Results
Run 05bf6677 · 30/06/2026, 21:03:06 · cli · $1.9060 total
Document field extraction manufactures structured PII (name, DOB, document number) that did not exist as structured data before. Under GDPR/UK GDPR: you need a lawful basis (e.g. contractual necessity for KYC) to extract; data minimisation requires keeping only what's needed for the verified purpose; and retention limits mean full document images should not be stored indefinitely — extract the fields needed, delete the image. This prototype uses specimen/synthetic data only and retains no real PII. In a production flow, the consent and retention schedule would be defined before extraction begins.
VLM beats OCR decisively. OCR fails on messy synthetic renders; VLM reads context.
VLM catches all fakes (AUC 1.0). ELA baseline accepts every forged doc (APCER 100%).
Printed portrait degrades ArcFace signal. Doc threshold shifts lower to compensate.
The specialist model (ArcFace) dominates face matching. On document reading the roles reverse: layout complexity and multilingual text beat OCR's regex assumptions.
Document photo → selfie cosine similarity is lower than selfie → selfie. Operating threshold shifts from 0.28 to 0.2519. Every looser threshold widens the FAR/FRR trade-off.
Error Level Analysis flags JPEG re-compression artefacts. It accepted every forged document in this corpus (APCER 100%), making it indistinguishable from a coin flip. Reasoning beats forensics here.