Reproduce “Who Shaped What? Untangling Human and AI Creative Contributions Through Spatial Provenance in Image Editing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Riya Sahni, Christine Dierk, Lydia Chilton, Eunyee Koh, Doga Dogan, Tongyu Zhou
Roop links editing suggestions, responses, previews, and choices to image regions and summarizes recorded negotiation in a heat map. In a study of 20 participants, 14 rated their creative contribution lower during AI-suggested than user-initiated editing; medians were 4 and 5, respectively. Participants’ accounts show activity alone does not establish contribution, and the workflow comparison does not isolate suggestion effects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.