Reproduce “CrowdForge: Effects of Audio and Visual Audience Participation Modalities on Agency, Collaboration, and Engagement in AI-Mediated MR Performances” 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
Torin Hopkins, Shih-Yu Ma, Zander Trafton-Hancock, Ellen Yi-Luen Do, Luca Turchet
CrowdForge lets audiences vote on AI-generated music and a mixed-reality stage during guitarist-and-DJ performances. It compares audio-only, visual-only, and combined participation across two performances. Participants said visible stage changes were easier to notice than subtle musical effects, but agency ratings did not differ significantly by condition. Among 14 respondents, only human guitar tone rated above neutral (p = 0.007, r = 0.72).
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.