FlowState

Summary

FlowState is a compact SSM-based time-series foundation model with a functional basis decoder for sampling-rate-invariant forecasting.

Role In The Wiki

FlowState anchors the continuous-basis decoding direction: the model maps numeric time-series histories into coefficient space and samples a continuous forecast at the requested temporal resolution.

Evidence

Relation To Foundation TSFM Agenda

Use the source-level agenda mapping in flowstate-2025 rather than duplicating verdict rows here.

At the entity level, FlowState anchors the continuous-basis decoding direction: the model maps numeric time-series histories into coefficient space and samples a continuous forecast at the requested temporal resolution. This page should stay as the object card; source pages carry slot-level verdicts, evidence, and missing pieces.