Similarity Field Theory: A Mathematical Framework for Intelligence

• URL: http://arxiv.org/abs/2509.18218v3
• Date: Mon, 13 Oct 2025 18:42:31 GMT
• Title: Similarity Field Theory: A Mathematical Framework for Intelligence
• Authors: Kei-Sing Ng,
• Abstract summary: This paper introduces Similarity Field Theory, a mathematical framework that formalizes the principles governing similarity values among entities and their evolution.<n>At a high level, this framework reframes intelligence and interpretability as geometric problems on similarity fields.<n>We prove two theorems: (i) asymmetry blocks mutual inclusion; and (ii) stability requires either an anchor coordinate or eventual confinement within a level set.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We posit that persisting and transforming similarity relations form the structural basis of any comprehensible dynamic system. This paper introduces Similarity Field Theory, a mathematical framework that formalizes the principles governing similarity values among entities and their evolution. We define: (1) a similarity field $S: U \times U \to [0,1]$ over a universe of entities $U$, satisfying reflexivity $S(E,E)=1$ and treated as a directed relational field (asymmetry and non-transitivity are allowed); (2) the evolution of a system through a sequence $Z_p=(X_p,S^{(p)})$ indexed by $p=0,1,2,\ldots$; (3) concepts $K$ as entities that induce fibers $F_{\alpha}(K)={E\in U \mid S(E,K)\ge \alpha}$, i.e., superlevel sets of the unary map $S_K(E):=S(E,K)$; and (4) a generative operator $G$ that produces new entities. Within this framework, we formalize a generative definition of intelligence: an operator $G$ is intelligent with respect to a concept $K$ if, given a system containing entities belonging to the fiber of $K$, it generates new entities that also belong to that fiber. Similarity Field Theory thus offers a foundational language for characterizing, comparing, and constructing intelligent systems. At a high level, this framework reframes intelligence and interpretability as geometric problems on similarity fields -- preserving and composing level-set fibers -- rather than purely statistical ones. We prove two theorems: (i) asymmetry blocks mutual inclusion; and (ii) stability requires either an anchor coordinate or eventual confinement within a level set. These results ensure that the evolution of similarity fields is both constrained and interpretable, culminating in a framework that not only interprets large language models but also introduces a novel way of using them as experimental probes of societal cognition, supported by preliminary evidence across diverse consumer categories.

Related papers

• Canonicalizing Multimodal Contrastive Representation Learning [76.15228959754727]
  We show that across model families such as CLIP, SigLIP, and FLAVA, a geometric relationship exists between their embedding spaces.<n>This finding enables backward-compatible model upgrades, avoiding costly re-embedding, and has implications for the privacy of learned representations.
  arXiv  Detail & Related papers  (2026-02-19T18:09:36Z)
• Learning with the $p$-adics [26.431600220740354]
  We study the suitability of a radically different field as an alternative to $mathbbR$ -- the ultrametric and non-archimedean space of $p$-adic numbers, $mathbbQ_p$.<n>The hierarchical structure of the $p$-adics and their interpretation as infinite strings make them an appealing tool for code theory and hierarchical representation learning.
  arXiv  Detail & Related papers  (2025-12-27T19:40:42Z)
• Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing [52.124267908936396]
  The model is composed of $M$ arms and $K$ plays.<n>Each arm has a number of capacities, and each unit of capacity is associated with a reward function.<n>When multiple plays compete for the arm capacity, the arm capacity is allocated in a larger priority weight first manner.
  arXiv  Detail & Related papers  (2025-12-25T11:19:09Z)
• Uniqueness of purifications is equivalent to Haag duality [44.33169165028139]
  We show that, if the two systems are modelled by commuting von algebra Neumanns $M_A$ and $M_B$ on a Hilbert space $mathcal H$, uniqueness of purifications is equivalent to Haag duality $M_A = M_B'$.
  arXiv  Detail & Related papers  (2025-09-16T10:05:17Z)
• On the Emergence of Linear Analogies in Word Embeddings [5.440589713820591]
  Models such as Word2Vec and GloVe construct word embeddings based on the co-occurrence probability $P(i,j)$ of words $i$ and $j$ in text corpora.<n>We introduce a theoretical generative model in which words are defined by binary semantic attributes, and co-occurrence probabilities are derived from attribute-based interactions.
  arXiv  Detail & Related papers  (2025-05-24T11:42:26Z)
• Geometric Learning Dynamics [0.0]
  We present a unified framework for modeling learning dynamics in physical, biological, and machine learning systems.<n>The quantum regime corresponds to $alpha = 1$ and describes Schr"odinger-like dynamics that emerges from a discrete shift symmetry.<n>The efficient learning regime corresponds to $alpha = tfrac12$ and describes very fast machine learning algorithms.
  arXiv  Detail & Related papers  (2025-04-20T19:56:41Z)
• QUDsim: Quantifying Discourse Similarities in LLM-Generated Text [70.22275200293964]
  We introduce an abstraction based on linguistic theories in Questions Under Discussion (QUD) and question semantics to help quantify differences in discourse progression.<n>We then use this framework to build $textbfQUDsim$, a similarity metric that can detect discursive parallels between documents.<n>Using QUDsim, we find that LLMs often reuse discourse structures (more so than humans) across samples, even when content differs.
  arXiv  Detail & Related papers  (2025-04-12T23:46:09Z)
• Universal coarse geometry of spin systems [0.0]
  We show that both states and dynamics of a spin system have a canonically associated coarse geometry on the set of sites in the thermodynamic limit.<n>We establish a basic compatibility between the dynamical coarse structure associated to a quantum circuit $alpha$ and the coarse structure of the state $psicirc alpha$ where $psi$ is any product state.
  arXiv  Detail & Related papers  (2024-11-12T16:39:33Z)
• A Theory of Interpretable Approximations [61.90216959710842]
  We study the idea of approximating a target concept $c$ by a small aggregation of concepts from some base class $mathcalH$. For any given pair of $mathcalH$ and $c$, exactly one of these cases holds: (i) $c$ cannot be approximated by $mathcalH$ with arbitrary accuracy. We show that, in the case of interpretable approximations, even a slightly nontrivial a-priori guarantee on the complexity of approximations implies approximations with constant (distribution-free and accuracy-
  arXiv  Detail & Related papers  (2024-06-15T06:43:45Z)
• Constructions of $k$-uniform states in heterogeneous systems [65.63939256159891]
  We present two general methods to construct $k$-uniform states in the heterogeneous systems for general $k$. We can produce many new $k$-uniform states such that the local dimension of each subsystem can be a prime power.
  arXiv  Detail & Related papers  (2023-05-22T06:58:16Z)
• Merging Ontologies Algebraically [1.6404357211482503]
  We show that aligning and merging operations share some generic properties, e.g., idempotence, comativity, and representativity, labeled by (I), (C), (A), and (R) We also show that the merging system given by $V$-alignment satisfies the properties: (I), (C), (A), and (R)
  arXiv  Detail & Related papers  (2022-08-18T08:57:58Z)
• Algebraic Aspects of Boundaries in the Kitaev Quantum Double Model [77.34726150561087]
  We provide a systematic treatment of boundaries based on subgroups $Ksubseteq G$ with the Kitaev quantum double $D(G)$ model in the bulk. The boundary sites are representations of a $*$-subalgebra $Xisubseteq D(G)$ and we explicate its structure as a strong $*$-quasi-Hopf algebra. As an application of our treatment, we study patches with boundaries based on $K=G$ horizontally and $K=e$ vertically and show how these could be used in a quantum computer
  arXiv  Detail & Related papers  (2022-08-12T15:05:07Z)
• A Classification of $G$-invariant Shallow Neural Networks [1.4213973379473654]
  We prove a theorem that gives a classification of all $G$-invariant single-hidden-layer or "shallow" neural network ($G$-SNN) architectures with ReLU activation. We enumerate the $G$-SNN architectures for some example groups $G$ and visualize their structure.
  arXiv  Detail & Related papers  (2022-05-18T21:18:16Z)
• Unsupervised Semantic Segmentation by Distilling Feature Correspondences [94.73675308961944]
  Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. We present STEGO, a novel framework that distills unsupervised features into high-quality discrete semantic labels. STEGO yields a significant improvement over the prior state of the art, on both the CocoStuff and Cityscapes challenges.
  arXiv  Detail & Related papers  (2022-03-16T06:08:47Z)
• Quantum double aspects of surface code models [77.34726150561087]
  We revisit the Kitaev model for fault tolerant quantum computing on a square lattice with underlying quantum double $D(G)$ symmetry. We show how our constructions generalise to $D(H)$ models based on a finite-dimensional Hopf algebra $H$.
  arXiv  Detail & Related papers  (2021-06-25T17:03:38Z)
• An Optimal Separation of Randomized and Quantum Query Complexity [67.19751155411075]
  We prove that for every decision tree, the absolute values of the Fourier coefficients of a given order $ellsqrtbinomdell (1+log n)ell-1,$ sum to at most $cellsqrtbinomdell (1+log n)ell-1,$ where $n$ is the number of variables, $d$ is the tree depth, and $c>0$ is an absolute constant.
  arXiv  Detail & Related papers  (2020-08-24T06:50:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.