Pith Number

pith:L3NLAG7E

pith:2025:L3NLAG7EU2L7CG3RYNC5CCB7NZ

not attested not anchored not stored refs resolved

PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models

Ivan Srba, Maria Bielikova, Robert Belanec

PEFT-Factory supplies one controlled environment that bundles 19 PEFT methods with 27 datasets for reproducible LLM fine-tuning comparisons.

arxiv:2512.02764 v3 · 2025-12-02 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{L3NLAG7EU2L7CG3RYNC5CCB7NZ}

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

we introduce PEFT-Factory, a unified framework for efficient fine-tuning LLMs using both off-the-shelf and custom PEFT methods... providing a ready-to-use, controlled, and stable environment, improving replicability and benchmarking of PEFT methods.

C2weakest assumption

That the modular design and native implementations of the 19 PEFT methods actually deliver stable, comparable results across the 27 datasets without hidden implementation differences or post-hoc tuning that would undermine fair benchmarking.

C3one line summary

PEFT-Factory supplies a ready-to-use, extensible codebase that unifies 19 PEFT methods and evaluation pipelines for fine-tuning large autoregressive language models.

References

87 extracted · 87 resolved · 15 Pith anchors

[1] online" 'onlinestring :=

[2] write newline

[3] Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, and David Ha 2019 · arXiv:1906.02569

[4] Lightning AI. 2023. Litgpt. https://github.com/Lightning-AI/litgpt 2023

[5] M ath QA : Towards interpretable math word problem solving with operation-based formalisms 2019 · doi:10.18653/v1/n19-1245

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:10:11.692840Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5edab01be4a697f11b71c345d1083f6e57b5e5aa3528d70dfb4b1e1923008bb3

Aliases

arxiv: 2512.02764 · arxiv_version: 2512.02764v3 · doi: 10.48550/arxiv.2512.02764 · pith_short_12: L3NLAG7EU2L7 · pith_short_16: L3NLAG7EU2L7CG3R · pith_short_8: L3NLAG7E

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/L3NLAG7EU2L7CG3RYNC5CCB7NZ \
  | 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: 5edab01be4a697f11b71c345d1083f6e57b5e5aa3528d70dfb4b1e1923008bb3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "25bcd70f0aa37135444ef1f29e54eab459bfbbf54815ae8f08a1f92ed2089ae6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-12-02T13:44:41Z",
    "title_canon_sha256": "79e97e4a54cfde0d432c85ad0b2cd5fe8e27d6bd0b88c4c52d8dc84960a02cae"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.02764",
    "kind": "arxiv",
    "version": 3
  }
}