Cell-sim contest winner admits its method is a denoised weighted mean, 2× over baseline

anshulkundaje · x · 2026-11-20

The author of the winning Arc Institute cell-simulation contest entry explains that at its core the method is a denoised weighted mean achieving roughly 2× the performance of a simple mean. Stanford professor Anshul Kundaje pushes back: such a baseline shortcut's effectiveness is entirely a function of train-test similarity and shouldn't count as a real "cell simulator."

Related event: Stanford professor challenges Arc virtual cell challenge winner: data privilege or methodological edge(18 posts)→

Original post →

More from Research

Research channel →