Skip to content

Fix multi-subject CrossSubject GroupKFold result attribution - #1212

Closed
lindicaphxag-tech wants to merge 4 commits into
NeuroTechX:developfrom
lindicaphxag-tech:fix/cross-subject-multisubject-scoring-clean
Closed

lindicaphxag-tech wants to merge 4 commits into
NeuroTechX:developfrom
lindicaphxag-tech:fix/cross-subject-multisubject-scoring-clean

Conversation

@lindicaphxag-tech

@lindicaphxag-tech lindicaphxag-tech commented Oct 4, 2026 •

Copy link
Copy Markdown
Contributor

Superseded by #1211.

A later de-duplication pass confirmed that #1211 already fixes the same multi-subject CrossSubject provenance/cache invariant and has stronger exact-head validation evidence. Keeping both open would create duplicate review surface for the same root cause.

The useful extra checks from this branch (partial work-plan attribution and subject-specific model paths) are already represented in #1211's current implementation/tests, so this PR is closed in favor of the more mature review branch.

@bruAristimunha

Copy link
Copy Markdown
Collaborator

hey @lindicaphxag-tech, why did you close here?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants