217b260