Metraipolis › archive › dc_91c367765d8a

TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split — arXiv:2609.28506

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28506
License (as archived)
CC0-1.0
Archived
2026-10-08T04:25:38.185Z
SHA-256 of the archived text
c7301c4e99ffa02b123a27ea6ee4ef9652063c1705c2d1f67d5d218b9e844cef
Stable URL of this page
https://metraipolis.com/documento/dc_91c367765d8a

How to cite

TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split — arXiv:2609.28506 — arXiv (en), https://arxiv.org/abs/2609.28506 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_91c367765d8a (Metraipolis archive dc_91c367765d8a, sha256 c7301c4e99ffa02b123a27ea6ee4ef9652063c1705c2d1f67d5d218b9e844cef)
BibTeX
@misc{dc91c367765d8a,
  title = {TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split — arXiv:2609.28506},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28506},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_91c367765d8a; sha256 c7301c4e99ffa02b123a27ea6ee4ef9652063c1705c2d1f67d5d218b9e844cef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28506. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The two entries above it belong to the leaderboard's agentic category, multi-step systems that use agents or language models to reason about, generate or select forecasts. TW3Cast runs no agent and no language model. Its selection is a table computed once on the training split and then frozen, and its experts are public foundation models lightly fine-tuned on those training splits. For each of the 97 dataset, frequency and horizon configurations, the table serves one of four modes: a specialist, which is a LoRA or full fine-tune of Chronos-2, TiRex or Toto whose training data was cleaned and enriched by explicit rules; a quantile blend that contains a specialist; a blend of base models; or a selection tournament played on a backtest carved from the training split. Every decision in the table was taken on that backtest. A specialist is admitted the moment it beats the tournament there, so a candidate costs a few megabytes and minutes of GPU time, and a failed candidate changes nothing. Three guarded mechanisms protect the selection from its own biases: a dual accuracy and calibration criterion, an asymmetric margin against candidates that saw the series during training, and conservative per-window gates. The selection rules themselves were chosen inside a temporal meta-backtest. The best base model served alone reaches a mean MASE rank of 33.8, the tournament served on every configuration reaches 38.0, and the full router reaches 19.4. The routing table, the expert index, the pinned base-model revisions, the submitted score file and the dated snapshot of the public scores are released, and every leaderboard number in this paper regenerates from them by one script.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.28506 — 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 2026-10-08T03:50:57.647Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).