Skip to content

The N-Universe A Mathematical Framework for the Representation of Human Abstracts in AI Systems

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

Contemporary artificial intelligence systems demonstrate remarkable capacity for pattern recognition and statistical inference; however, an explicit internal structure for representing human abstract concepts such as power, love, trust, and freedom remains absent. These notions are typically treated as qualitative or context dependent constructs, without a formal relational architecture that enables structural interpretation, manipulation, and dynamic simulation. The N-Universe is introduced as a mathematical and geometric framework designed to represent human abstracts as structured relational entities within a unified formal space. The framework is grounded on the structural principle that each human abstract possesses an intrinsic geometry, understood as a characteristic relational organization that can be formally described through distinct geometric structures. Such geometries are not metaphorical illustrations, but mathematically defined configurations expressing essential properties including orientation, distribution, symmetry, intensity, and dynamic variation. Whereas Gärdenfors' conceptual spaces employ geometry in a static sense, as a similarity metric organizing categorization within a single cognitive agent, the N-Universe employs geometry in a dynamic sense, describing how an abstract behaves, propagates, and reacts over time within a bounded social-relational environment N composed of interacting human agents. The shared vocabulary of "intrinsic geometry" should not obscure this fundamental difference in what is being modeled: a static representational structure versus a dynamic relational process. Within this setting, abstract concepts are modeled as geometric configurations defined over a relational domain in which vectors, fields, and gradients encode structural properties. Power is formally defined as a vector structure possessing magnitude, vertical direction, and orientation determined by the interaction between applied power and reactive power. This formulation allows power to be interpreted as an oriented relational magnitude whose dynamics arise from the interplay between deliberate action and structural response of the environment. Love may be conceived, under the intrinsic geometry principle proposed by the N-Universe, as a radial field centered on a relational nucleus, with intensity decreasing as structural distance increases, thereby expressing cohesion and affective attraction. In a similar manner, trust may be interpreted as a continuous structural gradient describing stability and directional coherence across agents along relational or temporal axes. These formulations indicate potential geometric extensions of the framework rather than fully formalized components of the present model. Formally, a structured relational space is defined in which abstract fields are measurable, dynamically evolving, and computationally tractable. Symbolic interpretation is integrated with continuous mathematical representation, enabling hybrid reasoning and structured semantic analysis. By transforming qualitative human abstracts into geometrically intrinsic and mathematically coherent relational objects, a foundation is established for interpretable abstraction modeling, social simulation, and structurally grounded artificial intelligence systems.

View source

Similar papers

#artificial intelligence Open access May 2023

Evaluating the Performance of Large Language Models on GAOKAO Benchmark

GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations of such models.

Xiaotian Zhang, Chun-yan Li, Yi Zong et al. · 216 citations · ⚡17

PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection

Empirically, PRISM reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines, and achieves this efficiency while simultaneously enhancing performance, surpassing models fine-tuned on the full dataset across eight multimodal and three language understanding benchmarks.

Jinhe Bi, Yifan Wang, Danqi Yan et al. · 73 citations · ⚡4
#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

This paper designs Markov decision processes (MDPs) for different combinatorial problems and proposes to train conditional GFlowNets to sample from the solution space and demonstrates that GFlowNet policies can efficiently find high-quality solutions.

Dinghuai Zhang, H. Dai, Esmeralda S. Whitammer et al. · 59 citations · ⚡8

Ethically Aligned Design of Autonomous Systems: Industry viewpoint and an empirical study

An empirical study on the current state of practice in artificial intelligence ethics is conducted by means of a multiple case study of five case companies, which indicates a gap between research and practice in the area.

Ville Vakkuri, Kai-Kristian Kemell, Joni Kultanen et al. · 56 citations · ⚡6
#artificial intelligence Conference Open access Jun 2018

The Key Concepts of Ethics of Artificial Intelligence

It is suggested that the focus on finding keywords is the first step in guiding and providing direction for future research in the AI ethics field.

Ville Vakkuri, P. Abrahamsson · 39 citations · ⚡2

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.