Modelling the density \(p(x)\) by probabilistic generative models is an intuitive way to detect out-of-distribution (OOD) data, but it fails in the deep learning context. In this paper, we list some falsehoods that machine learning researchers believe about density-based OOD detection. Many recent works have proposed likelihood-ratio-based methods to `fix' this issue. We propose a framework, the OOD proxy framework, to unify these methods, and we argue that likelihood ratio is a principled method for OOD detection and not a mere `fix'. Finally, we discuss the relationship between domain detection and semantics.