Metraipolis › archive › dc_08127b5f2b4e
$t_0$: A Time-Series Foundation Model for Forecasting with Context — arXiv:2609.24559
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24559
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:07:49.747Z
- SHA-256 of the archived text
b324d6dc5d6db7f1f730eb4d6b14521d6aaffeedd43e727d0c9645bf1abd1690- Stable URL of this page
https://metraipolis.com/documento/dc_08127b5f2b4e
How to cite
$t_0$: A Time-Series Foundation Model for Forecasting with Context — arXiv:2609.24559 — arXiv (en), https://arxiv.org/abs/2609.24559 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08127b5f2b4e (Metraipolis archive dc_08127b5f2b4e, sha256 b324d6dc5d6db7f1f730eb4d6b14521d6aaffeedd43e727d0c9645bf1abd1690)
BibTeX
@misc{dc08127b5f2b4e,
title = {$t_0$: A Time-Series Foundation Model for Forecasting with Context — arXiv:2609.24559},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24559},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08127b5f2b4e; sha256 b324d6dc5d6db7f1f730eb4d6b14521d6aaffeedd43e727d0c9645bf1abd1690},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24559. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present $t_0$, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: $\texttt{t0-alpha}$ and $\texttt{t0-beta}$, respectively 102M and 256M parameters. Both condition their forecasts on target history, past covariates, and known-future covariates, without task-specific retraining. Their transformer layers alternate attention along time and across variates. They produce probabilistic forecasts through quantile predictions. Pretraining combines curated public data with synthetic generator families constructed to contain covariate-to-target dependencies. On GIFT-Eval, $\texttt{t0-alpha}$ reaches an aggregate CRPS of 0.4941, and $\texttt{t0-beta}$ a CRPS of 0.4738 and a MASE of 0.6865, third on both and within 4.0% of the best zero-shot TSFM. On fev-bench they score 42.2 and 46.7 in skill, the latter third again and 2.0 points behind the leader. We analyze $\texttt{t0-alpha}$ in depth. Known-future covariates raise its skill by 6.3 percentage points across 30 tasks. The report also examines its calibration, its rollout strategy on long horizons, and its robustness to missing data. On the Victoria electricity-demand benchmark, $\texttt{t0-beta}$ is among the most accurate models with a context of nearly a year. In an independent Macrocosm evaluation of hourly ERCOT prices over 29 months, both cut the MAE of the lagged-price baseline by 38%.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.24559 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:58:09.428Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).