Metraipolis › archive › dc_561ec65ef97f

Transferable Evidence Reconstruction for Longitudinal Glucose Representations — arXiv:2609.28199

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.28199
License (as archived): CC0-1.0
Archived: 2026-10-08T10:57:37.426Z
SHA-256 of the archived text: c767d82d36ea2eaaf4b012b7c53e7285f35bd2bd5e3b854bf4c9de901f989766
Stable URL of this page: https://metraipolis.com/documento/dc_561ec65ef97f

How to cite

Transferable Evidence Reconstruction for Longitudinal Glucose Representations — arXiv:2609.28199 — arXiv (en), https://arxiv.org/abs/2609.28199 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_561ec65ef97f (Metraipolis archive dc_561ec65ef97f, sha256 c767d82d36ea2eaaf4b012b7c53e7285f35bd2bd5e3b854bf4c9de901f989766)

BibTeX

@misc{dc561ec65ef97f,
  title = {Transferable Evidence Reconstruction for Longitudinal Glucose Representations — arXiv:2609.28199},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28199},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_561ec65ef97f; sha256 c767d82d36ea2eaaf4b012b7c53e7285f35bd2bd5e3b854bf4c9de901f989766},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28199. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long physiological recordings contain many routine measurements, while predictive information often lies in rare events, sustained burden, and recurring patterns. These properties can be computed as label-free evidence, but directly using them as features leaves limited labeled data to separate reproducible associations from sample-specific ones. Learning to reconstruct evidence can exploit unlabeled recordings, yet joint reconstruction does not explicitly require the decoding rule to transfer across individuals. We introduce transferable evidence reconstruction (TER): a Ridge regressor fits evidence from representations in one group and predicts it in an identity-disjoint group without refitting. The transfer error trains the encoder through the differentiable fit. For continuous glucose monitoring (CGM), clock-aware encoding preserves the multi-day content and timing needed for evidence recovery. Matched interventions connect the gains to reduced fitting-group sensitivity, with structured targets improving on raw recovery. Across ten leading CGM and time-series baselines, TER sets a new best metric on 12/14 phenotype tasks and exceeds the strongest prior overall PR-AUC/ROC-AUC/Macro-F1 by 4.95/4.43/0.66 percentage points; the PR-AUC and ROC-AUC gains are $2.6\times$ and $2.2\times$ the respective gaps between the two strongest baselines. Meal-response and future-CGM studies further demonstrate predictive utility. TER thus uses meaningful signal properties to supervise not only what a representation preserves, but how reliably it can be read across individuals.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.28199 — 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 2026-10-08T10:06:16.775Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).