Pith. sign in

Timeflow: Towards stochastic-aware and efficient time series generation via flow matching modeling,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Evaluating Generative Time-Series Models on Data with Point Masses

cs.LG · 2026-08-10 · conditional · novelty 6.0

Rolling-origin evaluation windows misrepresent the atom mass of intermittent time series, a permutation control isolates coupling contributions at fixed CRPS, and an autoregressive hurdle beats a conditional flow on five of six datasets under run-length statistics.

citing papers explorer

Showing 1 of 1 citing paper.

  • Evaluating Generative Time-Series Models on Data with Point Masses cs.LG · 2026-08-10 · conditional · none · ref 3

    Rolling-origin evaluation windows misrepresent the atom mass of intermittent time series, a permutation control isolates coupling contributions at fixed CRPS, and an autoregressive hurdle beats a conditional flow on five of six datasets under run-length statistics.