eval: validate local recurrent competition - #14
Merged
Conversation
production D1由来の新規development/holdout、provenance、contamination audit、gold、6 variantsと二baseline gateを観測前に固定する。局所neighbor/query/path recurrent strategy、diagnostics、tests、requirements、実験手順を同じfreezeへ含める。
freeze後にdevelopmentを一度実行し、全6 variantsと固定gate判定を保存する。候補は0件だったためholdoutを開かず、default維持とtradeoffを文書化する。
lipluscodex
commented
Aug 1, 2026
lipluscodex
left a comment
Member
Author
There was a problem hiding this comment.
自己レビュー: PASS(ブロッカーなし)
受入確認:
- freeze commit
3562c0fにproduction D1由来の新development/holdout、balanced gold、zero-write provenance、contamination audit、6 variants、二baseline gate、実装、tests、requirementsを固定し、result artifactが存在しないことを確認。 - freezeからhead
9cc2b37までcore code、fixture、gold、manifest、provenance、audit tool、requirementsは不変。 - development resultを独立再生成し、保存JSONとbyte一致。
- candidate gate通過は0件、selectionは
current。holdout runnerは固定stop ruleで拒否し、holdout resultを生成しないことを確認。 - 6 variantsすべてでrelation path 3/3とfeedback isolationは成立。local neighbor/pathはrelation MRRを0.5278へ改善したがdirect/negativeが退行し、query追加はcontrol側を回復させる一方relation改善が縮小したため、固定gate不合格は妥当。
- default
current_positive_additiveは不変。 - ローカル42 tests PASS、GitHub CI SUCCESS、PR mergeable CLEAN。
判定区分:
- 今回: マージ可。Issue #13の事前固定実験、陰性結果保存、holdout非開封条件を満たす。
- 後続: 局所化だけではdirect signalを保持できなかったため、seed entry residualを競合外anchorとして保持する別の事前固定ablationが候補。今回のfreeze後に追加しない。
- 受容したトレードオフ: candidate 0件のためholdoutを開かず、defaultを変更しない。未開封holdoutは将来の別プロトコルへ流用せず、Issue #13の凍結artifactとして保持する。
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #13
production D1由来の相互非重複development/holdout、provenance、contamination audit、6 variantsと二baseline gateを観測前に固定し、局所neighbor/query/path recurrent strategyを実装しました。
freeze後のdevelopmentでは候補gate通過が0件だったためholdoutを開かず、全tradeoffとdefault維持をversioned resultと文書へ保存します。