Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Identifying conditional independence of variables in graphical models is a key to finding tractable solutions, and faithfulness is a key condition of these relationships. The authors provide necessary and sufficient conditions for determining faithfulness in Gaussian graphical models (based on partitioning variables outside the conditioning set into two disjoint subsets), and show how this theoretical result can be translated into an algorithm for determining if a distribution is faithful. PROS: - Clear, well-written paper with illustrative examples - Addresses a relevant problem and provides a meaningful theoretical result - Provides a practical test for faithfulness in Gaussian graphical model CONS: - Theoretical result is restricted to Gaussian graphical models Quality: This paper provides addresses a theoretical problem (faithfulness in Gaussian graphical models). The claims are well-reasoned and the proofs support the claims. The resulting algorithm provides a useful test of faithfulness.