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.