An orchard-blight pair is scored two ways. A/B would ask which variant wins on F1. Testers instead want disagreements on odd leaf edges as defect clues. Which technique should they pick?

A/B would ask which blight variant wins on F1. Testers who want disagreements on odd leaf edges as defect clues should pick back-to-back testing, especially on unusual inputs. Sequential testing stops a statistical pile early, and a framework suitability review checks the toolkit, not the leaf edges.