Reproduce “Floor It, Then Fill It: Simulating Creator Ecosystems for Fair Video-Content Recommendation Systems at Billion User Scale” 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
Sohini Roychowdhury, Long Sha, Sunand Agarwal, Payal Kamboj, Shuyang Chen, Junlin Zhang, Scott Chen, Hui Zhang
The authors simulate view allocation for creators over 12 weeks, topping up toward 90% of a target after crediting organic views, then allocating the remainder with a reward favoring creators below parity. Under a graduated target and 70% reserve, parity-gap yields more stable ranks and less funded-status turnover than VPV-only; simulated small-creator organic reach grows about 33% weekly, not established online.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.