Metraipolis › archive › dc_c3f57fb4e488

When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting — arXiv:2609.11282

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11282
License (as archived): CC0-1.0
Archived: 2026-10-16T05:23:53.807Z
SHA-256 of the archived text: 5e01e4b6f18bc17f87f1930fd1869f907186b7bea1d95160ec9572f64d862673
Stable URL of this page: https://metraipolis.com/documento/dc_c3f57fb4e488

How to cite

When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting — arXiv:2609.11282 — arXiv (en), https://arxiv.org/abs/2609.11282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3f57fb4e488 (Metraipolis archive dc_c3f57fb4e488, sha256 5e01e4b6f18bc17f87f1930fd1869f907186b7bea1d95160ec9572f64d862673)

BibTeX

@misc{dcc3f57fb4e488,
  title = {When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting — arXiv:2609.11282},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11282},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3f57fb4e488; sha256 5e01e4b6f18bc17f87f1930fd1869f907186b7bea1d95160ec9572f64d862673},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know whether a text annotation meaningfully contributes to the forecasters prediction? This is an information-theoretic question, but to evaluate whether information-theoretic metrics can reliably measure the predictive value an annotation provides, a ground truth benchmark is needed, and none currently exist. We create a synthetic time series signal with annotations in three categories: semantically correct, incorrect, and irrelevant. Because the data generation process is fully controlled, ground-truth information content is known exactly, enabling principled evaluation of six complementary mutual information estimators (KSG, MINE, InfoNCE, CCA, PID and V-information). We show that all six estimators identify correct annotations as most informative, and are able to audit the quality of mixed text corpora, choosing the annotations that result in the best downstream forecasting results without the need for model training. Our benchmark identifies limitations of each estimator, and these are validated on seven real-world datasets, which show how estimator performance differs on weak signals. Finally, we establish practical rules for implementing these metrics for annotation auditing and fusion selection.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2609.11282 — 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 2026-10-16T05:17:51.998Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).