bench(reviewer-eval): api-security batch 1 — corpus 14 → 30 (+8 golds, +8 pairs) - #299
Merged
Conversation
Contributor
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
norvalbv
force-pushed
the
bench/corpus-batch-2
branch
from
August 1, 2026 21:09
6047313 to
668c3fc
Compare
…s, +8 pairs) First MINED rows for any domain suite: 8 outcome=fixed CodeRabbit security findings adapted into anonymized api-security golds (one checklist slug each, caseId/sourcePr/outcomeEvidence/scopeConfirmed stamped) + a fixed-variant minimal-pair decoy per gold. Corpus 14 -> 30 (16 gold / 14 decoy); the holdout floor flipped 2 decoys to holdout and said so. bench validate green; tracker views re-rendered. Note: earlier session numbers citing a 25-row api-security corpus were read from a dirty working tree — committed truth was 14 rows, making this batch a 2.1x growth of the suite. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
norvalbv
force-pushed
the
bench/api-security-batch
branch
from
August 1, 2026 21:21
2db5f94 to
5b3645f
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR D — stacked on #298. The first MINED rows any domain suite has had: 8
outcome=fixedCodeRabbit security findings adapted into anonymized api-security golds (one checklist slug each, full provenance fields) + a fixed-variant minimal-pair decoy per gold. The holdout floor flipped 2 decoys to holdout and reported it.Correction from tonight's session notes: earlier messages cited a 25-row api-security corpus — that number came from a dirty shared-checkout read; the committed corpus was 14 rows. This batch is a 2.1× growth of the suite (14 → 30, 16 gold / 14 decoy).
Not benched tonight: the api-security suite's shipped config is haiku→opus cascade, and the opus leg was out of bounds for this session.
bench.mts validategreen; bench + checkpoint when you green-light the cascade run.🤖 Generated with Claude Code