Metraipolis › archive › dc_ca8e7d63d38c

Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role — arXiv:2610.03410

Source
arXiv
Original
https://arxiv.org/abs/2610.03410
License (as archived)
CC0-1.0
Archived
2026-10-05T23:10:54.059Z
SHA-256 of the archived text
4b29af6a736c8017ec3cbed437c9874186cb9bcb1dfa9d47a70edbaebc38828c
Stable URL of this page
https://metraipolis.com/documento/dc_ca8e7d63d38c

How to cite

Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role — arXiv:2610.03410 — arXiv, https://arxiv.org/abs/2610.03410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca8e7d63d38c (Metraipolis archive dc_ca8e7d63d38c, sha256 4b29af6a736c8017ec3cbed437c9874186cb9bcb1dfa9d47a70edbaebc38828c)
BibTeX
@misc{dcca8e7d63d38c,
  title = {Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational Role — arXiv:2610.03410},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03410},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca8e7d63d38c; sha256 4b29af6a736c8017ec3cbed437c9874186cb9bcb1dfa9d47a70edbaebc38828c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contrastive representation learning is increasingly used to recover low-dimensional structure from neural recordings, but its output is typically validated by decoding accuracy rather than by the geometry of the manifold it produces. We apply CEBRA to EEG recorded from dyads in conversation, and analyze the resulting embedding, which training constrains to the 2D sphere. Labels describing the dyads, including the absolute difference between partners' autism-quotient scores, decode well above chance (0.77 against a 0.55 majority baseline for binary AQ magnitude; 0.44 against 0.25 for the six-class $|\Delta$AQ$|$ partition). However, the two permutation controls have notable differences in results: permuting labels over a frozen embedding yields p = 0.001, whereas retraining the encoder under each permutation yields p = 0.50. Only the latter tests the label rather than the geometry. Consistent with this, spherical mixture structure and per-class dispersion track identity rather than autism trait differences in dyads; frequency-band and non-oscillatory activity ablation controls do not change the results. However, participant-level model does separate from its identity-aware null (p = 0.0099) while speaker-versus-listener role analysis performs at chance in the same embedding, indicating a manifold organized by individual -- and, in contrast with current neurolinguistics models, almost invariant to speaking vs. listening. Based on these results, we suggest that retraining-based nulls should be the default for grouped-data contrastive embeddings.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Neurons and Cognition (q-bio.NC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.03410 — 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 2026-10-05T23:01:38.774Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).