TZStats aiX Lab | Tian Zheng, Columbia Stats
TZStats aiX Lab | Tian Zheng, Columbia Stats
About
Posts
People
Projects
Publications
Contact
AI Evaluation
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics. This makes them more …
Tian Zheng
,
Carter K. T. Hsu
PDF
Cite
Code
DOI
arXiv
GitHub (TZstats-Columbia)
Cite
×