{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "lucasuiii-modeling-workbench--compare-two-candidate-models",
 "repo": "Lucasuiii/modeling-workbench",
 "repo_url": "https://github.com/Lucasuiii/modeling-workbench",
 "repo_slug": "lucasuiii-modeling-workbench",
 "title": "Test two candidate models before choosing one",
 "page_title": "How to test two candidate models before choosing one with Modeling Workbench",
 "summary": "Run both candidates as cheap exploratory runs and record why one was selected.",
 "who": "A modeler on a contest team who has two plausible approaches to one problem and must justify the choice in the paper.",
 "problem": "Picking a model first and testing it later makes it hard to show a real comparison or explain the choice.",
 "outcome": "A recorded comparison table of candidates, with exploratory run evidence and a written reason for the selected model.",
 "steps": [
  "In MODEL_CONTRACT.json, write two candidates, each with why_considered and discriminating_evidence.",
  "Run each candidate as an exploratory run: `python3 \"$S/record_run.py\" --project <project folder> --candidate CAND-A -- python3 code/try_a.py`. (inferred, check the README)",
  "Repeat the same command for CAND-B with its own script.",
  "Mark the chosen candidate as selected and write decision_rationale that cites the exploratory run IDs.",
  "Run `python3 \"$S/cumcm_check.py\" --project <project folder> --stage model-design --gate-mode preflight` to print the candidate comparison table. (inferred, check the README)"
 ],
 "agent_prompt": "Use the Modeling Workbench repo in <tool folder> to compare two candidate models for the problem in <project folder>. Record an exploratory run for each candidate, select one with a written rationale, and run the model-design check. Verify the comparison table lists both candidates and the selected one cites its runs.",
 "agents": [
  "codex",
  "claude-code"
 ],
 "difficulty": "Advanced",
 "time": "2 hours 30 minutes",
 "basis": "readme",
 "caveat": "The workflow records and checks the comparison, but it does not prove that the chosen model is mathematically correct or globally optimal.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.10 or newer with the Python dependencies the README lists",
  "A MATLAB or Python calculation backend",
  "XeLaTeX and a PDF rendering tool, needed before the paper stage",
  "Official contest problem files, attachments and submission rules in one folder",
  "Codex or Claude Code with access to the local tool folder"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": false,
 "score": 0.8,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/lucasuiii-modeling-workbench/compare-two-candidate-models/",
 "md": "https://dedupedai.com/use-cases/lucasuiii-modeling-workbench/compare-two-candidate-models/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/lucasuiii-modeling-workbench--compare-two-candidate-models.json",
 "api_version": "v1"
}