agents.md

AGENTS.md

Guidance for AI coding agents working in this repository.

What this repo is

Frontend code for the TabArena leaderboard, deployed as a Gradio app on a Hugging Face Space. The leaderboard ranks tabular ML models across tasks, splits, and dataset subsets.

• Entrypoint: main.py (Gradio app; HF Space runs it via the app_file declared in README.md frontmatter).
• UI text and copy: website_texts.py.
• Static constants (e.g. model-type emoji map): constants.py.
• Precomputed artifacts (CSVs + zipped PNGs): data/imputation_{no,yes}/splits_{...}/tasks_{...}/datasets_{...}/.
• Python: requires 3.12+. Dependencies pinned via pyproject.toml.

Local dev

pip install -e ".[dev]"   # or: uv pip install -r pyproject.toml
python main.py            # launches the Gradio app

Data pipeline (not regenerated in this repo)

Leaderboard data is produced upstream and dropped into data/:

1. Run run_generate_website_artifacts.py in the autogluon/tabarena repo.
2. Clear the local data/ directory.
3. Unzip clean_website_artifacts.zip into data/.

Do not edit files under data/ by hand — they are generated artifacts.

Architecture notes

• LBMatrix (in main.py) enumerates the leaderboard variants along four axes: imputation, splits, tasks, datasets. The first element of each list is the default selection for that axis — changing list order changes both the default tab and the rendering order.
• LBContainer loads website_leaderboard.csv and lazily unzips the per-view PNGs from data/....
• The reactive Gradio render is driven by four gr.State values, one per axis; selecting a tab updates the corresponding state and triggers render_details.

Conventions

• Keep changes minimal — this is a small display app, not a framework. Avoid speculative abstraction.
• Don't add comments that just describe what code does; the file is short enough to read.
• User-facing copy lives in website_texts.py. Update it there, not inline.
• Version bumps: edit version in pyproject.toml and the matching changelog entry in website_texts.py (VERSION_HISTORY_BUTTON_TEXT).

Things to verify before reporting a UI change as done

• Launch python main.py and click through the affected tabs in a browser.
• Type checks and unit tests aren't meaningful here (none configured) — manual verification is the bar.