{
  "abstract": "Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting and transferable representation learning, classification still typically requires fitting a task-specific classifier on each target dataset, while individual channels of multivariate inputs are often encoded independently. We introduce ChorusTIC, a classification-native foundation model for in-context classification across heterogeneous channel configurations without target-task parameter updates. ChorusTIC combines episode-consistent Random Subchannel Slot Concatenation with a shared dual-axis encoder to model temporal and cross-channel interactions and map variable channel configurations into a fixed-width representation independent of the original channel count. It then calibrates feature axes using context-derived distributions and predicts query labels through leakage-protected in-context learning. We pretrain ChorusTIC solely on synthetic labeled episodes comprising context and query sets that share a task background, with classes distinguished by sparse temporal or cross-channel rules. Evaluations on the complete UEA-30 and UCR-128 archives show strong full-context and low-label performance without target-specific classifier fitting.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.24033",
  "author_total": 9,
  "authors": [
    {
      "name": "Juntao Fang"
    },
    {
      "name": "Shifeng Xie"
    },
    {
      "name": "Ruichu Cai"
    },
    {
      "name": "Shengji Zheng"
    },
    {
      "name": "Zijian Li"
    },
    {
      "name": "Keli Zhang"
    },
    {
      "name": "Lujia Pan"
    },
    {
      "name": "Themis Palpanas"
    },
    {
      "name": "Zhifeng Hao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/agx7crsp2we48.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.24033",
  "fulltext_url": null,
  "id": "agx7crsp2we48",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.24033",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1711|Time Series Analysis and Forecasting"
    ]
  ],
  "openalex": "W7204500144",
  "pdf_url": "https://arxiv.org/pdf/2608.24033",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/agx7crsp2we48.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:58Z",
      "native_id": "2608.24033",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.24033"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning",
  "title_text": "ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:58Z",
  "url": "https://research.draconitic.com/paper/agx7crsp2we48",
  "venue": "arXiv",
  "versions": []
}