pith:5MYS7Y3P
GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models
GraphWalker selects in-context demonstrations for EHR reasoning by building graphs that combine patient clinical data with LLM estimates of information gain, then using cohort discovery and lazy greedy search to reduce redundancy and local-
arxiv:2604.06684 v2 · 2026-04-08 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{5MYS7Y3PLFIZRWA5GUVQGS7USA}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
GraphWalker consistently outperforms state-of-the-art ICL baselines, yielding substantial improvements in clinical reasoning performance.
That jointly modeling patient clinical information and LLM-estimated information gain via graphs, combined with cohort discovery and lazy greedy search, will reliably overcome perspective limitation, cohort awareness, and information aggregation issues on real EHR data without introducing new selection biases or overfitting to the tested benchmarks.
GraphWalker improves LLM clinical reasoning on EHRs by graph-guided selection of in-context examples that jointly uses data similarity and model signals, plus cohort-level structure and greedy aggregation to reduce redundancy.
Formal links
Receipt and verification
| First computed | 2026-06-08T01:04:04.473430Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
eb312fe36f595198d81d352b034bf4901ec386e1b4a4d2e367e1bb3b46e844dd
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/5MYS7Y3PLFIZRWA5GUVQGS7USA \
| 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: eb312fe36f595198d81d352b034bf4901ec386e1b4a4d2e367e1bb3b46e844dd
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "fc07c7731cc9631747b5887214e92517ee1d268d953a2466e0d7a915801c2230",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-08T04:59:49Z",
"title_canon_sha256": "a5aad80c028b98799bd951a66e6ea5f7ed10b22dc2ab0405a4e3acb063c817e0"
},
"schema_version": "1.0",
"source": {
"id": "2604.06684",
"kind": "arxiv",
"version": 2
}
}