Si-Di Chang

An executable contract linking observable support, statistical calibration, and justified claims is contributed an executable contract linking observable support, statistical calibration, and justified claims.

Withholding just one terminal receipt can render coverage inconclusive, challenging the reliability of agent evaluations in practice.

Initial claims of substantial welfare gains from marketplace guardrails are misleading, with rigorous checks revealing many results as invalid.

Subtle wording changes in benchmark rubrics can swing model performance by over 13%, revealing a hidden subjectivity in "objective" gold labels.