Metraipolis › archive › dc_fd8f9aaa4a50

Measurement-Gated Provenance Attenuation for Frozen EEG Representations — arXiv:2609.32889

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32889
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:56.211Z
SHA-256 of the archived text
3dfbad2fc0e51ca31b86351f83d0f5a8a347962a1f00f160e379e6f1c7954978
Stable URL of this page
https://metraipolis.com/documento/dc_fd8f9aaa4a50

How to cite

Measurement-Gated Provenance Attenuation for Frozen EEG Representations — arXiv:2609.32889 — arXiv (en), https://arxiv.org/abs/2609.32889 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd8f9aaa4a50 (Metraipolis archive dc_fd8f9aaa4a50, sha256 3dfbad2fc0e51ca31b86351f83d0f5a8a347962a1f00f160e379e6f1c7954978)
BibTeX
@misc{dcfd8f9aaa4a50,
  title = {Measurement-Gated Provenance Attenuation for Frozen EEG Representations — arXiv:2609.32889},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32889},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd8f9aaa4a50; sha256 3dfbad2fc0e51ca31b86351f83d0f5a8a347962a1f00f160e379e6f1c7954978},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32889. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Frozen EEG representations retain acquisition signatures as well as neural activity. Source predictability alone does not identify what should be removed: it can reflect measurement effects or genuine biological and population differences, which should not be erased. We propose Measurement-Gated Provenance Attenuation (MGPA), built on one principle: measurement evidence determines where correction may act, and preserved information determines what it should aim for. Paired measurement contrasts define a gate outside which nothing changes; inside it, the source score is moved to the value the preserved coordinates already predict: for a fixed affine score, this keeps the same information as any target set by those coordinates and needs the least expected squared movement. Closed-form and critic-guided iterative constructions apply it without source identity or encoder retraining. Three studies test the principle at increasing distance from its assumptions. Under controlled reference changes, where the source-task association is known, MGPA brings source to near chance with task performance unchanged, whereas erasing what predicts source (LEACE) lowers frozen-task AUROC from .753 to .656 while barely touching source; ablations attribute the attenuation to the gate's directions and 2.7x less movement to the conditional target. Across recordings from different devices and electrodes, iterative correction lowers source accessibility while preserving or improving task performance. Finally, one iterative map selected on one task and reused unchanged on existing heads for two others raises their worst-association AUROC (lowest over device-label shifts) by .057 and .019 over LEACE, at a cost to those heads while the training association holds. A reusable correction shows its value in how an existing predictor behaves once acquisition cues stop being reliable, not only in what a probe can read.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32889 — 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 2026-10-07T22:14:27.794Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).