This supplementary material provides guidelines and resources for researchers to ensure comprehensive and reproducible reporting in machine learning-based science. It includes detailed instructions for each section of the REFORMS checklist, which aims to enhance the transparency and reliability of scientific claims made using machine learning. The guidelines cover various aspects such as study design, computational reproducibility, data quality, preprocessing, modeling, data leakage, metrics and uncertainty, generalizability, and limitations. Each section provides specific recommendations and references to support researchers in reporting their findings accurately and transparently. Additionally, a table of references is included to provide additional context and examples on reporting quality and problems in scientific literature.This supplementary material provides guidelines and resources for researchers to ensure comprehensive and reproducible reporting in machine learning-based science. It includes detailed instructions for each section of the REFORMS checklist, which aims to enhance the transparency and reliability of scientific claims made using machine learning. The guidelines cover various aspects such as study design, computational reproducibility, data quality, preprocessing, modeling, data leakage, metrics and uncertainty, generalizability, and limitations. Each section provides specific recommendations and references to support researchers in reporting their findings accurately and transparently. Additionally, a table of references is included to provide additional context and examples on reporting quality and problems in scientific literature.