# Beyond "Made with AI": Visualizing Provenance Density to Mitigate the Transparency Penalty

arXiv: https://arxiv.org/abs/2609.03460 · HTML: https://mlsanity.com/paper/2609.03460/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [Human heuristics for AI-generated language are flawed](https://mlsanity.com/paper/2206.07271/) (2022)
- [Epistemic Injustice in Generative AI](https://mlsanity.com/paper/2408.11441/) (2024)
- [Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models](https://mlsanity.com/paper/2507.07484/) (2025)
- [Penalizing Transparency? How AI Disclosure and Author Demographics Shape Human and AI Judgments About Writing](https://mlsanity.com/paper/2507.01418/) (2025)
- [Understanding Reader Perception Shifts upon Disclosure of AI Authorship](https://mlsanity.com/paper/2510.24011/) (2025)

## Abstract (arXiv)

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.