A couple of interesting Arrow-related papers have appeared at conferences recently: Integrating Lightweight Compression Capabilities into Apache Arrow [1] Magpie: Python at Speed and Scale using Cloud Backends [2]
I’m sharing them so that people are aware of the evolving state-of-the-art. Julian [1] https://www.researchgate.net/publication/342996896_Integrating_Lightweight_Compression_Capabilities_into_Apache_Arrow <https://www.researchgate.net/publication/342996896_Integrating_Lightweight_Compression_Capabilities_into_Apache_Arrow> [2] http://cidrdb.org/cidr2021/papers/cidr2021_paper08.pdf <http://cidrdb.org/cidr2021/papers/cidr2021_paper08.pdf>