
thumb|300px|The UTF-8-encoded Japanese Wikipedia article for Mojibake displayed as if interpreted as [[Windows-1252]] thumb|300px|The UTF-8-encoded Russian Wikipedia article on Church Slavonic displayed as if interpreted as [[KOI8-R]]
thumb|300px|The UTF-8-encoded Japanese Wikipedia article for Mojibake displayed as if interpreted as [[Windows-1252]] thumb|300px|The UTF-8-encoded Russian Wikipedia article on Church Slavonic displayed as if interpreted as [[KOI8-R]]
Mojibake (; , 'character transformation') is the garbled or gibberish text that is the result of text being decoded using an unintended character encoding. The result is a systematic replacement of symbols with completely unrelated ones, often from a different writing system.
Discovered by embedding cosine similarity (sentence-transformers MiniLM, 384-dim).