Ghost Sas

Model · Object detection

docverify-yolo-fields

Ghost Sas

Finds the 10 fields of a French payslip so that an edit found by the tamper model can be pinned to net pay or gross salary instead of "pixels at (812, 640)". In docverify, an edit inside a money field is what turns a page into high risk. Part of docverify: project · netpaye (net pay) · brut (gross salary) · salairebase (base salary) · netavantimpot (net before tax) · cotisations (total contributions) · test pages, scans and phone photos mixed. 19 ms per page on a T4; part of the 6.7 s full pipeline on 4 CPU threads. Synthetic French payslips only (generated, fake people and companies); other layouts need their own field list. AGPL-3.0, inherited from Ultralytics YOLO. The rest of docverify…

Model · Image segmentation

docverify

Ghost Sas

A forensic segmentation network that finds where a payslip was edited — copy-move, splice from another document, or a re-typed amount — and the small models and thresholds that turn its pixel map into a verdict an analyst can act on. Part of docverify, a complete system with arithmetic checks, PDF forensics and a local LLM note: TamperNet (~33M parameters): a pretrained ConvNeXt encoder on RGB, plus two forensic inputs — fixed SRM noise residual filters (edits break the sensor/print noise) and a JPEG/DCT branch (a pasted region carries its own 8×8 compression grid) — fused into a U-Net-style decoder that outputs one logit per pixel. The page score is the mean of the top-200 pixel logits.…