{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "xinxuxin-keystone-bench--check-what-a-new-version-regressed",
 "repo": "xinxuxin/keystone-bench",
 "repo_url": "https://github.com/xinxuxin/keystone-bench",
 "repo_slug": "xinxuxin-keystone-bench",
 "title": "Find which items a new assistant version fixed or broke",
 "page_title": "How to find which items a new assistant version fixed or broke with Keystone Bench",
 "summary": "Compare two saved runs item by item to see exactly what changed between versions.",
 "who": "A team shipping updates to a medical chat assistant that needs to know whether a new version got worse on specific decisive-fact cases.",
 "problem": "A single aggregate score can hide that a new version fixed some missing-evidence cases while breaking others.",
 "outcome": "A list of items that changed verdict between the two runs, so the team can review the regressions directly.",
 "steps": [
  "`pip install keystone-bench`",
  "`keystone build`",
  "`keystone run --family all --layer quick --model openrouter/openai/gpt-5.6-terra --judge openrouter/anthropic/claude-sonnet-5`",
  "Rerun the same command for the new version with a different output folder, so you have two run folders to compare (inferred, check the README)",
  "`keystone regress runs/v1 runs/v2`"
 ],
 "agent_prompt": "In the keystone-bench repo, compare two saved runs with keystone regress runs/<old> runs/<new>. Report the items that regressed and the items that were fixed, and confirm both runs used the same quick layer.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "1 hour",
 "basis": "readme",
 "caveat": "Both runs must use the same release and layer for the comparison to be meaningful, and the regression check only covers the twins in those runs.",
 "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": "Each run calls a model endpoint, so the API key must be set in the environment before the runs start."
  }
 ],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/xinxuxin-keystone-bench/check-what-a-new-version-regressed/",
 "md": "https://dedupedai.com/use-cases/xinxuxin-keystone-bench/check-what-a-new-version-regressed/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--check-what-a-new-version-regressed.json",
 "api_version": "v1"
}