Metraipolis › archive › dc_0d33b606567d

When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting — arXiv:2608.25128

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.25128
License (as archived)
CC0-1.0
Archived
2026-10-18T02:27:58.681Z
SHA-256 of the archived text
b1401ba3b5c45a6108c95b8152d0669a45997ba6309fe28cdf99aa8b1f9b637b
Stable URL of this page
https://metraipolis.com/documento/dc_0d33b606567d

How to cite

When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting — arXiv:2608.25128 — arXiv (en), https://arxiv.org/abs/2608.25128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d33b606567d (Metraipolis archive dc_0d33b606567d, sha256 b1401ba3b5c45a6108c95b8152d0669a45997ba6309fe28cdf99aa8b1f9b637b)
BibTeX
@misc{dc0d33b606567d,
  title = {When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting — arXiv:2608.25128},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.25128},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d33b606567d; sha256 b1401ba3b5c45a6108c95b8152d0669a45997ba6309fe28cdf99aa8b1f9b637b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.25128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-modal time series forecasting methods integrate auxiliary context into temporal predictions through increasingly sophisticated fusion mechanisms. A growing body of work reports substantial gains, yet it is often unclear whether they reflect genuine use of the context or incidental architectural effects. We ask a narrower, checkable question: when can auxiliary context help a forecaster at all? We identify two dataset-level conditions that must both hold: (1) the target is not dominated by a last-value shortcut (low autocorrelation rho_h), and (2) the context carries information about the target beyond history (non-zero conditional mutual information delta; when delta=0 no predictor can benefit---a distribution-free result). Through controlled experiments on MoME (a 14.3B-parameter mixture-of-experts model, 6 datasets, 10 seeds) and four additional fusion mechanisms implemented within a single-backbone testbed (5 datasets), we find that when both conditions hold, text-conditioned expert modulation contributes a sizeable MSE reduction; when either fails, the contribution collapses to the capacity floor of the modulation pathway and carries no context-attributable signal. We establish causality through two interventions: adding a shortcut to MoME suppresses routing contribution by 77-93% across 3 datasets; progressively corrupting context quality drives the context-specific benefit from +44% to negative. We validate the autocorrelation component of our diagnostic on 27 Monash Archive datasets. We provide a calibrated pre-training diagnostic that, on the datasets we test, yields no false positives in well-powered settings. We are explicit about the asymmetry of our evidence: the negative arm is broadly reliable, while the large positive magnitudes come from a single model family (MoME) and are corroborated only in direction by the testbed.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-27 in stat.AP).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Applications (stat.AP).
Pagina del lavoro: https://arxiv.org/abs/2608.25128 — 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 2026-10-18T02:27:21.261Z dalla pagina https://arxiv.org/catchup/stat.AP/2026-08-27?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).