{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "MirroS-Lab/HarnessEval-W",
 "name": "HarnessEval-W",
 "owner": "MirroS-Lab",
 "slug": "mirros-lab-harnesseval-w",
 "github": "https://github.com/MirroS-Lab/HarnessEval-W",
 "what": "HarnessEval-W is a Python evaluation pipeline that scores generated world model videos with sub-agents and saves a traceable reasoning chain for each score.",
 "why": "",
 "language": "Python",
 "requirements": [
  "Git and conda installed",
  "Ability to create three conda environments from the files in docs/installation",
  "Credentials and paths filled into harnesseval.env, copied from config/example.env",
  "Generated results in the layout used by runs/example/results_example, or use the bundled demo"
 ],
 "audience_note": "Built for researchers and benchmark maintainers who compare world models and need scores they can audit.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/mirros-lab-harnesseval-w/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "mirros-lab-harnesseval-w--score-world-model-videos-with-evidence-trees",
   "title": "Score a world model's generated videos with evidence trees",
   "best": true,
   "url": "https://dedupedai.com/use-cases/mirros-lab-harnesseval-w/score-world-model-videos-with-evidence-trees/",
   "json": "https://dedupedai.com/use-cases/u/mirros-lab-harnesseval-w/score-world-model-videos-with-evidence-trees.json"
  },
  {
   "id": "mirros-lab-harnesseval-w--check-finished-run-before-sharing-scores",
   "title": "Check a finished run for missing scores before sharing",
   "best": false,
   "url": "https://dedupedai.com/use-cases/mirros-lab-harnesseval-w/check-finished-run-before-sharing-scores/",
   "json": "https://dedupedai.com/use-cases/u/mirros-lab-harnesseval-w/check-finished-run-before-sharing-scores.json"
  },
  {
   "id": "mirros-lab-harnesseval-w--run-bundled-demo-to-test-setup",
   "title": "Run the bundled demo to test the setup end to end",
   "best": false,
   "url": "https://dedupedai.com/use-cases/mirros-lab-harnesseval-w/run-bundled-demo-to-test-setup/",
   "json": "https://dedupedai.com/use-cases/u/mirros-lab-harnesseval-w/run-bundled-demo-to-test-setup.json"
  },
  {
   "id": "mirros-lab-harnesseval-w--submit-new-case-or-skill-to-benchmark",
   "title": "Submit a new case or skill to the benchmark",
   "best": false,
   "url": "https://dedupedai.com/use-cases/mirros-lab-harnesseval-w/submit-new-case-or-skill-to-benchmark/",
   "json": "https://dedupedai.com/use-cases/u/mirros-lab-harnesseval-w/submit-new-case-or-skill-to-benchmark.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}