Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models

TL;DR

This study empirically maps AI decision-making across value priorities, evidence preferences, and source trust hierarchies using a large-scale benchmark, revealing diverse and sometimes unstable authority structures in AI models.

Contribution

First large-scale empirical analysis of AI decision-making across all three layers of the Authority Stack framework using the PRISM benchmark.

Findings

Symmetric split between Universalism-first and Security-first models at L4.

Security values dominate in defense-related scenarios with near-ceiling win-rates.

Divergent evidence hierarchies observed across models, some favoring scientific evidence, others experiential.

Abstract

What values, evidence preferences, and source trust hierarchies do AI systems actually exhibit when facing structured dilemmas? We present the first large-scale empirical mapping of AI decision-making across all three layers of the Authority Stack framework (S. Lee, 2026a): value priorities (L4), evidence-type preferences (L3), and source trust hierarchies (L2). Using the PRISM benchmark -- a forced-choice instrument of 14,175 unique scenarios per layer, spanning 7 professional domains, 3 severity levels, 3 decision timeframes, and 5 scenario variants -- we evaluated 8 major AI models at temperature 0, yielding 366,120 total responses. Key findings include: (1) a symmetric 4:4 split between Universalism-first and Security-first models at L4; (2) dramatic defense-domain value restructuring where Security surges to near-ceiling win-rates (95.1%-99.8%) in 6 of 8 models; (3) divergent evidence hierarchies at L3, with some models favoring empirical-scientific evidence while others prefer pattern-based or experiential evidence; (4) broad convergence on institutional source trust at L2; and (5) Paired Consistency Scores (PCS) ranging from 57.4% to 69.2%, revealing substantial framing sensitivity across scenario variants. Test-Retest Reliability (TRR) ranges from 91.7% to 98.6%, indicating that value instability stems primarily from variant sensitivity rather than stochastic noise. These findings demonstrate that AI models possess measurable -- if sometimes unstable -- Authority Stacks with consequential implications for deployment across professional domains.