Provenance Density: Visualizing Verified Claims to Overcome the Fluency Trap in AI-Generated Text

Summary

This arXiv paper (2509.00010) by Qing Zhang, Yifei Huang, and Juyoung Lee introduces the 'Fluency Trap': users trust fluent AI hallucinations while discounting accurate content once it is labeled AI-generated. The authors argue that binary 'Made with AI' labels disclose authorship but reveal nothing about the evidence behind a claim. They propose Provenance Density, an evidence-visualization interface displaying the density of verified claims within a text. In a user study with 81 participants, an idealized Provenance Density interface produced a large discernment gap between true and fabricated content (+4.15 points, d=1.82), while participants without any signal showed no detectable discrimination. A technical audit of 200 samples found that retrieval density alone is insufficient; surprisingly, a 'Consistency Veto' mechanism carried most of the discernment signal on dynamic queries. The paper concludes that effective transparency should shift from authorship disclosure to evidence visualization as AI-generated text becomes indistinguishable from human writing.