This review concerns the dataset and R code that the authors made available via the Figshare repository. The repository includes the relevant data and R scripts. However, several critical elements are missing or require clarification before this repository can be considered complete and ready for publication.

Metadata
- the repository includes three identical files ("xxx_metadata.txt"), all similar to the README.docx file in the subfolder "Final_Code_attach", which appears to be an error. I recommend keeping just one 'README.txt' file in the main folder.
- the README should also provide detailed guidance on which scripts to run and in what order, referencing the exact file names and locations. To make this easier, I suggest including a master script that: loads all required packages, sets the working directory, and sources the necessary scripts in the correct sequence.
- a clear data dictionary is currently missing. This should be added either within the README or as a separate file. It should provide descriptions of each column in the data file(s), including data types and units where applicable.
- I appreciate that the authors included R version and some package information. However, several packages used (particularly those used for figures) are not listed. A complete list of all packages and versions used across the scripts should be included.

Data Files
- the file predctions_categorical_grouped.csv was not in the repository, or at least I could not find it. If this file is an output of the model, it should be generated by one of the scripts. Again, the README should clarify which scripts produce which outputs and in what order to execute them.

• the script Sharecode_legacy_CDD.R uses the file path "./data/Seedling_data_2m_share.csv". However, this path does not match the file structure found in the Figshare repository. To prevent execution errors, the directory structure referenced in the scripts should match the structure in the repository precisely.

I recommend the authors revise the Figshare repository to include all missing files, provide clearer metadata and execution instructions, and ensure internal consistency between code and file structure.