Reproduce “Transactional Data Change for Real-Time Analytics in Lakehouses” 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
Dongyang Geng, Haoqiong Bian, Zinuo Li, Haoyue Li
Retina brings transaction-source updates into lakehouse analytics by appending row versions rather than rewriting immutable files. Queries filter versions against a timestamped snapshot, coordinated with replay by a watermark protocol. Tests report median freshness at the 10-millisecond level and HyBench P99 below 250 milliseconds; on HyBench SF1333, 16-node stable throughput reached 3,203.8K rows per second for that workload and setup.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.