A dependency-light Python script (standard library only) that takes paired objective metric scores and human MOS — optionally with per-clip MOS confidence intervals — and prints the full ITU-T P.1401-style validation report: Pearson PCC, Spearman SROCC, Kendall KROCC, RMSE, and the outlier ratio, with a monotonic mapping applied before the linear statistics (a built-in least-squares fit, or the 5-parameter logistic when SciPy is available). Reads a CSV or runs on a built-in sample dataset, expla
Download free PDF
The handbook · 7 volumes
Fora Soft Video Engineering Handbook
This metric-validation stats calculator turns paired metric scores and MOS into a P.1401-style report with PCC, SROCC, KROCC, RMSE and outlier ratio. Our seven-volume handbook explains the video stack end to end; Volume 1 covers quality metrics and how codecs create artifacts, Volume 6 the AI models behind learned metrics, and Volume 3 QoE monitoring in delivery. Written by Nikolay Sapunov, CEO at Fora Soft.
Validating whether a metric predicts what your viewers actually rate?
Send us your scores and MOS data, and we will run the validation, read the results and say whether the metric is safe to automate decisions on. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
