Search papers, labs, and topics across Lattice.
4
0
5
1
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.
Subtle wording changes in benchmark rubrics can swing model performance by over 13%, revealing a hidden subjectivity in "objective" gold labels.
LLM-judged investment rationales reward verbosity and confidence over actual financial insight, penalizing concise, correct reasoning by nearly 3 points.
