Stylometric Fingerprints of AI Rewriting: Punctuation, Syntax, and Model Attribution Across 60,786 Paired Texts

Working paper and open per-text data. We compared 60,786 human-written academic texts with AI rewrites of the same texts produced by eight AI model configurations across six model families, and computed 49 stylometric features for every text: punctuation rates, passive voice, nominalization, first person, contractions, sentence openers, lexical diversity, word length, and a set of hedge and connective phrases. The paired design controls topic and content, so every change is caused by the model itself. AI rewrites use longer words (Cohen's d = 1.57 for words of seven or more letters), more nominalizations (d = 1.12), higher lexical diversity (d = 1.31), more passive voice, and more commas, while first person, contractions, questions, and repeated sentence openers are mostly removed. A multinomial logistic regression reading only the 49 features identifies which of six models produced a rewrite with 64.3 percent accuracy against a 16.7 percent chance rate, and a gradient boosting model raises this only to 66.4 percent. DeepSeek is the most identifiable model and OpenAI is the least. Qwen changes the style of the human source text least and DeepSeek changes it most. Files: per-text stylometric features for all 121,572 texts (opaque pair identifiers; corpus, model, discipline, side, and all 49 features), the attribution and analysis results, all analysis and figure code, and the paper PDF. The corpus pair texts are not included. Paper page: https://textpulse.ai/research/ai-style-fingerprints