StoryScope: Investigating Idiosyncrasies in AI Fiction

Researchers have developed StoryScope, a pipeline that analyzes discourse-level narrative features to distinguish AI-generated fiction from human-written stories without relying on stylistic cues. Testing on a corpus of 61,608 stories revealed that narrative features alone achieve 93.2% accuracy in detecting AI versus human writing, with AI stories tending to over-explain themes and favor tidy plots while human stories exhibit greater moral ambiguity and temporal complexity. The findings demonstrate that differences in underlying narrative construction, not just writing style, can reliably separate human original works from AI-generated fiction.

Computer Science Computation and Language Submitted on 3 Apr 2026 v1 https://arxiv.org/abs/2604.03136v1 , last revised 13 Apr 2026 this version, v4 Title:StoryScope: Investigating idiosyncrasies in AI fiction View PDF /pdf/2604.03136 Abstract:As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in this space focuses on identifying surface-level signatures of AI writing, we ask instead whether AI-generated stories can be distinguished from human ones without relying on stylistic signals, focusing on discourse-level narrative choices such as character agency and chronological discontinuity. We propose StoryScope, a pipeline that automatically induces a fine-grained, interpretable feature space of discourse-level narrative features across 10 dimensions. We apply StoryScope to a parallel corpus of 10,272 writing prompts, each written by a human author and five LLMs, yielding 61,608 stories, each ~5,000 words, and 304 extracted features per story. Narrative features alone achieve 93.2% macro-F1 for human vs. AI detection and 68.4% macro-F1 for six-way authorship attribution, retaining over 97% of the performance of models that include stylistic cues. A compact set of 30 core narrative features captures much of this signal: AI stories over-explain themes and favor tidy, single-track plots while human stories frame protagonist' choices as more morally ambiguous and have increased temporal complexity. Per-model fingerprint features enable six-way attribution: for example, Claude produces notably flat event escalation, GPT over-indexes on dream sequences, and Gemini defaults to external character description. We find that AI-generated stories cluster in a shared region of narrative space, while human-authored stories exhibit greater diversity. More broadly, these results suggest that differences in underlying narrative construction, not just writing style, can be used to separate human-written original works from AI-generated fiction. Submission history From: Jenna Russell view email /show-email/36f6c12c/2604.03136 Fri, 3 Apr 2026 15:56:38 UTC 2,053 KB v1 /abs/2604.03136v1 Mon, 6 Apr 2026 01:44:49 UTC 2,052 KB v2 /abs/2604.03136v2 Wed, 8 Apr 2026 13:25:18 UTC 2,052 KB v3 /abs/2604.03136v3 v4 Mon, 13 Apr 2026 20:04:18 UTC 2,045 KB References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .