{ "_why": [ "Surfaces excluded from renaming because they are REAL-WORLD referents, not the author's", "invented proper nouns. The R49 rule is that ambiguous cases are deliberately RENAMED --", "renaming is the safe direction and leaving is the leaking one -- so this list is kept to", "categories that are unambiguously real: geography, demonyms, brands, and foreign-language", "titles or common nouns that function as ordinary address.", "", "⚠ SENSITIVITY FLOOR, stated because it is part of the result: every surface in the top 200", "by count was classified, and several were read IN CONTEXT first (that is how `G` was caught).", "Below the top 200 surfaces were NOT individually read, so a rare real-world referent may be", "renamed. That is the safe direction and an accepted cost, not an oversight.", "", "⚠ Hemingway is a far harder case than Bronte or Yarros for this: his fiction is saturated", "with real cities, real armies, real wars and four languages. The 23-form non-ASCII alphabet", "measured on this corpus is the same fact from the other side." ], "_caught_by_reading_in_context": { "G": "NOT a name. It is the fragment left by `B.G.`, `G.M.`, `G2`, `G3` -- 248 occurrences. Renaming it would have produced `B.Vasquez` inside the prose.", "Gran": "fragment of real names: `Gran Sasso D'Italia`, `Gran Italia` (a Milan restaurant), `Gran Hotel`.", "Shamba": "Swahili common noun for a farm or settlement, used throughout True at First Light as an ordinary place word.", "Ingles": "KEPT RENAMEABLE, deliberately. It is the gypsy band's in-world nickname for Robert Jordan, exactly parallel to Yarros's `Violence` for Violet -- a nickname is the author's invention even when the word is not." }, "geography": [ "Africa", "America", "Madrid", "Milan", "Havana", "Venice", "Cuba", "Nairobi", "Segovia", "Valencia", "Cannes", "Biarritz", "Laitokitok", "Boise", "York", "Sebastian", "San", "Gran", "States", "Paris", "Spain", "Italy", "Austria", "France", "Switzerland", "Kenya", "Tanganyika", "Chicago", "Michigan", "Florida", "Guadarrama", "Escorial", "Navacerrada", "Pamplona", "Burguete", "Bayonne", "Kilimanjaro", "Ebro", "Tagus", "Adriatic", "Piave", "Isonzo", "Gorizia", "Udine", "Torcello", "Trieste", "Bimini", "Nantucket", "Constantinople", "Smyrna" ], "demonyms_and_languages": [ "American", "Americans", "Cuban", "Cubans", "Indian", "Indians", "Italian", "Italians", "German", "Germans", "Austrian", "Austrians", "Russian", "Russians", "Spanish", "English", "French", "Basque", "Extremaduran", "Kamba", "Wakamba", "Masai", "Mau", "Arap", "Swahili", "Moorish", "Negro", "Gypsy", "Gypsies", "Croat", "Hungarian" ], "brands_and_products": [ "Perrier", "Packard", "Ford", "Fiat", "Cinzano", "Anis", "Chianti", "Marsala", "Bass", "Gordon", "Thermos", "Mannlicher", "Springfield", "Winchester", "Mauser" ], "foreign_titles_and_common_nouns": [ "Tenente", "Signor", "Signora", "Signorina", "Bwana", "Memsahib", "Hapana", "Ngoma", "Shamba", "Don", "Dona", "Senor", "Senora", "Senorita", "Maestro", "Matador", "Picador", "Banderillero", "Guardia", "Ayuntamiento", "Mister", "Missus", "Doc" ], "acronym_fragments": ["G", "GI", "CP", "BG", "GM", "MP", "RAF", "PC", "SIM"] }