A dependency-free (pure standard-library) Python tool that runs the golden-reference regression SUITE this article describes — distinct from 5.5's single-build gate. It loads a FROZEN baseline (the golden master: per-clip, per-rendition VMAF mean and 5th percentile blessed when the suite was created) and a candidate build, and for each reference clip it (1) compares the candidate to the frozen baseline within a NOISE-SIZED tolerance band computed per clip — margin = z * sqrt(model_sigma^2 + run_
Download free PDF
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
This golden-reference regression suite compares each new encoder build against a frozen baseline per clip and rendition, flagging mean and 5th-percentile drops. Our seven-volume handbook covers the video stack; Volume 1 is the place to start for quality metrics, encoder settings and artifacts, with Volume 3 on ABR and QoE and Volume 6 on AI models. Written by Nikolay Sapunov, CEO at Fora Soft.
Worried a new encoder build will quietly lower quality in production?
Share your encoding pipeline and test clips, and we will set up a regression suite and thresholds your CI can run on every build. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
