A systematic benchmark shows Arrow, Parquet, and ORC each excel in different dimensions and all compress ML embeddings poorly, motivating co-designed formats.
www.json.org/json-en
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Data Formats in Analytical DBMSs: Performance Trade-offs and Future Directions
A systematic benchmark shows Arrow, Parquet, and ORC each excel in different dimensions and all compress ML embeddings poorly, motivating co-designed formats.