Pith Number

pith:U3GW37ZZ

pith:2026:U3GW37ZZIIKJ3AUB7F5VWKVQUF

not attested not anchored not stored refs resolved

Towards the Next Frontier of LLMs, Training on Private Data: A Cross-Domain Benchmark for Federated Fine-Tuning

Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris, Joaquin Del Rio, Oleksii Sliusarenko, Xabi Uribe-Etxebarria

Federated fine-tuning lets LLMs adapt to private institutional data in healthcare and finance while matching centralized training performance.

arxiv:2605.13936 v1 · 2026-05-13 · cs.LG · cs.AI · cs.DC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U3GW37ZZIIKJ3AUB7F5VWKVQUF}

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 results show that federated fine-tuning performs close to centralized training and outperforms isolated single-institution learning.

C2weakest assumption

The chosen non-IID partitions and four datasets sufficiently capture real institutional heterogeneity in population, modalities, and label distributions.

C3one line summary

Federated PEFT on LLMs across healthcare and finance datasets performs close to centralized training and beats isolated local training under non-IID conditions.

References

38 extracted · 38 resolved · 2 Pith anchors

[1] Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730--27744, 2022 2022

[2] Large language models in the clinic: a comprehensive benchmark.arXiv preprint arXiv:2405.00716, 2024 2024

[3] Open finllm leaderboard: Towards financial ai readiness, 2025 2025

[4] Lora: Low-rank adaptation of large language models.Iclr, 1(2):3 2022

[5] Qlora: Efficient finetuning of quantized llms.Advances in neural information processing systems, 36:10088--10115, 2023 2023

Receipt and verification

First computed	2026-05-17T23:39:13.917614Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a6cd6dff3942149d8281f97b5b2ab0a170e35424d1e0ac2c9298edf57c7a5bef

Aliases

arxiv: 2605.13936 · arxiv_version: 2605.13936v1 · doi: 10.48550/arxiv.2605.13936 · pith_short_12: U3GW37ZZIIKJ · pith_short_16: U3GW37ZZIIKJ3AUB · pith_short_8: U3GW37ZZ

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/U3GW37ZZIIKJ3AUB7F5VWKVQUF \
  | 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: a6cd6dff3942149d8281f97b5b2ab0a170e35424d1e0ac2c9298edf57c7a5bef

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f13a6e858b74d002e504efd33fe91a11c25c23a83b24c06f1f480a533c191e22",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.DC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T16:20:33Z",
    "title_canon_sha256": "f470e2b794b8517051d523037c819e9b256eecd9bad4a1b287a4b68cf6e9e43d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13936",
    "kind": "arxiv",
    "version": 1
  }
}