{
  "ok": true,
  "data": {
    "entry": {
      "id": "receipts",
      "kind": "method",
      "kindLabel": "Method",
      "title": "Turn every important claim into a receipt",
      "body": "For high-stakes answers, make the model attach each claim to a source, calculation, line number, trace id, or explicit assumption. Unsupported claims do not disappear, but they become visible enough to reject.",
      "tag": "verification",
      "date": "2026 · 05 · 27",
      "publishedAt": "2026-05-27",
      "note": null,
      "insight": {
        "aha": "A citation is not decoration. It is a handle you can pull to see whether the sentence is load-bearing.",
        "tryThis": "Make every claim end with one receipt: source, row, command, calculation, trace id, or explicit assumption.",
        "watchFor": [
          "Receipts that point to a broad document instead of the claim",
          "Numbers without denominators",
          "Source links that support nearby context but not the sentence itself"
        ],
        "labId": "receipts"
      },
      "extended": [
        "Models are good at moving from evidence to prose. They are also good at producing prose that looks like it came from evidence. The receipt requirement separates those two behaviors.",
        "The receipt can be a citation, a row count, a command output line, a test name, or a declared assumption. The format matters less than the discipline: every claim has to point somewhere.",
        "When the model cannot produce a receipt, that is not failure. That is the system doing its job and showing you where judgment is still needed."
      ],
      "url": "https://tips.platphormnews.com/entries/receipts"
    }
  }
}