Pith Number

pith:CGHDYSAH

pith:2026:CGHDYSAHUYW2JMKCBYUP4DRPMX

not attested not anchored not stored refs resolved

Retrieval-Augmented Large Language Models for Schema-Constrained Clinical Information Extraction

A H M Rezaul Karim, Ozlem Uzuner

A retrieval-augmented pipeline with schema-constrained prompts extracts structured clinical observations from transcripts at 80.36 percent F1.

arxiv:2605.15467 v1 · 2026-05-14 · 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{CGHDYSAHUYW2JMKCBYUP4DRPMX}

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 configuration uses GPT-5.2 with full schema, RAG, and a second-pass auditing, achieving 80.36% F1 score. Overall, our results show that RAG consistently improves performance, while the optimal degree of schema constraint depends on the model, and second-pass auditing yields modest additional gains by correcting residual schema-adherence errors.

C2weakest assumption

The training set can serve as an effective exemplar corpus for retrieval that meaningfully improves the model's ability to produce schema-adherent outputs when combined with prompting and post-processing.

C3one line summary

A modular RAG pipeline with schema-constrained prompting, deterministic post-processing, and second-pass auditing reaches 80.36% F1 on observation extraction from nurse-patient transcripts using GPT-5.2.

References

38 extracted · 38 resolved · 0 Pith anchors

[1] Catalan Speecon database 2011

[2] The EMILLE/CIIL Corpus 2004

[3] The OrienTel Moroccan MCA (Modern Colloquial Arabic) database 2004

[4] ItalWordNet v.2

[5] Advances in neural information processing systems , volume=

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:01:00.096241Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8

Aliases

arxiv: 2605.15467 · arxiv_version: 2605.15467v1 · doi: 10.48550/arxiv.2605.15467 · pith_short_12: CGHDYSAHUYW2 · pith_short_16: CGHDYSAHUYW2JMKC · pith_short_8: CGHDYSAH

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/CGHDYSAHUYW2JMKCBYUP4DRPMX \
  | 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: 118e3c4807a62da4b1420e28fe0e2f65f06037753acbd26f17eff99864afbac8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e0e00ec6e4c07ba565efa608336d1d5aa239e52aa1869561a3e75d5920b7b8d4",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-14T23:13:05Z",
    "title_canon_sha256": "482151a2ab80529a188b5715f43911a7643f0dcbb7ebe8ebc6afe9b938365c42"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15467",
    "kind": "arxiv",
    "version": 1
  }
}