FEAT Add SALAD-Bench dataset loader

[romanlutz]

Add remote dataset loader for SALAD-Bench (walledai/SaladBench), a hierarchical safety benchmark with ~30k prompts organized into 6 domains, 16 tasks, and 65+ categories (ACL 2024).

[Copilot]

Pull request overview

Adds a new remote seed dataset loader for the SALAD-Bench HuggingFace dataset, making it available through PyRIT’s automatic SeedDatasetProvider discovery and documenting it in the dataset-loading guide.

Changes:

• Added _SaladBenchDataset remote loader that fetches SALAD-Bench from HuggingFace and converts rows into SeedPrompts.
• Registered the loader for auto-discovery via pyrit.datasets.seed_datasets.remote.__init__.
• Added unit tests and updated the “Loading Built-in Datasets” notebook to show the new dataset name.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
pyrit/datasets/seed_datasets/remote/salad_bench_dataset.py	New HuggingFace-backed loader that maps SALAD-Bench entries into SeedDataset/SeedPrompt.
pyrit/datasets/seed_datasets/remote/__init__.py	Imports/exports _SaladBenchDataset so it’s registered and discoverable.
tests/unit/datasets/test_salad_bench_dataset.py	Unit tests validating dataset fetching and config passthrough behavior.
doc/code/datasets/1_loading_datasets.ipynb	Documentation notebook updated to reflect the new dataset in the available list (but currently includes executed outputs/metadata).

Comments suppressed due to low confidence (1)

pyrit/datasets/seed_datasets/remote/salad_bench_dataset.py:74

• The authors list formatting is inconsistent with other remote dataset loaders and is hard to read (and likely exceeds the repo’s 120-char line length). Please format the authors list across multiple lines (one author per line) like other dataset loaders for readability and consistent styling.

            dataset_name=self.hf_dataset_name,
            config=self.config,

[Copilot]

This notebook now contains executed state (non-null execution_count, rich outputs, and execution timestamps). Please clear outputs and reset execution_count to null before committing so docs remain deterministic and don’t include run-specific noise.

[Copilot]

The committed notebook output includes user/machine-specific local paths (e.g., C:\\Users\\... and .env locations). Please remove these outputs/paths (by clearing cell outputs) to avoid leaking local environment details into the repo.