Repository navigation
[HWORKS-3591] Document how an LLM judge decides pass or fail - #717
Merged
gibchikafa merged 7 commits intoOct 24, 2026
Merged
Conversation
The evaluation guide showed criterion weights only in examples. Explain the
weighted average, the default pass score, floors ("never below"), that the
judge model never sees weights or floors, and what an ungradable judge means.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ge is not a page of failures Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
… on the evaluation job Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ed not be running Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
jimdowling
approved these changes
Oct 24, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The evaluation guide showed judge criteria only through examples with
"weight": 1; nothing said what a weight does, what "never below" means in the judge config UI, or when a judged trial passes.Adds How a judge decides pass or fail under The checks in
user_guides/agents/evaluation:pass_score, defaulting to three quarters of the way up the scale (4 on 1 to 5)critical_min, "never below") fail a trial whatever the averageMatches
hopsworks_agents/eval/judges.pyandjudge_config.py; the same text went into thehops-agent-evalsskill (hopsworks-api #1352). Markdownlint clean; the new code block is within 88 columns.🤖 Generated with Claude Code