Date
Publisher
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.
Study at a glance
- Question: How can visual marks show readers and educators how humans and AI collaborated on a piece of writing?
- Setting and data: Data from writer-AI interactions.
- Method: Formative study evaluating a tool's effectiveness in assessing AI co-authored writing.
Why it matters
As generative AI becomes part of everyday writing, educators and readers want to understand how AI shaped the process and where human effort was focused. Yet existing approaches often reduce these dynamics to summary metrics or simplified provenance.
Key findings
- DraftMarks visualizes the co-writing process using physical metaphors, such as eraser crumbs for revision intensity and tape or smudges for AI-generated text.
- The tool's algorithm computes collaboration metrics and writing traces from user interactions to show how human effort and AI shaped an artifact.
- Different types of readers require distinct computational logic to effectively review and evaluate writing co-authored with AI.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
