Algorogenic thumbprints in literary translation: an epistemic network analysis of LLM translations of classical Chinese fantasy

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

This study examines algorogenic thumbprints in literary translation, referring to recurrent and reproducible stylistic patterns in large language model (LLM) outputs. Using epistemic network analysis (ENA) across seven decision-making domains—lexical choice, syntactic structure, cultural adaptation, stylistic register, semantic fidelity, narrative flow, and intertextual reference—we examine translations of two classical Chinese fantasy novels produced by Claude Opus 4.5, ChatGPT 5.2 Pro, and Gemini 3.0 Pro, alongside published human translations and a Western fantasy reference corpus. The findings show that, under neutral-prompt and deterministic conditions, the LLMs exhibit model-specific architectures centered on Lexical Choice–Intertextual Reference with varying narrative coordination, while the two published human translations examined show distinct lexical-intertextual-narrative and lexical-syntactic-cultural patterns. The study therefore suggests that Baker’s framework of translator thumbprints can be usefully extended to algorithmic translation and demonstrates the usefulness of ENA for modeling the relational structures underlying translation decision-making.