fix(evals): harden H1 methods and add synthetic QA pack#53
Merged
Conversation
ernestprovo23
changed the title
ernestprovo23
marked this pull request as ready for review
July 19, 2026 00:07
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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\n- harden DSE-708 paid-study provenance, blocked randomization, grading, blinding, and receipt accounting\n- bind confirmatory decisions to frozen study evidence with task-clustered quality analysis\n- enforce separate single-model latency baseline, spend, reliability, and grader-completeness gates\n- use Bonferroni simultaneous one-sided bounds for the three secondary guardrails\n- add a balanced 24-task open-book synthetic QA fixture pack for harness validation\n\n## Evidence\n- 638 tests passed\n- Ruff check and format check passed\n- git diff --check passed\n- Gitleaks scanned 106 commits; no leaks found\n- multiple independent methods reviews completed; final rereview pending\n\n## Boundaries\n- stacked on draft PR #52; PR #51 remains the H0 prerequisite\n- no provider calls were made\n- committed keys are synthetic fixtures and are not valid paid-pilot evidence\n- a paid pilot requires separately access-controlled grader keys with a frozen pre-execution hash and an explicitly approved spend ceiling\n- confirmatory GO/REDESIGN/KILL remains prohibited until preregistered held-out evidence exists\n\nLinear: DSE-708