Pith Number

pith:PI5MLL6K

pith:2026:PI5MLL6K24L6XEWLSGJAM46RFS

not attested not anchored not stored refs pending

Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent

Jean G. Rosario, Josef Hardi, Marcos Martinez-Romero, Mark A. Musen, Martin J. O'Connor, Stephen A. Fisher

Augmenting an LLM with real-time queries to biomedical terminology services improves metadata standardization accuracy over the model alone.

arxiv:2604.08552 v2 · 2026-03-10 · cs.DB · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PI5MLL6K24L6XEWLSGJAM46RFS}

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

augmenting the LLM with real-time tool access consistently improves prediction accuracy over the LLM alone across both ontology-constrained and non-ontology-constrained fields

C2weakest assumption

The expert-curated gold standard is treated as ground truth and the real-time terminology services always return canonically correct terms without introducing new errors.

C3one line summary

An LLM system with real-time access to ontology services outperforms plain LLM prompting on standardizing 839 HuBMAP legacy metadata records against an expert gold standard.

Receipt and verification

First computed	2026-06-19T16:12:53.938509Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7a3ac5afcad717eb92cb91920673d12cb4be95a68f874be6e9dace9626a96a31

Aliases

arxiv: 2604.08552 · arxiv_version: 2604.08552v2 · doi: 10.48550/arxiv.2604.08552 · pith_short_12: PI5MLL6K24L6 · pith_short_16: PI5MLL6K24L6XEWL · pith_short_8: PI5MLL6K

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/PI5MLL6K24L6XEWLSGJAM46RFS \
  | 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: 7a3ac5afcad717eb92cb91920673d12cb4be95a68f874be6e9dace9626a96a31

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "16e18b1c4c8b586ade2a62f68125a74dc64a80f4094857de5e530974db2b67b3",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.DB",
    "submitted_at": "2026-03-10T18:47:30Z",
    "title_canon_sha256": "ba5d3cc5ac20f7f39f8a6d8e2cd81f2bf71d1fe99cddda9ca888fef75df27e13"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.08552",
    "kind": "arxiv",
    "version": 2
  }
}