Pith Number

pith:XSJCDPQS

pith:2026:XSJCDPQS372E5DUFEUGV5RKXKQ

not attested not anchored not stored refs resolved

TabPFN-3: Technical Report

Adrian Hayler, Alan Arazi, Anurag Garg, Benjamin J\"ager, Bernhard Sch\"olkopf, Brendan Roof, Clara Cornu, David Salinas, Diana Kriuchkova, Dominik Safaric, Eliott Kalfon, Felix Birkel, Frank Hutter, Georg Grab, Jake Robertson, Jan Hendrik Metzen, Jerry Chen, Julien Siems, Klemens Fl\"oge, Kursat Kaya, Lennart Purucker, L\'eo Grinsztajn, Lilly Charlotte Wehrhahn, Lydia Sidhoum, Madelon Hulsebos, Magnus B\"uhler, Marie Salmon, Mihir Manium, Nick Erickson, Noah Hollmann, Oscar Key, Philipp Jund, Philipp Singer, Samuel M\"uller, Sauraj Gambhir, Shi Bin (Liam) Hoo, Simon Bing, Simone Alessi, Siyuan Guo, Vladyslav Moroshan, Yann LeCun

TabPFN-3 outperforms all tuned and ensembled models on the TabArena tabular benchmark with a single forward pass.

arxiv:2605.13986 v1 · 2026-05-13 · 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{XSJCDPQS372E5DUFEUGV5RKXKQ}

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 standard tabular benchmark TabArena, a forward pass of TabPFN-3 outperforms all other models, including tuned and ensembled baselines, by a significant margin, and pareto-dominates the speed/performance frontier. TabPFN-3-Plus (Thinking) beats all non-TabPFN models by over 200 Elo on TabArena, rising to 420 Elo on the largest data subset, and outperforms AutoGluon 1.5 extreme while being 10x faster.

C2weakest assumption

That benchmark wins on TabArena and other reported datasets, achieved via synthetic pretraining and test-time scaling, will generalize to arbitrary unseen real-world tabular distributions without hidden overfitting to the evaluation suites or synthetic data generator.

C3one line summary

TabPFN-3 delivers state-of-the-art tabular prediction performance on benchmarks up to 1M rows, is up to 20x faster than prior versions, and introduces test-time scaling that beats non-TabPFN models by hundreds of Elo points.

References

298 extracted · 298 resolved · 10 Pith anchors

[1] arXiv:2506.16791 [cs] 2025

[2] AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data 2003 · arXiv:2003.06505

[3] A targeted real-time early warning score (trewscore) for septic shock.Science translational medicine, 7(299):299ra122–299ra122, 2015 2015

[4] Mimic-iii, a freely accessible critical care database.Scientific data, 3(1):1–9 2016

[5] Deep neural networks detect suicide risk from textual facebook posts.Scientific reports, 10(1):16685, 2020 2020

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases

Receipt and verification

First computed	2026-05-17T23:39:13.319210Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bc9221be12dff44e8e85250d5ec5575405b13f3d27971128803d2e7670bb5e8a

Aliases

arxiv: 2605.13986 · arxiv_version: 2605.13986v1 · doi: 10.48550/arxiv.2605.13986 · pith_short_12: XSJCDPQS372E · pith_short_16: XSJCDPQS372E5DUF · pith_short_8: XSJCDPQS

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/XSJCDPQS372E5DUFEUGV5RKXKQ \
  | 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: bc9221be12dff44e8e85250d5ec5575405b13f3d27971128803d2e7670bb5e8a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "934474672251d10a921e9abdad8961e6b2e4069302316d6df9a0e979a4754a03",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T18:01:43Z",
    "title_canon_sha256": "daf73d720c130d23fcec478f4224a2da1974d195d2e321265396253c90e5ec7d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13986",
    "kind": "arxiv",
    "version": 1
  }
}