What exactly has TabPFN learned to do?

Calvin Mccarter

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

calvinmccarter/tabpfn-eval — marked official in Papers with Code
automl/TabPFN

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

, a Transformer model pretrained to perform incontext learning on fresh tabular classification problems, was presented at the last ICLR conference. To better understand its behavior, we treat it as a black-box function approximator generator and observe its generated function approximations on a varied selection of training datasets. Exploring its learned inductive biases in this manner, we observe behavior that is at turns either brilliant or baffling. We conclude this post with thoughts on how these results might inform the development, evaluation, and application of prior-data fitted networks (PFNs) in the future. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.08978")
get_code_for_paper("2502.08978")
have("2502.08978")

Connect an agent — have() is free.