# DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces

arXiv: https://arxiv.org/abs/2509.23505 · HTML: https://mlsanity.com/paper/2509.23505/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2025.

## Built on by (most cited first, 6 of 6)

- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- ["I Didn't Make the Micro Decisions": Measuring, Inducing, and Exposing Goal-Level AI Contributions in Collaboration](https://mlsanity.com/paper/2605.21363/) (2026)
- [TreeWriter: AI-Assisted Hierarchical Planning and Writing for Long-Form Documents](https://mlsanity.com/paper/2601.12740/) (2026)
- [Human-AI Interaction Traces as Blackout Poetry: Reframing AI-Supported Writing as Found-Text Creativity](https://mlsanity.com/paper/2604.09605/) (2026)
- [StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents](https://mlsanity.com/paper/2608.18050/) (2026)
- [When No One Owns the Judgment: Accountability Under Contribution Dissolution in Human-AI Collaboration](https://mlsanity.com/paper/2609.29312/) (2026)

## Abstract (arXiv)

As generative AI becomes part of everyday writing, questions of transparency and productive human effort are increasingly important. Educators, reviewers, and readers want to understand how AI shaped the process. Where was human effort focused? What role did AI play in the creation of the work? How did the interaction unfold? Existing approaches often reduce these dynamics to summary metrics or simplified provenance. We introduce DraftMarks, an augmented reading tool that surfaces the human-AI writing process through familiar physical metaphors. DraftMarks employs skeuomorphic encodings such as eraser crumbs to convey the intensity of revision, and masking tape or smudges to mark AI-generated content, simulating the process within the final written artifact. By using data from writer-AI interactions, DraftMarks' algorithm computes various collaboration metrics and writing traces. Through a formative study, we identified computational logic for different readership, and evaluated DraftMarks for its effectiveness in assessing AI co-authored writing.