{
  "abstract": "Financial and socio-economic forecasting often requires information beyond numerical histories, as policy statements, news reports, institutional releases, and event descriptions may signal structural regimes or short-term shocks. Recent multimodal time-series methods incorporate timestamp-aligned texts as auxiliary variables in numerical forecasting backbones, but typically treat all textual signals as homogeneous local covariates. This overlooks an important distinction between local event-level text and broader contextual narratives. This paper proposes GLoR-Forecast (Global-Local Text Routing for Forecasting), a state-contingent textual fusion framework for multimodal time-series forecasting. The model encodes timestamp-aligned texts with a frozen language model, projects them into compact local textual variables, and attentively aggregates them into a global contextual representation. A text router then uses the current numerical time-series state as a query to dynamically weight local and global textual features. The fused representation augments the numerical sequence and can be used with standard forecasting backbones; we instantiate it with iTransformer. Experiments on nine Time-MMD domains show consistent gains over TaTS, reducing average MSE by 5.8% and MAE by 4.7%. The strongest improvements appear in Economy, Social Good, Traffic, and Agriculture, suggesting that state-dependent textual routing helps exploit both slow-moving structural context and short-term event shocks.",
  "abstract_shown": true,
  "affiliations": [
    "School of Economics and Management, China University of Geosciences"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Jianing Li"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/76v2f8wjkm8f0.bib",
  "cited_by": 0,
  "doi": "10.1038/s41598-026-67974-0",
  "fulltext_url": "https://doi.org/10.1038/s41598-026-67974-0",
  "id": "76v2f8wjkm8f0",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://doi.org/10.1038/s41598-026-67974-0",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "Q"
    ],
    [
      "lcc",
      "R"
    ],
    [
      "openalex",
      "1711|Time Series Analysis and Forecasting"
    ]
  ],
  "openalex": "W7213922448",
  "pdf_url": "https://www.nature.com/articles/s41598-026-67974-0_reference.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/76v2f8wjkm8f0.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T14:20:57Z",
      "native_id": "11e8b6c8830d4bb783186cfebca50cdc",
      "source": "doaj",
      "url": "https://doi.org/10.1038/s41598-026-67974-0"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R",
      "subfield": "general"
    }
  ],
  "title": "GLoR-forecast: state-contingent global-local text routing for financial and socio-economic time-series forecasting",
  "title_text": "GLoR-forecast: state-contingent global-local text routing for financial and socio-economic time-series forecasting",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T14:21:17Z",
  "url": "https://research.draconitic.com/paper/76v2f8wjkm8f0",
  "venue": "Scientific Reports",
  "versions": []
}