Holograin: Detecting Documents Redrawn by AI
Holograin is our detector for scanned documents and photos redrawn by an AI image generator. It catches 90% of AI-edited pages after upload while flagging 1 genuine page in 100. This is how it compares with frontier LLMs and open AI-image detectors.
Greg T
A Deepfake Can Look Real. It Still Has to Be True.
A forger can wash away every trace of how a document was made: print it, rescan it, regenerate it with an image model. What the document claims survives the wash, and a claim can be checked. Here is how we check those claims, where our own checks burned us first, and the two numbers that keep us honest.
Greg T
Forest and the case for treating the decision as infrastructure, not an inbox
Forest made the case that OCR deserves to be treated as infrastructure rather than a commodity. This is the companion argument from upstream: the layer that receives the data deserves the same seriousness, because a perfectly extracted figure can still wait three days, get approved by the wrong person, and leave no record that it happened.
Greg T
Forest
BenchmarkThe Bank Statement Extraction Benchmark
A real-world benchmark for bank-statement transaction extraction. holofin clears 98% of statements with zero errors. Frontier LLMs read almost every row, but on a minority of layouts they hand back rows that aren't on the page — unpredictably — so a model that's 90% accurate per row returns a fully-correct statement only ~75–80% of the time.
Holofin Engineering
Your Table Extractor Passed. The Numbers Didn't.
An auditor opens your extraction output for a balance sheet. The model reports 99.2% cell accuracy. Impressive. Then she totals the asset column by hand, the way auditors do, and it comes to a number that is off by one row. Assets no longer equal liabilities plus equity. The statement does not close.
Greg T
Document Fraud Detection: What a PDF Can't Hide
We used to think document fraud was a visual problem. Wrong fonts. Misaligned columns. A logo that felt slightly off. We built checks around what humans see, because what humans see is all we had.
Greg T
When Documents Fight Back
Page 1: Account summary, two columns. Page 15: Same account, three columns, different header names. Page 47: A scan with a coffee stain. Page 89: The totals page, which references transactions you extracted 70 pages ago.
Greg T
The Invisible Audit Trail
An auditor opens your export file, finds a closing balance of €47,500, and pulls up the source PDF. Page 3, bottom-right corner: €47,000. Different number. "Where does the difference come from? Who changed it?"
Greg T
HoloRecall: Show, Don't Tell
There's a moment in every classification project where you watch the model confidently get something wrong. Not a hard case. Not an ambiguous edge. Something a human would solve in half a second without thinking.
Greg T