Tabular foundation models fail to classify statistically matched legal vs rule-violating database states, achieving only chance accuracy without rule-derived audits.
NeurIPS 2024 Third Table Representation Learning Workshop , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Models
Tabular foundation models fail to classify statistically matched legal vs rule-violating database states, achieving only chance accuracy without rule-derived audits.