{
"_note": "MINIMAL stop words only. 'universal' covers Latin-script languages — only words safe across ALL Latin languages (no per-language lists due to cross-language collisions like German 'die'). 'unsegmented' covers scripts without word boundaries — each script has its own Unicode range so no collision risk. Let term weighting handle the rest.",
"universal": [
"a", "an", "the",
"is", "are", "was", "were", "be", "been", "being",
"in", "on", "at", "to", "of", "for", "with", "from", "by",
"and", "or", "but",
"i", "me", "my", "we", "our", "you", "your",
"it", "its", "he", "she", "they", "them",
"this", "that"
],
"unsegmented": {
"zh": ["的", "了", "着", "把", "被", "让", "给"],
"ja": ["の", "は", "が", "を", "に", "で", "と", "も", "か", "よ", "ね", "わ", "へ", "や"],
"ko": ["은", "는", "이", "가", "을", "를", "에", "에서", "와", "과", "도", "의", "로", "으로"],
"th": ["ที่", "ของ", "ใน", "จะ", "ได้", "ให้", "กับ", "อยู่", "ไม่", "เป็น", "มี", "ว่า", "แล้ว", "ก็"],
"lo": ["ທີ່", "ໃນ", "ຂອງ", "ໄດ້", "ເປັນ", "ກັບ", "ຈະ", "ບໍ່", "ມີ", "ແລ້ວ"],
"my": ["သည်", "ကို", "က", "တွင်", "နှင့်", "များ", "၏", "ဖြင့်", "သို့"],
"km": ["នៅ", "ដែល", "និង", "មាន", "ជា", "នេះ", "ត្រូវ", "ពី", "ក្នុង", "គឺ"]
}
}