docs: #162D certification completion report (NOT_CERTIFIED) - #179
Merged
Conversation
Full operational run: fresh N=100 blind corpus (zero overlap with #162B/#162C on sample IDs and content hashes), dual human review with operator adjudication, labels frozen before reveal, deterministic evaluation. Terminal decision: NOT_CERTIFIED. G0/G1/G5/G6/G7 pass (P0 parity 100%, storage accuracy +11pp with CI [+5,+17]pp, zero false eligibility, zero automatic positives). G2 fails at 14.29% vs 15%; G3/G4 fail because P3's review routing misses the one canonical high-consequence evidence-starved ordinary-kind case (routes defer+no-review where labels require review). Automatic admission: INSUFFICIENT_EVIDENCE, ppv null. Also fixes build_reviewer_b_packet to enumerate packet case order (packets carry no case field).
23 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Completes the operational phase of #176 (#162D): P3 kind-decoupled candidate certification against a fresh N=100 blind corpus.
Terminal decision: NOT_CERTIFIED
The doctrine was frozen and merged (PR #177/#178) before corpus selection; overlap with both spent corpora is zero on sample IDs AND content hashes; labels were frozen before reveal; the runner replayed deterministically. Full evidence in
docs/162d-certification-completion.mdand the content-freecertification-report-162d-v1.json(report digest7d6e593c…).Includes a small fix:
build_reviewer_b_packetenumerated acasefield that production packets do not carry; it now numbers packet order directly (39 tests green, ruff+mypy clean).No production behavior change. Parent #162 remains open.