Compare text using deterministic, case-insensitive bag-of-words token-overlap similarity for lexical duplicate screening. Lowercase each input and tokenize with Python Unicode regex \w+ (letters, digits and underscores). Count repeated tokens. Similarity = sum(min(count_a(token),count_b(token))) / max(words_a,words_b,1), rounded to four decimal places. Returns exactly similarity in [0,1], words_a