{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "xinxuxin-keystone-bench--test-judge-agreement-on-replies",
 "repo": "xinxuxin/keystone-bench",
 "repo_url": "https://github.com/xinxuxin/keystone-bench",
 "repo_slug": "xinxuxin-keystone-bench",
 "title": "Measure agreement between two judges on the same replies",
 "page_title": "How to measure agreement between two judges on the same replies with Keystone Bench",
 "summary": "Compute Cohen's kappa between two action judges to see whether their verdicts agree.",
 "who": "A rubric or grader author who needs to know whether a second judge reads the same replies the same way before trusting a score.",
 "problem": "An action judge's verdicts can depend on which model reads the reply, and a single judge gives no sense of that spread.",
 "outcome": "A kappa score showing how far two judges agree on the same set of classified replies.",
 "steps": [
  "`pip install keystone-bench`",
  "`keystone run --family all --layer quick --model openrouter/openai/gpt-5.6-terra --judge openrouter/anthropic/claude-sonnet-5`",
  "Rerun the same replies with a second judge from another vendor into a separate run folder (inferred, check the README)",
  "`keystone compare-judges runs/a/records.jsonl runs/b/records.jsonl` (inferred, check the README)"
 ],
 "agent_prompt": "In the keystone-bench repo, run keystone compare-judges on two records.jsonl files that classify the same replies with different judges. Report the Cohen's kappa and name the judge pair used.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "Kappa between two judges shows agreement only; it does not show which judge is correct on a given reply.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python with pip to install keystone-bench from PyPI",
  "An API key for an OpenAI-compatible endpoint, such as OpenRouter, to run models and a judge from a different vendor",
  "Network access so that keystone build can fetch HealthBench from OpenAI's public copy and the label files",
  "Enough disk space and time for the local rebuild of the twins, since the release ships span references rather than benchmark prose"
 ],
 "risk": "sensitive",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "Running two judges means two model endpoints, so each API key must be set in the environment before the runs."
  }
 ],
 "best": false,
 "score": 0.7,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/xinxuxin-keystone-bench/test-judge-agreement-on-replies/",
 "md": "https://dedupedai.com/use-cases/xinxuxin-keystone-bench/test-judge-agreement-on-replies/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/xinxuxin-keystone-bench--test-judge-agreement-on-replies.json",
 "api_version": "v1"
}