The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting
A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different question: whether \emph{adding context}, a longer lookback, a retrieval plug-in, or a pretrained model, will help. These are not the same question. The value of context is a property of the operating point, not of the series. Any index built from the power spectrum is invariant under phase randomization, whereas the beyond-second-order value that retrieval and foundation models supply is not, because a phase-randomized series is asymptotically
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Mert Onur Cakiroglu →
“The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting”
- LinkedLinked via arxiv author · 85%Mehmet Dalkilic →
“The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting”
- LinkedLinked via arxiv author · 85%Hasan Kurban →
“The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting”
- FuzzySimilar title/name (fuzzy) · 59%sktime/pytorch-forecasting →
“Fuzzy title match (0.73): “The Spectrum Is Not Enough: When Context Helps Time-Series F” ≈ “sktime/pytorch-forecasting””
- FuzzySimilar title/name (fuzzy) · 59%amazon-science/chronos-forecasting →
“Fuzzy title match (0.73): “The Spectrum Is Not Enough: When Context Helps Time-Series F” ≈ “amazon-science/chronos-forecasting””