Metraipolis › archive › dc_4f41784ed2cd

DODR: Deterministic Operator-Driven Reasoning in Latent Space — arXiv:2609.04782

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04782
License (as archived)
CC0-1.0
Archived
2026-10-16T22:20:54.474Z
SHA-256 of the archived text
5611253f690abab2fd3f13c2dc429767fb443e3b188744267c15b35cf431184a
Stable URL of this page
https://metraipolis.com/documento/dc_4f41784ed2cd

How to cite

DODR: Deterministic Operator-Driven Reasoning in Latent Space — arXiv:2609.04782 — arXiv (en), https://arxiv.org/abs/2609.04782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f41784ed2cd (Metraipolis archive dc_4f41784ed2cd, sha256 5611253f690abab2fd3f13c2dc429767fb443e3b188744267c15b35cf431184a)
BibTeX
@misc{dc4f41784ed2cd,
  title = {DODR: Deterministic Operator-Driven Reasoning in Latent Space — arXiv:2609.04782},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04782},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f41784ed2cd; sha256 5611253f690abab2fd3f13c2dc429767fb443e3b188744267c15b35cf431184a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoregressive (AR) large language models formulate reasoning as token-level probabilistic sampling, which induces three fundamental defects in complex logical reasoning: error accumulation, probability substituting necessity, and the linear-chain information bottleneck. This paper proposes the Deterministic Operator-Driven Reasoning in Latent Space architecture (DODR), which reconstructs reasoning as reasoning-graph computation in a high-dimensional linear-algebraic space. Reasoning states are represented as snapshot vectors whose primitives are semantic units (phrases or sentences) rather than tokens, and each inference step is a deterministic matrix operation with no token sampling. Peirce's three inference types are formalized as three trainable matrix operators: a rank-deficient deduction operator (information collapse), a full-rank induction operator (information expansion), and an abduction operator defined as the Moore-Penrose pseudo-inverse of deduction (information hypothesizing). We prove that the operator set is minimal and complete given Peirce's trichotomy, that no single "super-operator" can realize all three types (a rank obstruction), and that reasoning graphs are Turing-complete with contractive backflow converging by Banach's fixed-point theorem. Experiments on 503 sample records (420 deduplicated samples) across dedicated and end-to-end settings show: deduction loss converges to 1.40e-05; induction achieves 0.9996 generalization coverage with 20/20 hard vetoes on counterexamples; abduction solutions exceed the random baseline by 28x with judgment accuracies of 72.5% (58/80, Wilson 95% CI [61.9%, 81.1%]) and 81.7% (49/60, CI [70.1%, 89.4%]); frozen operators attain 100% (60/60) on unseen cross-domain deduction. The architecture provides a structural zero-hallucination guarantee and a three-layer continual-learning mechanism. All data and code are released.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.04782 — 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 2026-10-16T22:18:11.389Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).