borg-wrappers: BORG-Guarded Cross-Validation Functions

In BORG: Bounded Outcome Risk Guard for Model Evaluation

BORG-Guarded Cross-Validation Functions

Description

These functions wrap common cross-validation functions from popular ML frameworks, adding automatic BORG validation. They block random CV when data dependencies are detected.

Details

BORG provides guarded versions of:

• borg_vfold_cv(): Wraps rsample::vfold_cv()

• borg_group_vfold_cv(): Wraps rsample::group_vfold_cv()

• borg_initial_split(): Wraps rsample::initial_split()

When dependencies are detected, these functions either:

1. Block the operation and suggest borg_cv() instead

2. Automatically switch to an appropriate blocked CV strategy

Value

No return value. This page documents the family of guarded CV wrapper functions; see individual functions for their return values.

BORG documentation built on March 20, 2026, 5:09 p.m.