Telling cause from effect from purely observational data, focusing on pairs of variables (X, Y), was introduced as a challenge at the NIPS 2008 workshop on causality. The basic scenario is: given independent and identically distributed (i.i.d.) observations $(x_1, y_1), \dots, (x_k, y_k)$ drawn from a distribution $P_{X,Y}$, infer whether $X$ causes $Y$ or $Y$ causes $X$, given the promise that exactly one is true. The NIPS 2013 challenge extended this to three classes: X rightarrow Y, Y rightarrow X, or a null class consisting of either the independent case $X \perp Y$ or the pure confounding case X leftrightarrow Y (shorthand for X leftarrow H rightarrow Y, where $H$ is an unobserved confounder).