pith. sign in
Pith Number

pith:UVBEQKV3

pith:2025:UVBEQKV3TMV4RHGB7ZAS4EUW2I
not attested not anchored not stored refs pending

Guidelines for Empirical Studies in Software Engineering involving Large Language Models

Brian Fitzgerald, Chetan Arora, Christoph Treude, Chunyang Chen, Cristina Martinez Montes, Daniel Russo, Davide Falessi, Davide Fucci, Fabio Calefato, Florian Angermeir, Junda He, Lukas B\"ohme, Lutz Prechelt, Marcos Kalinowski, Marvin Mu\~noz Bar\'on, Mircea Lungu, Neil Ernst, Paul Ralph, Rijnard van Tonder, Sebastian Baltes, Stefano Lambiase, Stefan Wagner

Guidelines organize LLM use in software engineering studies into seven types and provide eight reporting rules to boost reproducibility.

arxiv:2508.15503 v6 · 2025-08-21 · cs.SE

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UVBEQKV3TMV4RHGB7ZAS4EUW2I}

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 address this challenge through a collaborative effort of 22 researchers, presenting a taxonomy of seven study types that organizes how LLMs are used in SE research, together with eight guidelines for designing and reporting such studies.

C2weakest assumption

The guidelines assume that declaring usage, reporting versions and prompts, human validation, and open baselines will sufficiently mitigate threats from non-determinism and opacity, without the paper providing new empirical evidence that these practices improve reproducibility outcomes.

C3one line summary

A group of 22 researchers proposes seven study types and eight guidelines for empirical software engineering studies involving LLMs to enhance reproducibility and replicability.

Formal links

1 machine-checked theorem link

Cited by

7 papers in Pith

Receipt and verification
First computed 2026-05-25T02:01:06.475903Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

a542482abb9b2bc89cc1fe412e1296d2142692dcd147e588f2f07e6db6ae6680

Aliases

arxiv: 2508.15503 · arxiv_version: 2508.15503v6 · doi: 10.48550/arxiv.2508.15503 · pith_short_12: UVBEQKV3TMV4 · pith_short_16: UVBEQKV3TMV4RHGB · pith_short_8: UVBEQKV3
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UVBEQKV3TMV4RHGB7ZAS4EUW2I \
  | 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: a542482abb9b2bc89cc1fe412e1296d2142692dcd147e588f2f07e6db6ae6680
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "8dfd1ca1acf1d61e1b26adcb9bc4f84852bcfbebced2dc224ab91ec70d040fb3",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2025-08-21T12:30:30Z",
    "title_canon_sha256": "e0309463248c4b33dc5e30dc42b44758a0eef593f3d393d909aca9647c5e61ed"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.15503",
    "kind": "arxiv",
    "version": 6
  }
}