Require holdout and MSRE eCPS wins#246
Merged
Merged
Conversation
MaxGhenis
force-pushed
the
codex/ecps-holdout-msre-gate-20260606
branch
from
cffa309 to
6cea1bf
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Why
The clean-surface rollback showed that a candidate can be unsafe even when other content gates pass. The release gate should enforce the actual promotion rule: MP must beat production eCPS on full loss, holdout loss, and unweighted MSRE using the frozen benchmark evidence.
Tests
uv run ruff format src/microplex_us/pipelines/mp300k_artifact_gates.py tests/pipelines/test_mp300k_artifact_gates.pyuv run ruff check src/microplex_us/pipelines/mp300k_artifact_gates.py tests/pipelines/test_mp300k_artifact_gates.pyuv run --extra dev --extra policyengine python -m pytest -q tests/pipelines/test_mp300k_artifact_gates.py