Pith Number

pith:3CQNCPBC

pith:2026:3CQNCPBCK23WGCDBZTHTS5PACE

not attested not anchored not stored refs pending

Relational In-Context Learning via Synthetic Pre-training with Structural Prior

Chuan Shi, Jiaxuan You, Muhan Zhang, Yanbo Wang

RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models.

arxiv:2603.03805 v5 · 2026-03-04 · cs.LG · cs.AI · cs.DB

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{3CQNCPBCK23WGCDBZTHTS5PACE}

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

RDB-PFN achieves strong few-shot performance on 19 real-world relational prediction tasks, outperforming graph-based and single-table foundation-model baselines (given the same DFS-linearized inputs), while using a lightweight architecture and fast inference.

C2weakest assumption

Synthetic relational databases generated by the Relational Prior Generator from Structural Causal Models sufficiently capture the structural heterogeneity, join patterns, and statistical properties of real-world RDBs to support generalization to actual tasks.

C3one line summary

RDB-PFN is a relational foundation model pre-trained on over 2 million synthetic RDB tasks that achieves strong few-shot performance on 19 real-world relational prediction tasks via in-context learning.

Formal links

2 machine-checked theorem links

Cited by

2 papers in Pith

Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality

KumoRFM-2: Scaling Foundation Models for Relational Learning

Receipt and verification

First computed	2026-05-29T02:05:42.287875Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910

Aliases

arxiv: 2603.03805 · arxiv_version: 2603.03805v5 · doi: 10.48550/arxiv.2603.03805 · pith_short_12: 3CQNCPBCK23W · pith_short_16: 3CQNCPBCK23WGCDB · pith_short_8: 3CQNCPBC

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/3CQNCPBCK23WGCDBZTHTS5PACE \
  | 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: d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "94a47104e96c7ca2618d190a88fae53f276106d69b4f03f2a42d5898eb812177",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.DB"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-03-04T07:30:54Z",
    "title_canon_sha256": "6b2d0b6c0534919e143fbb24c06c8e79384c4a5631a179660dc1590a63661671"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.03805",
    "kind": "arxiv",
    "version": 5
  }
}