Metadata-Version: 2.4
Name: refereekit
Version: 0.0.1
Summary: A command-line toolkit for refereeing a paper: it verifies every page and equation a review cites against the submitted PDF, and drafts the report and editor letter in your voice. Placeholder; not yet released.
Author: Tzu-Chi Yen
License-Expression: MIT
Classifier: Development Status :: 1 - Planning
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# refereekit

refereekit is a command-line toolkit for refereeing a paper. It ingests the
submitted PDF, verifies every page and equation anchor a review cites
against that PDF, and drafts a referee report and an editor letter, in a
voice guide you supply, for you to edit. The verdict stays yours, and a
manuscript under review goes only to a model backend you have attested
keeps nothing.

This is a placeholder release that reserves the name. Version 0.0.1 contains
no functionality; the first real release will follow.

## Citation

If you use refereekit in your research, please cite the following paper:

```bibtex
@inproceedings{yen2026models,
    title={Models Quote, Code Verifies, Referees Judge: When the Verifier Is the Weak Link},
    author={Tzu-Chi Yen},
    booktitle={NeurIPS 2026 Workshop on AI-Native Academia},
    year={2026},
    url={https://openreview.net/forum?id=k3FgymBG6u}
}
```
