What question did this study set out to answer?

To develop an operator-algebraic metric for consciousness integrating various theories and AI alignment.

May 21, 2026Open Access

ITU Tier 1+ #2: Consciousness Metric (Kₛelf)

Key Points

To develop an operator-algebraic metric for consciousness integrating various theories and AI alignment.
Defined K_self as the modular Hamiltonian on combined spaces including attention and phenomenal experiences.
Computed numerical results using Phi on minimal networks related to established consciousness theories.
Integrated concepts from Global Workspace Theory, Integrated Information Theory, and AI alignment frameworks.
Identified top couplings such as mKQEC (0.95) and K_QG (0.92) relevant for consciousness metrics.
Ten falsifiable predictions made with varying probabilities, indicating future directions in consciousness research.

Abstract

Tier 1+ Pass-1. 5 paper 2 of 45. Operator-algebraic consciousness metric integrating GWT + IIT + AI alignment. Defines Kₛelf = -log ρₛelf as the operator-algebraic modular Hamiltonian on Hglobalworkspace ⊗ Hₐttention ⊗ Hₚhenomenal ⊗ Hₘeta. Kₛelf inherits from KQG via the CLPW 2023 type II crossed-product specialised to this scale. Numerical results. Phi computation on minimal networks, IIT 4. 0 Tononi 2023, GNW Dehaene 2014, AI alignment Bostrom 2014. Topics covered. Global Workspace Theory, IIT Tononi, GNW Dehaene, ARC-COGITATE 2023, hard problem Chalmers 1996, Dennett RIP 2024. 4. 19. 45-vertex polytope #2 top couplings: #1 mKQEC (0. 95), #17 KQG (0. 92), #28 Neuro (0. 92), #43 Meta (0. 92). Ten falsifiable predictions: Pₐvg=0. 70: arXiv 2026 (0. 90 S), IIT/GNW consensus 2030 (0. 40 W), AI consciousness debate 2027 (0. 75 M). Pass-2 roadmap: ~1. 7M: Consciousness analytics (600K) + Lean Mathlib (200K) + Neuro+AI partnerships (900K). Copyright © 2026 Munehiro Terada / Roboken. Licensed under CC-BY-4. 0.

ITU Tier 1+ #2: Consciousness Metric (Kₛelf)

Key Points

Abstract

Cite This Study