Availability of generated dataset + missing post_process_scripts/ directory

[hey-Cu]

Hi, thanks for releasing Chimera — really interesting work.

I'm trying to reproduce the paper and do some downstream analysis on the insider-threat dataset Chimera produces. I have two related questions before committing API budget to regenerate everything from scratch:

1. Is the generated dataset released somewhere?

The paper describes using the collected logs as labeled ground-truth data for insider threat detection research. Have you published the dataset used in the NDSS 2026 paper (the logs / CERT-format features produced by your runs) — e.g., on Zenodo, HuggingFace, or a SharePoint link similar to the one in zips/download.txt (which currently only hosts the patched OWL/Camel frameworks)?

Even a single representative scenario (the medical-institution 2-week run, for example) would let people benchmark detection methods against your ground truth without re-running the full simulation.

2. post_process_scripts/ referenced in README but missing from the repo

The "Repository Structure" section of README.md lists:

post_process_scripts/ # Jupyter notebooks and scripts for dataset post-processing

and the "Log Collection" section mentions post-processing extracts structured features (logon events, file operations, HTTP traffic, emails) to match CERT dataset format. However, this directory is not present in the repository (only referenced in .gitignore). Is it planned to be added, or is it available separately?

Thanks in advance!