E01¶


Research	R0055 — RLHF Yes-Men Claims
Run	2026-04-01
Claim	C025
Source	SRC01
Evidence	SRC01-E01
Type	Factual

CaTE is 'Center for Calibrated Trust Measurement and Evaluation' (not 'Calibrated AI Trust and Expectations'); at SEI/CMU with DoD

URL: https://www.cmu.edu/news/stories/archives/2024/april/sei-and-dod-center-to-ensure-trustworthiness-in-ai-systems

Extract¶

Launched in 2023, CaTE is a collaborative R&D center between SEI and OUSD(R&E). Its full name is Center for Calibrated Trust Measurement and Evaluation, not 'Calibrated AI Trust and Expectations' as the claim states. It defines calibrated trust as 'a psychological state of adjusted confidence aligned to end users' real-time perceptions of trustworthiness.' The SEI published a guidebook for TEVV of LAWS focusing on system trustworthiness and operator trust.

Relevance to Hypotheses¶

Hypothesis	Relationship	Strength
H1	Supports	Moderate
H2	Supports	Strong
H3	Contradicts	Strong

Context¶

Evidence directly relevant to testing the claim's factual assertions.