Can FutureSmart Document Intelligence extract a field by learning from examples?
FutureSmart Document Intelligence did not show learning from examples on this field. It returned the correct label, business, for the unseen invoice in both the seven-document collection and the separate control collection, and it offers no way to supply labeled examples or train from them.
1 of 1 test case failed
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 counts this row.
Rule learned only from labeled examplesFailEvidence
business business
Transcribed from Proof 4 · Screenshot
Transcribed from Proof 3 · Screenshot
Every message the tool sent, in order (2)
- Final response (message 1 of 2)
business
- Final response (message 2 of 2)
business
| ✗ | Expected: The unseen invoice should follow the label pattern shown in the examples.Found: It returned the correct label, business, for the unseen invoice in both collections, including the separate control with no examples, and it has no labeled-example training path. |
The product had to let labeled examples teach the field, but its settings and intake options show no training workflow. The same invoice returned business in the seven-document collection and in the separate one-document control, so the result does not show learning from examples.
Casing matches labels. The labeled examples' values match the capitalized banner text in each file, while the unseen invoice returns lower-case business.
Control matches training. The isolated control and the seven-document collection both return business for the same unseen invoice.
This version cannot separate learning from prior knowledge because the zero-example control still returned business. A later version used a new corpus, and this result was not rerun.
The unseen invoice prints no customer tier value; the correct label comes from the answer key.
One settings capture shows only document type and summary; the knowledge table shows customer tier with 3/3 filled, but that field's description is not shown.
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 row says which 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 row 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 | Training → | |
| Scenario | A field the tool can only get right from examples → | |
| Tool | FutureSmart Document Intelligence → |
Global scenario definition → · Global capability definition →
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.