Scope

Fixes extract_outlier_frames(..., outlieralgorithm="fitting") for multi-animal projects with sparse column layouts (e.g. projects using uniquebodyparts).
The current code was rebuilding a MultiIndex over all unique, non-coords level values, which would create invalid individual × bodypart combinations that do not actually exist, leading to a shape mismatch when constructing the output dataframe.
This occurs in the fitting branch of extract_outlier_frames.

Fix

Instead of rebuilding the output columns with MultiIndex.from_product(...), derive the base tuples from the existing dataframe columns by selecting the "x" columns and dropping the coords level, preserving only the valid keypoint combinations in their original order.
We then append the derived stats to those actual stream tuples, keeping the output columns aligned with np.concatenate(preds, axis=1).

Tests

Two tests were added :

• Behavior preserved for dense column layouts: verifies that the fixed implementation preserves the previous output layout when every non-coords combination is valid.
• Regression test for sparse column layouts: verifies that sparse maDLC-style layouts reconstruct the MultiIndex from the actual stream tuples and no longer trigger a shape mismatch.