Tabular foundation models used as in-context binary classifiers over discretized event times match or beat classical survival models on average across 48 real-world datasets.
We define the time-dependent risk score at timetk as the predicted probability of experiencing the event in the next interval, ˆr(Hi,tk) = ˆptk,k+1(Hi,tk)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Tabular Foundation Models Can Do Survival Analysis
Tabular foundation models used as in-context binary classifiers over discretized event times match or beat classical survival models on average across 48 real-world datasets.