Benchmark RadarSeq2Synth
Seq2Synth evaluates temporal fidelity of synthetic sequential tabular data across timestamp, cross-sectional, longitudinal, structural, and privacy dimensions, using a taxonomy to determine applicable metrics. It spans seven core datasets and multiple generators.
- Released
- 2026-07-17
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Addresses the gap in evaluating temporal structure in synthetic tabular data, which static metrics miss, providing a standardized framework for researchers and practitioners.
Motivation
Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and data-driven research, but evaluating their fidelity remains difficult because temporal structure is easily lost under conventional tabular metrics.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.