{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "simreal-ai-simreal-mlbench--validate-benchmark-catalog",
 "repo": "Simreal-AI/Simreal-MLBench",
 "repo_url": "https://github.com/Simreal-AI/Simreal-MLBench",
 "repo_slug": "simreal-ai-simreal-mlbench",
 "title": "Validate the 60-task benchmark catalog locally",
 "page_title": "How to validate the 60-task benchmark catalog locally with Simreal ML Bench",
 "summary": "Check the public task catalog and protocol config before building on the benchmark.",
 "who": "An ML engineer or benchmark maintainer who wants to confirm the public catalog is well-formed before adding an agent or a fork.",
 "problem": "Benchmark definitions drift or break silently, and it is hard to know whether a local copy still matches the published protocol.",
 "outcome": "A local confirmation that the task catalog and protocol configuration validate, with no credentials or model calls needed.",
 "steps": [
  "Create a virtual environment with `python3 -m venv .venv`.",
  "Activate it with `source .venv/bin/activate`.",
  "Install the package and test extras with `python -m pip install -e '.[test]'`.",
  "Validate the catalog with `mleb validate configs/catalog.json`."
 ],
 "agent_prompt": "In the Simreal-MLBench repository, create a virtual environment, install the package with `python -m pip install -e '.[test]'`, and run `mleb validate configs/catalog.json`. Report whether validation passed and how many tasks the catalog lists. Confirm the count is 60 before reporting success.",
 "agents": [
  "any"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "This only validates the public catalog and protocol config; it does not run any agent or touch the original competition datasets, which are acquired separately.",
 "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": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/simreal-ai-simreal-mlbench/validate-benchmark-catalog/",
 "md": "https://dedupedai.com/use-cases/simreal-ai-simreal-mlbench/validate-benchmark-catalog/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--validate-benchmark-catalog.json",
 "api_version": "v1"
}