A preprint study from researchers at the University of Maryland, College Park and Google DeepMind found that fiction written by artificial intelligence is easy to detect because it struggles with complex story structure and tends to moralize in clunky ways. The study, which looked at more than 50,000 AI-generated short stories, found that “AI stories over-explain themes and favor tidy, single-track plots while human stories frame protagonists’ choices as more morally ambiguous and have increased temporal complexity.” The researchers noted that “Claude produces notably flat event escalation, GPT over-indexes on dream sequences, and Gemini defaults to external character description,” and that “AI-generated stories cluster in a shared region of narrative space, while human-authored stories exhibit greater diversity.” The detector, called StoryScope, builds on NarraBench, a 2025 benchmark, and focuses on narrative features such as plot development, character descriptions, setting, and temporal structure. Jenna Russell, a University of Maryland researcher and study author who is also an intern at the AI-detection company Pangram, told 404 Media that the idea was to move past plain text detection and focus on ideas. To test StoryScope, the researchers selected 10,272 human-written stories then reverse engineered them into writing prompts.