{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "simreal-ai-simreal-mlbench--recompute-published-scores",
 "repo": "Simreal-AI/Simreal-MLBench",
 "repo_url": "https://github.com/Simreal-AI/Simreal-MLBench",
 "repo_slug": "simreal-ai-simreal-mlbench",
 "title": "Recompute a published benchmark score from saved counts",
 "page_title": "How to recompute a published benchmark score from saved counts with Simreal ML Bench",
 "summary": "Rebuild a reported task score from its reference counts to check the number yourself.",
 "who": "A research reviewer or lab analyst who has been given a reported ML Benchmark score and does not want to rely on trusting Simreal.",
 "problem": "A published agent score is hard to trust without seeing how it was produced, and reviewers need to confirm the arithmetic and provenance.",
 "outcome": "A recomputed task score from the public scoring code, plus a check of the submission id, artifact hash, and reference snapshot hash behind the number.",
 "steps": [
  "Set up the environment with `python3 -m venv .venv`, `source .venv/bin/activate`, and `python -m pip install -e '.[test]'`.",
  "Recompute a score from a snapshot and result pair with `mleb grade examples/snapshot.json examples/result.json`.",
  "Run the report verification script with `python scripts/verify_report.py`.",
  "Compare the submission id, artifact hash, and reference snapshot hash against the values in the reported result.",
  "Check the arithmetic against the 100 × p² rule described in SCORING.md."
 ],
 "agent_prompt": "In the Simreal-MLBench repository, run `mleb grade examples/snapshot.json examples/result.json` and then `python scripts/verify_report.py`. Replace the example files with the saved reference counts for <target task> if you have them. Report the recomputed score and whether the verification script passed.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "The local example files only demonstrate the grading path; checking a real reported number needs its saved reference counts, which the README says must be recomputed from saved data.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.11 or newer (Python 3.12 is the locally tested version)",
  "A local copy of the repository from github.com/Simreal-AI/Simreal-MLBench",
  "A terminal with a shell that supports the commands in the README",
  "For full agent evaluation only: contact with business@simreal.co to get access to the Simreal evaluation service"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.9,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/simreal-ai-simreal-mlbench/recompute-published-scores/",
 "md": "https://dedupedai.com/use-cases/simreal-ai-simreal-mlbench/recompute-published-scores/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/simreal-ai-simreal-mlbench--recompute-published-scores.json",
 "api_version": "v1"
}