Metraipolis › archive › dc_ebb0038b69ce

SORT-AI: A Projection-Based Structural Framework for AI Safety Alignment Stability, Drift Detection, and Scalable Oversight (2025) · OpenAlex W4417344585

Source
OpenAlex
Original
https://doi.org/10.20944/preprints202512.1334.v1
License (as archived)
CC-BY-4.0
Archived
2026-10-08T04:15:49.125Z
SHA-256 of the archived text
9fd0e872ea3519954fb8a1e9696abeb22f0e4f2ea785e130b27d87d49848b3f6
Stable URL of this page
https://metraipolis.com/documento/dc_ebb0038b69ce

How to cite

SORT-AI: A Projection-Based Structural Framework for AI Safety Alignment Stability, Drift Detection, and Scalable Oversight (2025) · OpenAlex W4417344585 — OpenAlex, https://doi.org/10.20944/preprints202512.1334.v1 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_ebb0038b69ce (Metraipolis archive dc_ebb0038b69ce, sha256 9fd0e872ea3519954fb8a1e9696abeb22f0e4f2ea785e130b27d87d49848b3f6)
BibTeX
@misc{dcebb0038b69ce,
  title = {SORT-AI: A Projection-Based Structural Framework for AI Safety Alignment Stability, Drift Detection, and Scalable Oversight (2025) · OpenAlex W4417344585},
  howpublished = {OpenAlex},
  url = {https://doi.org/10.20944/preprints202512.1334.v1},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_ebb0038b69ce; sha256 9fd0e872ea3519954fb8a1e9696abeb22f0e4f2ea785e130b27d87d49848b3f6},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: OpenAlex, https://doi.org/10.20944/preprints202512.1334.v1. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Opera scientifica in accesso aperto: scheda dai metadati OpenAlex (preprint).
Titolo: SORT-AI: A Projection-Based Structural Framework for AI Safety Alignment Stability, Drift Detection, and Scalable Oversight
Autori: Gregor Herbert Wegener
Anno: 2025 · Sede: Preprints.org
DOI: https://doi.org/10.20944/preprints202512.1334.v1
Accesso aperto: green · testo: https://doi.org/10.20944/preprints202512.1334.v1 · licenza del testo: cc-by
Citazioni ricevute (OpenAlex): 0
Temi (OpenAlex): Ethics and Social Impacts of AI; Safety Systems Engineering in Autonomy; Explainable Artificial Intelligence (XAI)

Abstract (testo degli autori, licenza cc-by):
As artificial intelligence systems scale in depth, dimensionality, and internal coupling, their behavior becomes increasingly governed by deep compositional transformation chains rather than isolated functional components. Iterative projection, normalization, and aggregation mechanisms induce complex operator dynamics that can generate structural failure modes, including representation drift, non-local amplification, instability across transformation depth, loss of aligned fixed points, and the emergence of deceptive or mesa-optimizing substructures. Existing safety, interpretability, and evaluation approaches predominantly operate at local or empirical levels and therefore provide limited access to the underlying structural geometry that governs these phenomena. This work introduces \emph{SORT-AI}, a projection-based structural safety module that instantiates the Supra-Omega Resonance Theory (SORT) backbone for advanced AI systems. The framework is built on a closed algebra of 22 idempotent operators satisfying Jacobi consistency and invariant preservation, coupled to a non-local projection kernel that formalizes how information and influence propagate across representational scales during iterative updates. Within this geometry, SORT-AI provides diagnostics for drift accumulation, operator collapse, invariant violation, amplification modes, reward-signal divergence, and the destabilization of alignment-relevant fixed points. SORT-AI is intentionally architecture-agnostic and does not model specific neural network designs. Instead, it supplies a domain-independent mathematical substrate for analysing structural risk in systems governed by deep compositional transformations. By mapping AI failure modes to operator geometry and kernel-induced non-locality, the framework enables principled analysis of emergent behavior, hidden coupling structures, mesa-optimization conditions, and misalignment trajectories. The result is a unified, formal toolset for assessing structural safety limits and stability properties of advanced AI systems within a coherent operator–projection framework.

Fonte: https://openalex.org/W4417344585 — metadati OpenAlex (CC0 1.0), consultati il 2026-10-07 via api.openalex.org. Interrogazione: «AI safety alignment».