chore(main): release trg 0.11.0 - #228
Conversation
PR SummaryLow Risk Overview This diff does not include application code; it only records what is already merged. The new changelog groups eval and hillclimb integrity work: held-out cases must not leak into iteration bundles or training signals, hillclimb rounds cannot keep changes unconfirmed on held-out splits, train gains cannot stand in for generalization, and suites with nothing measurable cannot read as passing. It also tightens grading trust (noise thresholds, judge confidence, model-scaling regressions) and fixes held-out leakage plus eval gates failing open (#229). Reviewed by Cursor Bugbot for commit 26a7b6d. Bugbot is set up for automated code reviews on this repo. Configure here. |
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: Repository: TrogonStack/rusty-monorepo/.coderabbit.yaml Review profile: CHILL Plan: Advanced Run ID: 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 |
d15f972 to
501f425
Compare
Signed-off-by: SHT Bot <61149376+sht-bot@users.noreply.github.com>
501f425 to
26a7b6d
Compare
|
🤖 Created releases: 🌻 |
An automated release has been created for you.
0.11.0 (2026-09-29)
Features
Bug Fixes
This PR was generated with Release Please. See documentation.