Real production, not a demo set.
The documents are scans from real supplier and carrier flows, in all their variety: degraded or skewed scans, handwritten annotations (3,899 documents flagged), international consignment notes in foreign languages (1,475), stamps and carbon copies. They have been processed on the server installed at the customer’s site since September 1, 2026. The visuals published on this site are synthetic samples: no real document is shown.
Documents processed with no human touch.
This rate rises with use. Every human validation or correction is a time-stamped verdict that teaches the system the layout: one verdict immediately re-adjudicates the documents of the same layout still pending — a median of 197 documents per verdict; on September 1, 11 verdicts validated 1,022 documents in one go. The 1.4% “validated after correction” are exactly that: a few dozen human corrections, 2,819 documents learned. For audit, 1.5% of the documents validated automatically are re-served to a person.
Against human-verified ground truth, field by field.
Counting rule: a field is correct if its value, once normalized (case, accents, whitespace, ISO date), is identical to the one established by a human annotator. Three levels are published, from the most demanding to the floor.
1 · Documents validated automatically, acceptance set with human-verified ground truth (September 2026)
| Field | Accuracy | Documents |
|---|---|---|
| Issuer | 99.4% | 336 documents |
| Date | 98.9% | 285 documents |
| Document number | 94.4% | 285 documents |
| Full core (number + date + issuer all correct together) | 92.9% | 336 documents |
Document type is measured separately: the annotator’s taxonomy is finer than the engine’s, so the gap is one of vocabulary, not of reading. Simulated final accuracy across the whole flow, strict policy: 95.0% (± 0.8) on 700 documents.
2 · Issuers never seen during training (1,000 documents, 127 issuers, July 2026)
| Field | Accuracy |
|---|---|
| Document number | 96.4% |
| Date | 97.2% |
| Issuer | 87.7% on the raw read · 97.9% after the resolution layer |
3 · Floor: the reading service alone, with no layout memory and no resolution (63,838 documents, July 2026)
| Field | Accuracy |
|---|---|
| Document number | 97.7% |
| Date | 97.5% |
| Document type | 95.3% |
| Issuer | 94.3% |
| Consignee | 94.2% |
On the clean subset of this sweep (38,849 documents), the four fields number, type, date and issuer are all correct together on 90.6% of documents.
On the baseline deployment, at the customer’s site.
Baseline configuration: one Ubuntu server, 12 cores, 64 GB of memory, one server-class GPU, database on the same server, no inbound connection. An outage of the reading service loses nothing: documents wait and are caught up on restart.
The only number that matters: the one on your documents.
A few hundred real documents, in the variety of your flows: your big suppliers and your small ones, the clean ones and the damaged ones.
Same fields, same counting rule, same confidence threshold. Field-level results, with the list of cases sent for validation.
The pilot sets the measured target for go-live. If your documents are not a fit, we tell you before, not after.
About the measurement.
Why publish all this rather than a single percentage?
Because a percentage on its own says nothing about which fields, which documents, or how many human validations. Two engines both advertised “at 99%” can behave very differently on unknown issuers or damaged scans. The method makes the figure comparable and verifiable — and it is the one we replay on your documents.
What is the difference between “documents validated” and “accuracy”?
The first measures what operations actually live with: the share of documents that go through the pipeline — with no intervention, or validated in bulk after a person corrected a layout once. The second measures, field by field, whether the extracted value is identical to the ground truth established by a human annotator. Both are published; neither is enough on its own.
Are the measurements taken on documents never seen before?
Yes, for two sets: 1,000 documents from 127 issuers absent from training, and an acceptance set of 697 documents with human-verified ground truth. The sweep of 63,838 documents measures the floor of the reading service alone across the whole flow.
What happens on uncertain fields?
Every field carries a confidence score; below the threshold, the document is validated with a reservation or sent to a person. The principle is never to guess silently: a flagged error costs one validation, a silent error costs a dispute. Every human correction immediately re-adjudicates the documents of the same layout still in the queue.
Can I run the test on my own delivery notes?
Yes. Send us a representative sample — a few hundred documents is enough — and we return field-level results, with the cases sent for validation. It is the starting point of every project.
Do you publish the processing speed?
Yes: 10,216 documents per hour on average over a full campaign, 7,788 in instantaneous steady state, on the baseline deployment installed at the customer’s site (one server, one server-class GPU).