Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -714,3 +714,22 @@ data/eval/instances.json the 30 cases with human labels results
trajectories/<run>/ one .jsonl + rendered .md per instance REPRODUCE.md
```

---

## Citation

If you use fairtask — the screening pipeline, the evaluation set, or the audit findings — please cite:

```bibtex
@software{kaparos2026fairtask,
author = {Kaparos, Manos},
title = {fairtask: evidence-verified fairness screening for SWE-bench-style coding tasks},
year = {2026},
month = aug,
version = {0.1.1},
url = {https://github.com/mnkprs/fairtask},
note = {Agent pipeline with a deterministic evidence verifier, evaluated against OpenAI's
SWE-bench Verified human annotations. micro1 Agentic Workflows Hackathon submission.}
}
```