title: "{{DATASET_NAME}} — Dataset Card" status: draft updated: {{DATE}} tags: [dataset]
{{DATASET_NAME}}¶
Paths and versions
Access & licensing (DUA, contacts, HF mirrors)
Sample sizes, subset breakdowns, and inclusion criteria
Base-pair / modality-specific statistics (e.g., total bp, TR windows)
Modality column map (per-modality feature names + schema refs)
Overlap logic and subject linking
QC thresholds and preprocessing
Linked assets
- External repos used (e.g., external_repos/caduceus)
- Walkthroughs covering extraction/validation
Available covariates
Notes and caveats