{
  "example_kind": "original synthetic manual planning case",
  "slug": "forecast-training-test-cutoff",
  "title": "Freeze a forecast evaluation cutoff before fitting",
  "scenario": "Synthetic planning case: A manual evaluation declares days 1–5 for fitting and days 6–8 held out. A proposed parameter choice uses day-seven outcomes before claiming performance on days 6–8.",
  "layout": "protocol",
  "dataset": {
    "heading": "Inspect the invented case records",
    "headers": [
      "Evidence window",
      "Declared use",
      "Proposed actual use"
    ],
    "rows": [
      [
        "Days 1–5",
        "Fit rule",
        "Fit rule"
      ],
      [
        "Day 6",
        "Held-out outcome",
        "Evaluate"
      ],
      [
        "Day 7",
        "Held-out outcome",
        "Used to choose parameter"
      ],
      [
        "Day 8",
        "Held-out outcome",
        "Evaluate"
      ]
    ]
  },
  "derivation": "The three declared held-out days include day seven. Using that outcome to select the rule violates the stated information boundary even if the final reported score uses all three rows.",
  "result": "The proposed rule has seen part of its held-out outcomes, so the declared evaluation is contaminated. Preserve the cutoff and choose a genuinely unseen evaluation or an explicitly different scope.",
  "boundary": "The artifact checks outcome leakage into fitting, separate from retaining a forecast vintage or rolling origins.",
  "limitations": "The cutoff alone does not validate sample size, features, timing or forecasting performance.",
  "sources": [
    "forecast"
  ],
  "tasks": [
    [
      "Freeze fitting and test identities",
      "Evaluation planner",
      "The days 1–5 versus 6–8 split is recorded before rule selection."
    ],
    [
      "Inspect every information use",
      "Reviewer",
      "Day-seven outcome influenced parameter choice rather than being unseen evaluation evidence."
    ],
    [
      "Restore a valid declared evaluation",
      "Method owner",
      "A new untouched cohort or transparently revised claim is chosen; contamination is not erased from history."
    ]
  ],
  "faqs": [
    [
      "Can held-out data be examined eventually?",
      "Yes for evaluation; using it for tuning changes what that same cohort can support."
    ],
    [
      "Does this require a specific train/test percentage?",
      "No. This example checks information boundaries, not a universal split ratio."
    ]
  ],
  "method_references": [
    {
      "id": "forecast",
      "title": "Forecasting: Principles and Practice — accuracy",
      "url": "https://otexts.com/fpp3/accuracy.html",
      "scope": "Genuine held-out forecast and point-error evaluation context. Binary scoring examples use their own explicit toy definitions; no real task model is validated."
    }
  ]
}