bench(reviewer-eval): correctness batch 2 — corpus 90 → 120 (+15 golds, +15 pairs) - #298
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/publish-correctness-90
branch
from
August 1, 2026 20:59
7b1eebc to
1150136
Compare
…ds, +15 pairs) Second mined tranche via the propose/finalize pipeline: 15 outcome=fixed CodeRabbit findings adapted into anonymized correctness golds (one lens each, caseId/sourcePr/outcomeEvidence/scopeConfirmed stamped) + a minimal-pair decoy per gold (real fix applied, variantOf/adapted). Decoys now 55 of the ~120 the correctness-reviewer-precision record names as its revisit threshold. Appended AFTER checkpoint evt-...-b0dc29a7d531 (frozen 90-row tree); the row-set corpusHash keeps the 90-row baseline paired over retained rows. No rebutted- thread decoys this tranche: they mostly fail the hard drops (missing line anchors / truncated hunks) — next cycle picks them up from the raw thread data. bench validate green (120 rows); tracker views re-rendered (freshness stamps). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
norvalbv
force-pushed
the
bench/corpus-batch-2
branch
from
August 1, 2026 21:09
6047313 to
668c3fc
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 C — stacked on #297. Second mined tranche through the propose/finalize pipeline: 15
outcome=fixedCodeRabbit findings as anonymized correctness golds + a minimal-pair decoy each. Decoys now 55 of the ~120 thecorrectness-reviewer-precisionrecord names as its revisit threshold.Deliberately appended after checkpoint
evt-…-b0dc29a7d531so the published evidence hashes the exact tree it measured; #295's row-setcorpusHashkeeps the 90-row baseline paired over retained rows through this append (that property, not coincidence).Honest gap: no rebutted-thread decoys this tranche — they mostly fail the pipeline's hard drops (missing line anchors / truncated hunks). Next mining cycle should relax extraction for those threads specifically.
bench.mts validategreen at 120 rows.🤖 Generated with Claude Code