Metraipolis › archive › dc_7fbe8ebf818f

State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking — arXiv:2608.03425

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03425
License (as archived)
CC0-1.0
Archived
2026-10-31T12:16:14.807Z
SHA-256 of the archived text
a97b30236086c66c7f176257470f849540db0ddf138eca42e1ad52860f756696
Stable URL of this page
https://metraipolis.com/documento/dc_7fbe8ebf818f

How to cite

State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking — arXiv:2608.03425 — arXiv (en), https://arxiv.org/abs/2608.03425 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fbe8ebf818f (Metraipolis archive dc_7fbe8ebf818f, sha256 a97b30236086c66c7f176257470f849540db0ddf138eca42e1ad52860f756696)
BibTeX
@misc{dc7fbe8ebf818f,
  title = {State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking — arXiv:2608.03425},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03425},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fbe8ebf818f; sha256 a97b30236086c66c7f176257470f849540db0ddf138eca42e1ad52860f756696},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03425. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the dominance of massive language models, leading paradigms like Transformers and Mamba fundamentally falter at continuous deterministic state tracking, suffering from catastrophic out-of-distribution (OOD) collapse when generalizing to extended sequences. To shatter this bottleneck, we present the \textbf{Complex State Propagator (CSP)}, a radically minimalist recurrent paradigm that operates strictly on the complex phase manifold without intermediate output projections, amplitude modulations, or per-step non-linearities. Crucially, we unveil an unprecedented architectural marvel: \textbf{the phase signal survives extreme depth with absolute zero informational attenuation}. By implementing an exact four-quadrant \textbf{Coordinate-to-Phase (C-to-2)} transformation governed by the \(\text{atan2}(y, x)\) activation, CSP forces the continuous optimization landscape to seamlessly align with discrete cyclic groups. Remarkably, with a mere \textbf{3-layer hidden topology} trained on short inputs (length 16),CSP demonstrates absolute mathematical purity, achieving a nearly $100\%$ validation accuracy and F1-score when generalized to a $4\times$ prolonged OOD length of 64 on the canonical Mod-3 tracking task. Our work establishes complex-valued, pure-phase propagation not merely as a compact alternative, but as a dominant frontier that beats heavy networks at a fraction of their size.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03425 — 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 2026-10-31T12:05:52.790Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).