Measurement Validation Reveals Five Dissociable Operational Constructs Underlying Self-Model and Agency in Artificial Neural Architectures
Fuwang Feng
Zenodo (CERN European Organization for Nuclear Research) May 25, 2026 preprint DOI: 10.5281/zenodo.20372254 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Experimental validation and diagnostic study |
|---|---|
| Population | Small custom artificial neural network simulations |
| Keywords | Proxy statistics Agency philosophy Construct python library Action physics Matching statistics Boundary topology Construct validity Sense of agency Artificial intelligence Machine learning Incremental validity Artificial neural network Cognitive psychology Sociotechnical system Extrapolation Consciousness Data mining |
| Key findings | Operational proxies for consciousness-like properties in artificial neural networks often fail independent behavioral validation, but can be refined into constructs with strong proxy-test convergence. |
Abstract
Operational proxies are common in artificial consciousness research, but their validity is rarely tested against independent behavioral measures. We evaluate such proxies in artificial neural architectures by comparing internal-state measures with behavior-level probes. Initial validation exposed substantial mismatches: a thalamus-inspired agency proxy was negatively correlated with independent agency tests (r=-0.860), and generic distributed self tests had poor convergence. Diagnostic experiments showed that the agency proxy primarily measured gating rather than action-outcome control, and that broad self-model scores conflated boundary maintenance, identity persistence, and ownership. After refinement, five operational constructs showed strong proxy-test convergence, including action agency (r=0.874) and boundary self (r=0.940). Mechanistic manipulations then separated their computational substrates: workspace mechanisms supported boundary and identity-temporal measures, action-outcome loops supported agency and action ownership, and meta-monitoring supported distributed body-schema measures. A subsequent minimal attention-based diagnostic showed that action-loop effects generalize to an attention-based substrate, while boundary-self validation remains measurement-limited. All architectures studied here are small custom simulations used as controlled measurement testbeds, not production-scale language models. The pattern argues that proxy validation should precede mechanistic interpretation, and that diagnostic failures of theoretically motivated proxies can themselves refine the construct set.