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

Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models explores This paper empirically maps the 'Authority Stack' of 8 AI models across values, evidence, and source trust, revealing significant domain-specific biases and framing sensitivity.. Commercial viability score: 3/10 in AI Alignment.