Bugfixes and consistency improvements

[psaegert]

No description provided.

[Copilot]

Pull request overview

This PR updates default parameter values for the refiner component and improves documentation consistency. The key changes are: (1) increasing the default n_restarts from 1 to 8 for better optimization reliability, (2) switching the default noise distribution from uniform to normal with corresponding kwargs, and (3) enhancing project metadata and documentation.

• Changed default n_restarts from 1 to 8 across refiner and model classes
• Updated default refiner_p0_noise_kwargs from {'low': -5, 'high': 5} (uniform) to {'loc': 0.0, 'scale': 5.0} (normal)
• Bumped version to 0.4.5 and expanded pyproject.toml metadata with keywords, classifiers, and URLs

Reviewed changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
src/flash_ansr/refine.py	Updated default n_restarts parameter from 1 to 8 in the fit method
src/flash_ansr/flash_ansr.py	Updated docstrings and default refiner_p0_noise_kwargs to use normal distribution parameters; updated load method default n_restarts to 8
src/flash_ansr/baselines/skeleton_pool_model.py	Updated default refiner_p0_noise_kwargs to use normal distribution parameters
src/flash_ansr/baselines/brute_force_model.py	Updated default refiner_p0_noise_kwargs to use normal distribution parameters
pyproject.toml	Bumped version to 0.4.5; added keywords, classifiers, and additional project URLs; improved project description
docs/training.md	Added helper scripts section with brief documentation
docs/index.md	Updated example code to use explicit n_restarts=8 and improved code formatting
docs/getting_started.md	Updated example code to use explicit n_restarts=8 and improved code formatting
docs/evaluation.md	Streamlined evaluation documentation, reorganized content into clearer sections
README.md	Updated project title to "Fast Amortized Neural Symbolic Regression" and bumped version to 0.4.5

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.