Inconsistency in CPT

Originally reported on Google Code with ID 9

Consider the following CPT example in Leapp;

x = ?:(1/3)
y = ?:(1/4)
z1 = ?! ( ~x & ~y -> ?:(1/5),
          ~x &  y -> ?:(1/7),
           x & ~y -> ?:(1/2),
           x &  y -> ?:(1/2))

Notice that z1 is independent of y when x is true (i.e. "context-specific Independence").

Then, It seems natural to factor out the two last entries as

z2 = ?! ( ~x & ~y -> ?:(1/5),
          ~x &  y -> ?:(1/7),
           x      -> ?:(1/2))

However the two distributions unexpectedly differ:

lea> :@ z1
61/210
lea> :@ z2
139/630

z1 is right while z2 is wrong.

Reported by pde@n-side.com on 2015-02-21 11:46:12

Comments (2)