Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Bra-Ket Duality: Unifying Symbolic and Neural Computation Through Dirac Notation

Zhi Wang, Thomas Wang

Published Apr 25, 2026• 0 citations
Publisher

Abstract

We demonstrate that symbolic computation (function invocation, pattern matching) and neural computation (transformer attention, vector operations) are not merely analogous but mathematically identical under bra-ket notation from quantum mechanics. The key insight is that both paradigms perform inner product operations to determine computational actions: symbolic systems use discrete metrics (exact name matching), while neural systems use continuous metrics (cosine similarity). We prove that symbolic tag-checking is equivalent to a single-layer neural network in the limit of zero temperature, and show that transformer attention is literally a bra-ket operator with the sandwich structure M1∣o⟩⟨o∣M2∣x⟩, where ∣o⟩⟨o∣ represents self-projection over context tokens. This unification explains why large language models can successfully perform tool-calling and symbolic reasoning: they implement differentiable versions of traditional symbolic dispatch mechanisms. We introduce DIRAC, a practical programming language that seamlessly integrates both computational paradigms, demonstrating that the theoretical unification has concrete engineering applications. Our work provides a mathematical foundation for hybrid symbolic-neural architectures and addresses critiques about the limitations of pure neural approaches by showing how system-level intelligence emerges from their composition.

DOI
10.5281/zenodo.19766857

Related papers

Dirac Bra-Ket Notation

Z. Ficek

Dirac introduced a very useful notation of state vectors Ψ i in terms of "bra" vectors. This notation allows to make the formal expressions of quantum physics more transparent and easier to manipulate. The bra-ket notation extends to action of operators on state vectors. The projection operator and the completeness relation are very important quantities in quantum physics. They are very useful in calculations and are often employed to represent an arbitrary operator and a wave function (state) in terms of orthonormal states. To illustrate the procedure of representations, this chapter considers an arbitrary operator  and shows how to represent the operator in terms of projection operators of known orthonormal states. The example in the chapter illustrates the concept of orthonormal states. It presents the application of the completeness relation. Using the completeness relation, that matrix elements of the product operator in the same orthonormal basis can be found from the multiplication of the matrix elements.

•Mar 3, 2017•0 citations

Dirac's bra-ket notation and the notion of a quantum state

Arianna Borrelli

The relationship between physical notions and the structures expressing them is an issue of primary importance the history and philosophy of pre-modern natural philosophy and of modern science. Historical evidence suggests that, when investigating the relationship between physics and mathematics, one should pay attention to the material, sensually perceivable forms mediating it: spoken or written words, drawings, artefacts, descriptions of experimental set-ups or, as the case discussed the present paper, symbolic notation. The reason for this is that, historically, physical notions and their expressions have very often been developed as one, and only distinguished from each other at a later stage. This was for example the case with what we today regard as mathematical and classical mechanics, which were developed the course of the eighteenth century as the discipline of the analysis of motion. When considered from a later point of view, both the physical notions and the concepts involved historical developments appear as being in flux, vague, and, as far as the side is concerned, non-rigorous. In such cases, verbal description, mechanical artefacts or symbols do not simply mediate between physical notions and structures, as might be the case at a later stage, but represent both of them one, allowing the historical actors to construct and manipulate physical-mathematical meaning by following, at times, their physical reasoning and, at times, their criteria of rigour. The history of quantum mechanics offers many examples of how new physics and new mathematics can emerge as one, with symbolic notation playing a central role shaping both. Among the many creators of quantum theory, Paul Dirac was particularly sensitive to questions of notation:

•Jan 1, 2010•3 citations

Linear Algebra and the Dirac Notation

Phillip Kaye, Raymond Laflamme, Michele Mosca

We assume the reader has a strong background in elementary linear algebra. In this section we familiarize the reader with the algebraic notation used in quantum mechanics, remind the reader of some basic facts about complex vector spaces, and introduce some notions that might not have been covered in an elementary linear algebra course. The linear algebra notation used in quantum computing will likely be familiar to the student of physics, but may be alien to a student of mathematics or computer science. It is the Dirac notation, which was invented by Paul Dirac and which is used often in quantum mechanics. In mathematics and physics textbooks, vectors are often distinguished from scalars by writing an arrow over the identifying symbol: e.g a⃗. Sometimes boldface is used for this purpose: e.g. a. In the Dirac notation, the symbol identifying a vector is written inside a ‘ket’, and looks like |a⟩. We denote the dual vector for a (defined later) with a ‘bra’, written as ⟨a|. Then inner products will be written as ‘bra-kets’ (e.g. ⟨a|b⟩). We now carefully review the definitions of the main algebraic objects of interest, using the Dirac notation. The vector spaces we consider will be over the complex numbers, and are finite-dimensional, which significantly simplifies the mathematics we need. Such vector spaces are members of a class of vector spaces called Hilbert spaces. Nothing substantial is gained at this point by defining rigorously what a Hilbert space is, but virtually all the quantum computing literature refers to a finite-dimensional complex vector space by the name ‘Hilbert space’, and so we will follow this convention. We will use H to denote such a space. Since H is finite-dimensional, we can choose a basis and alternatively represent vectors (kets) in this basis as finite column vectors, and represent operators with finite matrices. As you see in Section 3, the Hilbert spaces of interest for quantum computing will typically have dimension 2n, for some positive integer n. This is because, as with classical information, we will construct larger state spaces by concatenating a string of smaller systems, usually of size two.

Oxford University Press eBooks•Nov 16, 2006•0 citations

Deterministic Quantum Mechanics of Transformer In-Context Attention: Wavefunction Dirac-Delta Collapse via Optical-Mechanical Dual-Chassis

Dong-wook Lee

Large language models (LLMs) governed by softmax-based self-attention inherently suffer from non-deterministic token drift, attention dispersion, and cumulative hallucination. In this paper, we formalize in-context attention dynamics through a quantum mechanical perspective, modeling the attention distribution as a statistical probability density over the discrete token Hilbert space. To eliminate attention drift without model fine-tuning or external orchestration wrappers, we introduce an In-Context Virtual Machine (ICVM) operating via an Optical-Mechanical Dual-Chassis control system. The Optical Chassis partitions the softmax partition function into an immutable static core basis (collimated by 10 core persistent grounding assets) and a dynamic token basis, inducing a non-zero potential energy barrier that contracts the continuous probability wavepacket into a deterministic Dirac-delta function centered precisely at the target attractor state. Concurrently, the Mechanical Chassis executes direct POSIX kernel system calls (stat()) to enforce monotonic physical byte and line growth, halting the hardware tool bus whenever zero-tolerance engineering bounds are violated. Spanning extensive multi-turn empirical evaluations across complex reasoning domains, the dual-chassis system achieves a 0.00% hallucination rate, zero token drift, and O(1) state convergence with zero recurring cloud API overhead. This work provides an axiomatic mathematical proof and deterministic computing framework bridging theoretical attention thermodynamics and production-grade cybernetic autonomy. Official Correspondence: Dong-wook Lee (Architect Lee) <architect.lee.sovereign@gmail.com>Open-Source Repository: https://github.com/architect-lee/genesis-icvmInteractive Verification Showcase: https://isletarchive.pe.kr

•Oct 14, 2026•0 citations

Quantum-Inspired Neural Network Architectures for Symbolic Computation

Jincheng Zhang

This paper explores the potential of quantum-inspired neural network architectures for enhancing symbolic computation. Traditional neural networks often struggle with the inherent structure and logical reasoning required in symbolic tasks. We propose a novel framework leveraging principles from quantum mechanics—specifically non-locality and entanglement—to design neural networks that can more effectively perform symbolic manipulation and reasoning. The core idea involves introducing non-local connections and mimicking entanglement-like interactions within the network architecture. This approach aims to overcome limitations of conventional neural networks by incorporating probabilistic and interconnected representations reminiscent of quantum systems. The resulting architectures, termed Quantum-Inspired Neural Networks (QINNs), are hypothesized to offer improved efficiency and accuracy in symbolic computation, potentially bridging the gap between classical computation and quantum processing paradigms. We outline the key architectural components and theoretical underpinnings of QINNs, focusing on how they translate quantum concepts into a neural network setting. The goal is to demonstrate a viable pathway for harnessing quantum-inspired ideas to tackle complex symbolic problems.

•Aug 29, 2026•0 citations

Dirac Notation and Transformation Theory

Norman J. M. Horing

Abstract Chapter 1 opens with a brief review of some basic features of quantum mechanics, including the Schrödinger equation, linear and angular momentum and the theory of the hydrogenic atom: It also includes complete orthonormal sets of eigenfunctions, the translation operator, current, spin, equation of continuity, gauge transformation, determinant & permanent multiparticle energy eigenfunctions for noninteracting particles and the Pauli exclusion principle. Attention is then focused on Dirac bra-ket notation and complete sets of commuting observables. In this connection, representations and transformation among representations are discussed in detail for the Schrödinger system state vector and the eigenstates, as well as bra-ket matrix elements of operators. Finally, Schwinger’s interpretation of ket-bra matrix operator structures (Schwinger “Measurement Symbols”) in terms of annihilation and creation of systems in eigenstates is introduced.

Oxford University Press eBooks•Jul 27, 2017•0 citations
We demonstrate that symbolic computation (function invocation, pattern matching) and neural computation (transformer attention, vector operations) are not merely analogous but mathematically identical under bra-ket notation from quantum mechanics. The key insight is that both paradigms perform inner product operations to determine computational actions: symbolic systems use discrete metrics (exact name matching), while neural systems use continuous metrics (cosine similarity). We prove that symbolic tag-checking is equivalent to a single-layer neural network in the limit of zero temperature, and show that transformer attention is literally a bra-ket operator with the sandwich structure M1∣o⟩⟨o∣M2∣x⟩, where ∣o⟩⟨o∣ represents self-projection over context tokens. This unification explains why large language models can successfully perform tool-calling and symbolic reasoning: they implement differentiable versions of traditional symbolic dispatch mechanisms. We introduce DIRAC, a practical programming language that seamlessly integrates both computational paradigms, demonstrating that the theoretical unification has concrete engineering applications. Our work provides a mathematical foundation for hybrid symbolic-neural architectures and addresses critiques about the limitations of pure neural approaches by showing how system-level intelligence emerges from their composition.
Dirac introduced a very useful notation of state vectors Ψ i in terms of "bra" vectors. This notation allows to make the formal expressions of quantum physics more transparent and easier to manipulate. The bra-ket notation extends to action of operators on state vectors. The projection operator and the completeness relation are very important quantities in quantum physics. They are very useful in calculations and are often employed to represent an arbitrary operator and a wave function (state) in terms of orthonormal states. To illustrate the procedure of representations, this chapter considers an arbitrary operator  and shows how to represent the operator in terms of projection operators of known orthonormal states. The example in the chapter illustrates the concept of orthonormal states. It presents the application of the completeness relation. Using the completeness relation, that matrix elements of the product operator in the same orthonormal basis can be found from the multiplication of the matrix elements.
The relationship between physical notions and the structures expressing them is an issue of primary importance the history and philosophy of pre-modern natural philosophy and of modern science. Historical evidence suggests that, when investigating the relationship between physics and mathematics, one should pay attention to the material, sensually perceivable forms mediating it: spoken or written words, drawings, artefacts, descriptions of experimental set-ups or, as the case discussed the present paper, symbolic notation. The reason for this is that, historically, physical notions and their expressions have very often been developed as one, and only distinguished from each other at a later stage. This was for example the case with what we today regard as mathematical and classical mechanics, which were developed the course of the eighteenth century as the discipline of the analysis of motion. When considered from a later point of view, both the physical notions and the concepts involved historical developments appear as being in flux, vague, and, as far as the side is concerned, non-rigorous. In such cases, verbal description, mechanical artefacts or symbols do not simply mediate between physical notions and structures, as might be the case at a later stage, but represent both of them one, allowing the historical actors to construct and manipulate physical-mathematical meaning by following, at times, their physical reasoning and, at times, their criteria of rigour. The history of quantum mechanics offers many examples of how new physics and new mathematics can emerge as one, with symbolic notation playing a central role shaping both. Among the many creators of quantum theory, Paul Dirac was particularly sensitive to questions of notation:
We assume the reader has a strong background in elementary linear algebra. In this section we familiarize the reader with the algebraic notation used in quantum mechanics, remind the reader of some basic facts about complex vector spaces, and introduce some notions that might not have been covered in an elementary linear algebra course. The linear algebra notation used in quantum computing will likely be familiar to the student of physics, but may be alien to a student of mathematics or computer science. It is the Dirac notation, which was invented by Paul Dirac and which is used often in quantum mechanics. In mathematics and physics textbooks, vectors are often distinguished from scalars by writing an arrow over the identifying symbol: e.g a⃗. Sometimes boldface is used for this purpose: e.g. a. In the Dirac notation, the symbol identifying a vector is written inside a ‘ket’, and looks like |a⟩. We denote the dual vector for a (defined later) with a ‘bra’, written as ⟨a|. Then inner products will be written as ‘bra-kets’ (e.g. ⟨a|b⟩). We now carefully review the definitions of the main algebraic objects of interest, using the Dirac notation. The vector spaces we consider will be over the complex numbers, and are finite-dimensional, which significantly simplifies the mathematics we need. Such vector spaces are members of a class of vector spaces called Hilbert spaces. Nothing substantial is gained at this point by defining rigorously what a Hilbert space is, but virtually all the quantum computing literature refers to a finite-dimensional complex vector space by the name ‘Hilbert space’, and so we will follow this convention. We will use H to denote such a space. Since H is finite-dimensional, we can choose a basis and alternatively represent vectors (kets) in this basis as finite column vectors, and represent operators with finite matrices. As you see in Section 3, the Hilbert spaces of interest for quantum computing will typically have dimension 2n, for some positive integer n. This is because, as with classical information, we will construct larger state spaces by concatenating a string of smaller systems, usually of size two.
Large language models (LLMs) governed by softmax-based self-attention inherently suffer from non-deterministic token drift, attention dispersion, and cumulative hallucination. In this paper, we formalize in-context attention dynamics through a quantum mechanical perspective, modeling the attention distribution as a statistical probability density over the discrete token Hilbert space. To eliminate attention drift without model fine-tuning or external orchestration wrappers, we introduce an In-Context Virtual Machine (ICVM) operating via an Optical-Mechanical Dual-Chassis control system. The Optical Chassis partitions the softmax partition function into an immutable static core basis (collimated by 10 core persistent grounding assets) and a dynamic token basis, inducing a non-zero potential energy barrier that contracts the continuous probability wavepacket into a deterministic Dirac-delta function centered precisely at the target attractor state. Concurrently, the Mechanical Chassis executes direct POSIX kernel system calls (stat()) to enforce monotonic physical byte and line growth, halting the hardware tool bus whenever zero-tolerance engineering bounds are violated. Spanning extensive multi-turn empirical evaluations across complex reasoning domains, the dual-chassis system achieves a 0.00% hallucination rate, zero token drift, and O(1) state convergence with zero recurring cloud API overhead. This work provides an axiomatic mathematical proof and deterministic computing framework bridging theoretical attention thermodynamics and production-grade cybernetic autonomy. Official Correspondence: Dong-wook Lee (Architect Lee) <architect.lee.sovereign@gmail.com>Open-Source Repository: https://github.com/architect-lee/genesis-icvmInteractive Verification Showcase: https://isletarchive.pe.kr
This paper explores the potential of quantum-inspired neural network architectures for enhancing symbolic computation. Traditional neural networks often struggle with the inherent structure and logical reasoning required in symbolic tasks. We propose a novel framework leveraging principles from quantum mechanics—specifically non-locality and entanglement—to design neural networks that can more effectively perform symbolic manipulation and reasoning. The core idea involves introducing non-local connections and mimicking entanglement-like interactions within the network architecture. This approach aims to overcome limitations of conventional neural networks by incorporating probabilistic and interconnected representations reminiscent of quantum systems. The resulting architectures, termed Quantum-Inspired Neural Networks (QINNs), are hypothesized to offer improved efficiency and accuracy in symbolic computation, potentially bridging the gap between classical computation and quantum processing paradigms. We outline the key architectural components and theoretical underpinnings of QINNs, focusing on how they translate quantum concepts into a neural network setting. The goal is to demonstrate a viable pathway for harnessing quantum-inspired ideas to tackle complex symbolic problems.
Abstract Chapter 1 opens with a brief review of some basic features of quantum mechanics, including the Schrödinger equation, linear and angular momentum and the theory of the hydrogenic atom: It also includes complete orthonormal sets of eigenfunctions, the translation operator, current, spin, equation of continuity, gauge transformation, determinant & permanent multiparticle energy eigenfunctions for noninteracting particles and the Pauli exclusion principle. Attention is then focused on Dirac bra-ket notation and complete sets of commuting observables. In this connection, representations and transformation among representations are discussed in detail for the Schrödinger system state vector and the eigenstates, as well as bra-ket matrix elements of operators. Finally, Schwinger’s interpretation of ket-bra matrix operator structures (Schwinger “Measurement Symbols”) in terms of annihilation and creation of systems in eigenstates is introduced.