Beyond “Made with AI”: Visualizing Provenance Density to Mitigate the Transparency Penalty

Zhang, Qing; Huang, Yifei; Lee, Juyoung; Starner, Thad; Rekimoto, Jun

doi:10.24963/ijcai.2026/857

Beyond “Made with AI”: Visualizing Provenance Density to Mitigate the Transparency Penalty

Qing Zhang, Yifei Huang, Juyoung Lee, Thad Starner, Jun Rekimoto

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Human-Centred AI. Pages 7712-7720.

https://doi.org/10.24963/ijcai.2026/857

Keywords

Human-Centred AI: AI Ethics, Trust, Fairnes
Human-Centred AI: Humans and AI
Human-Centred AI: Natural Language Processing

Abstract

As generative AI makes polished prose cheap to produce, users can no longer rely on fluency as a proxy for truth. We call this failure mode the Fluency Trap: users trust fluent hallucinations while also discounting accurate content once it is disclosed as AI-generated. Binary "Made with AI" labels respond with authorship disclosure, but they do not show what supports a claim. We propose Provenance Density, an evidence-visualization interface that shows the density of verified claims in a text. In a user study with 81 participants, an idealized Provenance Density interface produced a large discernment gap between truth and fabrication (+4.15 points, d=1.82), whereas participants given no signal showed no detectable discrimination. A technical audit with 200 samples shows that retrieval density alone is insufficient; unexpectedly, the Consistency Veto carries most of the discriminative signal on dynamic queries. As AI-generated content becomes indistinguishable from human writing, effective transparency must move from authorship disclosure toward evidence visualization.

Qing Zhang, Yifei Huang, Juyoung Lee, Thad Starner, and Jun Rekimoto. 2026. Beyond “Made with AI”: Visualizing Provenance Density to Mitigate the Transparency Penalty. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7712–7720. https://doi.org/10.24963/ijcai.2026/857

@inproceedings{ijcai2026p857,
  title     = {Beyond “Made with AI”: Visualizing Provenance Density to Mitigate the Transparency Penalty},
  author    = {Zhang, Qing and Huang, Yifei and Lee, Juyoung and Starner, Thad and Rekimoto, Jun},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7712--7720},
  year      = {2026},
  month     = {8},
  note      = {Human-Centred AI},
  doi       = {10.24963/ijcai.2026/857},
  url       = {https://doi.org/10.24963/ijcai.2026/857},
}

TY  - CPAPER
TI  - Beyond “Made with AI”: Visualizing Provenance Density to Mitigate the Transparency Penalty
AU  - Zhang, Qing
AU  - Huang, Yifei
AU  - Lee, Juyoung
AU  - Starner, Thad
AU  - Rekimoto, Jun
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7712
EP  - 7720
DO  - 10.24963/ijcai.2026/857
UR  - https://doi.org/10.24963/ijcai.2026/857
ER  -