PhilSci Archive

From Computation to Coherence: Toward a Structural Symbolic Theory of General Intelligence

Freeman, N. Will (2025) From Computation to Coherence: Toward a Structural Symbolic Theory of General Intelligence. [Preprint]

This is the latest version of this item.

[img] Text
From_Computation_to_Coherence.pdf

Download (404kB)

Abstract

What distinguishes genuine intelligence from sophisticated simulation? This paper argues that the answer lies in symbolic coherence—the structural capacity to interpret information, revise commitments, and maintain continuity of reasoning across contradiction. Current AI systems generate fluent outputs while lacking mechanisms to track their own symbolic commitments or resolve contradictions through norm-guided revision. This theory proposes F(S), a structural identity condition requiring interpretive embedding, reflexive situatedness, and internal normativity. This condition is substrate-neutral and applies to both biological and artificial systems. Unlike behavioral benchmarks, F(S) offers criteria for participation in symbolic reasoning rather than surface-level imitation. To demonstrate implementability, the paper presents a justification graph architecture that supports recursive coherence and transparent revision. A diagnostic scalar, symbolic density, tracks alignment over symbolic time. By uniting philosophical insights with concrete system design, this framework outlines foundations for machines that may one day understand rather than simulate understanding.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Freeman, N. Willnwillfreeman@proton.me0009-0004-8681-241X
Keywords: Artificial general intelligence, Symbolic reasoning, Cognitive architecture, AI alignment, Machine understanding, AI interpretability
Subjects: Specific Sciences > Artificial Intelligence > AI and Ethics
Specific Sciences > Artificial Intelligence > Classical AI
Specific Sciences > Cognitive Science
Specific Sciences > Cognitive Science > Computation
Specific Sciences > Computation/Information
Specific Sciences > Computer Science
Specific Sciences > Artificial Intelligence
Specific Sciences > Cognitive Science > Concepts and Representations
Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User: Mr. N. Will Freeman
Date Deposited: 03 Jun 2025 13:15
Last Modified: 03 Jun 2025 13:15
Item ID: 25540
Subjects: Specific Sciences > Artificial Intelligence > AI and Ethics
Specific Sciences > Artificial Intelligence > Classical AI
Specific Sciences > Cognitive Science
Specific Sciences > Cognitive Science > Computation
Specific Sciences > Computation/Information
Specific Sciences > Computer Science
Specific Sciences > Artificial Intelligence
Specific Sciences > Cognitive Science > Concepts and Representations
Specific Sciences > Artificial Intelligence > Machine Learning
Date: 1 June 2025
URI: https://philsci-archive.pitt.edu/id/eprint/25540

Available Versions of this Item

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item