Pith Number

pith:5PZ7SAXM

pith:2022:5PZ7SAXMN3BHKV4ER2D4YRI6R3

not attested not anchored not stored refs resolved

TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

Frank Hutter, Katharina Eggensperger, Noah Hollmann, Samuel M\"uller

A pre-trained Transformer performs competitive classification on small tabular datasets in under a second with no tuning.

arxiv:2207.01848 v6 · 2022-07-05 · cs.LG · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5PZ7SAXMN3BHKV4ER2D4YRI6R3}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230× speedup.

C2weakest assumption

The prior over structural causal models used to generate the synthetic training data is sufficiently representative of the distribution of real-world small tabular classification problems so that the trained network generalizes without further adaptation.

C3one line summary

TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single forward pass without further updates.

References

41 extracted · 41 resolved · 2 Pith anchors

[1] Longformer: The Long-Document Transformer 2004 · arXiv:2004.05150

[2] V . Borisov, T. Leemann, K. Seßler, J. Haug, M. Pawelczyk, and G. Kasneci. Deep neural networks and tabular data: A survey. arXiv:2110.01889 [cs.LG],

[3] Language models are few-shot learners 1901

[4] URL https://proceedings.neurips.cc/paper_files/paper/ 2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf. T. Chen and C. Guestrin. Xgboost: A scalable tree boosting system. In B. Krishnapuram, M. Sh 2020

[5] arXiv preprint arXiv:2006.10029 , year= 2006

Formal links

2 machine-checked theorem links

Cited by

44 papers in Pith

Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretraining

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers

Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification

Tabular foundation models for robust calibration of near-infrared chemical sensing data

Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data

Receipt and verification

First computed	2026-05-17T23:38:53.722896Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2

Aliases

arxiv: 2207.01848 · arxiv_version: 2207.01848v6 · doi: 10.48550/arxiv.2207.01848 · pith_short_12: 5PZ7SAXMN3BH · pith_short_16: 5PZ7SAXMN3BHKV4E · pith_short_8: 5PZ7SAXM

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/5PZ7SAXMN3BHKV4ER2D4YRI6R3 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: ebf3f902ec6ec27557848e87cc451e8edfaca0c66d0f7e5f9b8697928331c1c2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "28acee69c2f4693367d647e5f9cdc9fc67a218e6b96d2d6eb8f36716d625ef9c",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2022-07-05T07:17:43Z",
    "title_canon_sha256": "25f4e9ad94e4b3fbf7db28c4ab7bfaae622b37a48b0e6199a0f88a4dd20dac16"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2207.01848",
    "kind": "arxiv",
    "version": 6
  }
}