Pith Number

pith:SKKEXQCK

pith:2026:SKKEXQCK6B54NWNPU5OCTEJPAX

not attested not anchored not stored refs pending

SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification

David Love, Jose D. Posada, Priya Desai, Somalee Datta

Small language models distilled from large ones match teacher performance on structured patient identifiers in clinical notes at 0.88 precision and 0.86 recall on standard hardware.

arxiv:2605.03301 v2 · 2026-05-05 · cs.CL · 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{SKKEXQCK6B54NWNPU5OCTEJPAX}

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

Our best distilled model matches its teacher on structured PHI categories (DATE, DOCTOR, ID, PATIENT, PHONE) and achieves micro-averaged span-level precision of 0.88 and recall of 0.86 on standard workstation hardware.

C2weakest assumption

The set-cover diversity sampling combined with human-in-the-loop adjudication yields a dataset representative of modern clinical narratives that supports generalization beyond the sampled notes and institutions.

C3one line summary

SHIELD dataset and distilled DeBERTa v3 model achieve 0.88 micro precision and 0.86 recall on PHI de-identification while matching teacher performance on structured categories.

Receipt and verification

First computed	2026-07-02T00:18:29.478279Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

92944bc04af07bc6d9afa75c29912f05ceec9288e8456ca80a8bb47e5bfd87c5

Aliases

arxiv: 2605.03301 · arxiv_version: 2605.03301v2 · doi: 10.48550/arxiv.2605.03301 · pith_short_12: SKKEXQCK6B54 · pith_short_16: SKKEXQCK6B54NWNP · pith_short_8: SKKEXQCK

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/SKKEXQCK6B54NWNPU5OCTEJPAX \
  | 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: 92944bc04af07bc6d9afa75c29912f05ceec9288e8456ca80a8bb47e5bfd87c5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "226807d8055754f1641ff4cfa70746c91dd4a0de43b785d843152abfb180ec67",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-05T02:43:55Z",
    "title_canon_sha256": "b5b3ae82ae781ac83b229a07ee1750e903abf3bc0e2d45ba25bc13cb1c9dcbd3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03301",
    "kind": "arxiv",
    "version": 2
  }
}