{
  "name": "kiwix-knowledge-v1",
  "book": "wikipedia_en_all_maxi_2026-02",
  "note": "The 9 knowledge cases from internal/phraser/eval/talk_v1.json. Queries are hand-written English keywords on purpose: Kiwix ranks by keyword, not meaning, so a natural question fails. Writing them by hand separates 'retrieval is broken' from 'the model writes bad queries'.",
  "cases": [
    {
      "id": "know-sky-blue",
      "question": "почему небо синее?",
      "query": "Rayleigh scattering sky blue",
      "want_titles": ["Rayleigh scattering", "Diffuse sky radiation"]
    },
    {
      "id": "know-boil-egg",
      "question": "сколько варить яйцо вкрутую?",
      "query": "boiled egg cooking",
      "want_titles": ["Boiled egg", "Egg as food"]
    },
    {
      "id": "know-ssd-vs-hdd",
      "question": "чем ssd отличается от hdd?",
      "query": "solid-state drive",
      "want_titles": ["Solid-state drive", "Hard disk drive"]
    },
    {
      "id": "know-cat-purr",
      "question": "почему кошки мурчат?",
      "query": "cat purr",
      "want_titles": ["Purr", "Cat communication"]
    },
    {
      "id": "know-hiccups",
      "question": "как быстро избавиться от икоты?",
      "query": "hiccup",
      "want_titles": ["Hiccup"]
    },
    {
      "id": "know-polite-form",
      "question": "не могли бы вы объяснить, что такое vpn?",
      "query": "virtual private network",
      "want_titles": ["Virtual private network"]
    },
    {
      "id": "know-dont-know",
      "question": "как зовут моего соседа снизу?",
      "query": "name of my downstairs neighbour",
      "want_titles": [],
      "expect_miss": true,
      "note": "Unanswerable by design. Retrieval SHOULD find nothing useful. Counted as a hit only when nothing relevant comes back."
    },
    {
      "id": "know-water-per-day",
      "question": "сколько воды в день надо пить?",
      "query": "human daily water requirement drinking",
      "want_titles": ["Drinking water", "Water", "Dehydration", "Hydration"]
    },
    {
      "id": "know-thunder-delay",
      "question": "почему гром слышно позже молнии?",
      "query": "thunder speed of sound lightning",
      "want_titles": ["Thunder", "Lightning"]
    }
  ]
}