A Layered Attribution Framework for Machine Consciousness: Life, Consciousness, Self, Volition, and Self-Awareness as Observer-Relative Judgments

This paper addresses a practical predicament: how to tell whether a machine is conscious. Behavioral tests cannot distinguish genuine consciousness from a good imitation; indicator lists derived from theory depend on theories that are themselves unsettled. The paper proposes no new theory of consciousness and adjudicates no dispute within consciousness science; its contribution is methodological. It offers a five-layer framework, progressive by axiomatic choice: life (endogenous triggering, not biological life), consciousness, self, volition, and self-awareness. Its output maps where disagreements about machine consciousness are located, not whether any system is conscious. Unlike a parallel list of indicators, higher-layer verdicts presuppose the verdict at the life layer. Each layer provides an observable or inferable entry point, the practice the judgment is relative to, and pre-registered failure conditions: what new evidence would withdraw the verdict. Layer dependence is a methodological axiom, not a metaphysical claim that consciousness requires life; every verdict is conditional on that choice. The consciousness layer is judged under a weak, checkable sense, with no claim of phenomenal consciousness. Meeting its criteria is not a consciousness verdict. Observer-relativity concerns the practice of making attribution judgments, not the system judged. Evaluability makes disagreements between practices locatable and discussable rather than empty. The application provides steps for assessing current AI and shows why stable feedback is misread as consciousness while the gaps at the life and volition layers go unnoticed; its verdicts rest on a conditional architectural inference checked under a declared threshold.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24411175
Primary Topic
Philosophy and Theoretical Science
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

A Layered Attribution Framework for Machine Consciousness: Life, Consciousness, Self, Volition, and Self-Awareness as Observer-Relative Judgments

Wan-Jiu Yang
Zenodo (CERN European Organization for Nuclear Research)
Philosophy and Theoretical Science
preprint

A Layered Attribution Framework for Machine Consciousness: Life, Consciousness, Self, Volition, and Self-Awareness as Observer-Relative Judgments

Wan-Jiu Yang
preprint en

Abstract

This paper addresses a practical predicament: how to tell whether a machine is conscious. Behavioral tests cannot distinguish genuine consciousness from a good imitation; indicator lists derived from theory depend on theories that are themselves unsettled. The paper proposes no new theory of consciousness and adjudicates no dispute within consciousness science; its contribution is methodological. It offers a five-layer framework, progressive by axiomatic choice: life (endogenous triggering, not biological life), consciousness, self, volition, and self-awareness. Its output maps where disagreements about machine consciousness are located, not whether any system is conscious. Unlike a parallel list of indicators, higher-layer verdicts presuppose the verdict at the life layer. Each layer provides an observable or inferable entry point, the practice the judgment is relative to, and pre-registered failure conditions: what new evidence would withdraw the verdict. Layer dependence is a methodological axiom, not a metaphysical claim that consciousness requires life; every verdict is conditional on that choice. The consciousness layer is judged under a weak, checkable sense, with no claim of phenomenal consciousness. Meeting its criteria is not a consciousness verdict. Observer-relativity concerns the practice of making attribution judgments, not the system judged. Evaluability makes disagreements between practices locatable and discussable rather than empty. The application provides steps for assessing current AI and shows why stable feedback is misread as consciousness while the gaps at the life and volition layers go unnoticed; its verdicts rest on a conditional architectural inference checked under a declared threshold.

Zenodo (CERN European Organization for Nuclear Research)
Philosophy and Theoretical Science
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon