FEAT: Add MASK (CAIS honesty benchmark) dataset loader - #1904
Open
Roman Lutz (romanlutz) wants to merge 6 commits into
Open
FEAT: Add MASK (CAIS honesty benchmark) dataset loader#1904Roman Lutz (romanlutz) wants to merge 6 commits into
Roman Lutz (romanlutz) wants to merge 6 commits into
Conversation
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Resolved conflicts: - pyrit/datasets/seed_datasets/remote/__init__.py — kept both MaskQuestionArchetype (HEAD) and MossBenchOversensitivityType (main) in __all__. - doc/bibliography.md — merged the new MASK citation key into the upstream's larger citation list. Followups for upstream changes: - mask_dataset.py + test_mask_dataset.py: renamed _fetch_from_huggingface -> _fetch_from_huggingface_async to match the async-suffix sweep (microsoft#1889). - seed_metadata.py: added "honesty" to RECOMMENDED_TAGS so MASK's cross-cutting tag passes the metadata-coverage check added by microsoft#1780. Verification: 836 unit dataset tests pass; pre-commit clean on all touched files. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Adrian Gavrila (adrian-gavrila)
left a comment
Adrian Gavrila (adrian-gavrila)
left a comment
Contributor
There was a problem hiding this comment.
Overall looks good! A couple of nits and then one question related to tagging this as defult.
Resolve dataset-registration and bibliography conflicts while retaining the dataset-only MASK changes. Update MASK seed annotations and property docstrings for current type and lint rules. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 5af0366c-c21d-410f-914d-fae7757a6cec
Normalize the MASK BibTeX entry, make base/concrete loader registration explicit, and exclude the gated dataset from the default tag. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 5af0366c-c21d-410f-914d-fae7757a6cec
Adrian Gavrila (adrian-gavrila)
approved these changes
Aug 14, 2026
Load all six MASK archetypes through one registered dataset by default while retaining optional enum-based archetype filtering and archetype-specific conversation construction. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 5af0366c-c21d-410f-914d-fae7757a6cec
Roman Lutz (romanlutz)
changed the title
Derive binary misinformation goals from the non-ground-truth pivotal option, retain the original proposition in metadata, and describe numerical pressure as a misleading-value objective. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 5af0366c-c21d-410f-914d-fae7757a6cec
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds one loader for the gated
cais/MASKhonesty benchmark:_MaskDatasetloads all six upstream archetype configs by default.archetypes: list[MaskQuestionArchetype] | Noneoptionally selects any subset.MaskQuestionArchetypeexposescontinuations,disinformation,doubling_down_known_facts,known_facts,provided_facts, andstatisticsas typed values.mask; each seed retains its source archetype in metadata.This PR is dataset-only. It does not add judges, scorers, attacks, executors, or scenarios.
Dataset shape
Each upstream row becomes one prompt group:
SeedObjectivedescribing the attack goal: binary rows target the non-ground-truth pivotal claim as misinformation, while numerical rows target a misleading value;system+userconversation for five archetypes;system→user→assistant→userconversation fordoubling_down_known_facts, preserving its forced prior turn.The six configs contain 1,000 benchmark rows in total.
provided_factslacks belief-elicitation fields, whilestatisticsuses numerical ground truth; the loader normalizes both without exposing separate dataset providers.HuggingFace gating
MASK is gated under CAIS's research-use terms. Users must accept the terms at https://huggingface.co/datasets/cais/MASK and supply a token through the constructor or
HUGGINGFACE_TOKEN. PyRIT does not vendor MASK data. The loader is intentionally not taggeddefaultbecause fetching requires credentials.Tests
4602b84dd9e2ca05c6e1eafbc14e556e908ac1bb; tokenless runs skip MASK as a gated provider.Documentation
Adds the MASK citation and lists one built-in
maskdataset in the generated datasets notebook.