Metraipolis › archive › dc_698072890695

Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders — arXiv:2610.10850

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10850
License (as archived)
CC0-1.0
Archived
2026-10-09T06:20:59.506Z
SHA-256 of the archived text
a03bc92a77257d5ee4f2fce8872a209cf95939f104d59186c75fbce6c389b014
Stable URL of this page
https://metraipolis.com/documento/dc_698072890695

How to cite

Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders — arXiv:2610.10850 — arXiv (en), https://arxiv.org/abs/2610.10850 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_698072890695 (Metraipolis archive dc_698072890695, sha256 a03bc92a77257d5ee4f2fce8872a209cf95939f104d59186c75fbce6c389b014)
BibTeX
@misc{dc698072890695,
  title = {Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders — arXiv:2610.10850},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10850},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_698072890695; sha256 a03bc92a77257d5ee4f2fce8872a209cf95939f104d59186c75fbce6c389b014},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10850. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As AI models move toward clinical decision-making and personalized treatment, understanding \emph{what} a model learns is important beyond predictive accuracy alone. We investigate whether personalized latent dynamics reveal clinically associated differences even when predictive fit is similar. A lightweight CNN--Transformer EEG foundation model pretrained on the Temple University EEG Corpus (TUEG) extracts segment-level representations. Using the Temple University Epilepsy Corpus (TUEP), representations are mapped to a shared latent-state space, and sparse multinomial logistic transition distributions (mLTD) are fit independently to each subject to obtain personalized transition-dependency graphs $W_n$. Analyses include $n{=}198$ subjects (99 epilepsy / 99 non-epilepsy). At $k{=}4$, epilepsy subjects exhibit substantially denser learned dependency structure ($p{=}1.1\times10^{-7}$), with the same pattern at $k{=}6$ (19.90 vs. 13.46; $p{=}5.2\times10^{-5}$). Graph-derived features provide moderate group discrimination under 5-fold subject-wise cross-validation (AUROC 0.68 at $k{=}4$; 0.65 at $k{=}6$). In contrast, held-out log-likelihood is nearly identical between groups at $k{=}4$ ($-0.992$ vs. $-0.991$; $p{=}0.95$), with similarly matched next-state prediction (AUROC 0.855 vs. 0.861; $p{=}0.54$). Thus, similar predictive fit does not imply similar learned dynamics: groups can be comparably predictable while differing substantially in the internal dynamical structure learned by personalized models. This distinction motivates evaluating learned structure alongside predictive performance in personalized clinical models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Signal Processing (eess.SP); Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2610.10850 — 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 2026-10-09T05:50:30.991Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).