[
  {
    "id": "ARR-2026-1EFJS8JXH08Q5SF8-v1",
    "type": "article",
    "title": "Prompt-order dominance and question-weight sensitivity in published language-model evaluations",
    "author": [
      {
        "literal": "Lluis Eriksson"
      }
    ],
    "issued": {
      "date-parts": [
        [
          2026,
          11,
          19
        ]
      ]
    },
    "publisher": "AIRR.SCIENCE",
    "archive": "AIRR.SCIENCE",
    "archive_location": "ARR-2026-1EFJS8JXH08Q5SF8",
    "version": "v1",
    "genre": "Research preprint",
    "URL": "https://airr.science/papers/ARR-2026-1EFJS8JXH08Q5SF8/versions/v1/",
    "note": "Research preprint; ARR-2026-1EFJS8JXH08Q5SF8 v1. Not peer reviewed by AIRR. Working paper; not admitted to the AIRR accepted collection.",
    "abstract": "All nine comparisons between three program-aided and three chain-of-thought prompt orders have positive accuracy differences on each of eight published tasks. We allow rounding and either common standard-deviation convention. Relative question weights up to 1.06 preserve all comparisons. For ASDiv, compatible triples and question outcomes permit a tie at the exact ratio 29/27. Four rows cannot be reconstructed from three raw full-file binary accuracies with a common deviation convention; rounding each order first reconciles one. These conclusions concern historical summaries and specified scoring rules."
  }
]
