Learn more about the technology, based on years of research at Carnegie Mellon University
Rockfish is built on peer-reviewed work from Carnegie Mellon on time-series data generation, rare event synthesis, and privacy-preserving generative models — published at NeurIPS, ICML, AAAI, SIGCOMM, and IMC. The science is what makes the synthetic data trustworthy.
CAIS 2026 · CMU
Testing time-series agents with synthetic data
How to generate realistic, domain-specific evaluation suites that expose failures in AI analytics agents before they reach production — using synthetic time-series data and grounded Q&A pairs.
IMC - CMU
Synthetic time series data
The foundational research establishing that generative models can produce realistic networked time-series data — statistically faithful enough to replace or augment production datasets for training and testing.
AAAI · CMU
Generating rare events in synthetic data
A technique for synthesizing realistic examples of rare occurrences — the anomaly spikes, failure cascades, and edge cases that almost never appear in production data but are critical for model robustness.