This is a rejoinder to the reply by Yang Bao, Bin Ke, Bin Li, Y. Julia Yu, and Jie Zhang to my article “Critique of an Article on Machine Learning in the Detection of Accounting Fraud,” published in Econ Journal Watch in March 2021. Here I explain why the authors’ reply did not address the fundamental issue raised in my critique, which asked for a reasonable justification as to why fraud identifiers were changed for select observations in the sample—a choice that was undisclosed in the original publication, and one that contradicted the logic presented in their paper. That change was critical. Without it, their publication failed to improve upon prior literature in the detection of accounting fraud.