Metraipolis › archive › dc_40473a17ced2

WavePhaseNet: A DFT-Based Method for Constructing Semantic Conceptual Hierarchy Structures (SCHS) — arXiv:2602.14419

Source
arXiv (en)
Original
https://arxiv.org/abs/2602.14419
License (as archived)
CC0-1.0
Archived
2026-10-19T05:40:08.326Z
SHA-256 of the archived text
cdc45c91aeb45bbc64981c5739341686365030c864b08f21b6e9cc86fdcaa32a
Stable URL of this page
https://metraipolis.com/documento/dc_40473a17ced2

How to cite

WavePhaseNet: A DFT-Based Method for Constructing Semantic Conceptual Hierarchy Structures (SCHS) — arXiv:2602.14419 — arXiv (en), https://arxiv.org/abs/2602.14419 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_40473a17ced2 (Metraipolis archive dc_40473a17ced2, sha256 cdc45c91aeb45bbc64981c5739341686365030c864b08f21b6e9cc86fdcaa32a)
BibTeX
@misc{dc40473a17ced2,
  title = {WavePhaseNet: A DFT-Based Method for Constructing Semantic Conceptual Hierarchy Structures (SCHS) — arXiv:2602.14419},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2602.14419},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_40473a17ced2; sha256 cdc45c91aeb45bbc64981c5739341686365030c864b08f21b6e9cc86fdcaa32a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2602.14419. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically demonstrating that hallucination is an inevitable structural limitation. The embedding space functions as a conditional expectation over a {\sigma}-algebra, and its failure to be isomorphic to the semantic truth set fundamentally causes logical consistency breakdown. WavePhaseNet Method The authors propose WavePhaseNet, which explicitly constructs a Semantic Conceptual Hierarchy Structure (SCHS) using Discrete Fourier Transform (DFT). By applying DFT along the sequence dimension, semantic information is decomposed into frequency bands: low-frequency components capture global meaning and intent, while high-frequency components represent local syntax and expression. This staged separation enables precise semantic manipulation in diagonalized space. Dimensionality Reduction GPT-4's 24,576-dimensional embedding space exhibits a 1/f spectral structure based on language self-similarity and Zipf's law. Through cumulative energy analysis, the authors derive that approximately 3,000 dimensions constitute the lower bound for "complete representation." This demonstrates that reduction from 24,576 to 3,000 dimensions preserves meaning and intent while enabling rigorous reasoning and suppressing hallucination. Cohomological Consistency Control The reduced embedding space, constructed via cohomological regularization over overlapping local windows, allows defining a graph structure and cochain complex. This quantifies inconsistencies among local inferences as coboundary-based losses. Applying harmonic projection based on Hodge theory positions cohomology as a computable regularization principle for controlling semantic consistency, extracting maximally consistent global representations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.LG).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2602.14419 — 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 2026-10-19T05:18:32.515Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).