Pith. sign in
Pith Number

pith:UT7WDUMP

pith:2026:UT7WDUMPMFEDZIRMQVEIEJVUDL
not attested not anchored not stored refs resolved

Improving LLM-Driven Test Generation by Learning from Mocking Information

Flynn Teh, Hengcheng Zhu, Jamie Lee, Mattia Fazzini, Mengzhen Li, Valerio Terragni

Leveraging mocking information from existing tests allows LLMs to generate unit tests that cover more code and kill more mutants than standard methods.

arxiv:2604.19315 v1 · 2026-04-21 · cs.SE

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UT7WDUMPMFEDZIRMQVEIEJVUDL}

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

The results show that MOCKMILL's tests cover lines of code and kill mutants that existing tests and baseline-generated tests miss.

C2weakest assumption

That the mocking information extracted from existing tests provides generalizable guidance that improves LLM test generation beyond what the models can achieve with standard prompting alone.

C3one line summary

MOCKMILL uses mocking information from existing tests to guide LLMs in producing unit tests that achieve higher code coverage and kill more mutants than prior tests or baseline LLM approaches on 10 Java classes.

References

35 extracted · 35 resolved · 0 Pith anchors

[1] G. J. Myers, C. Sandler, and T. Badgett,The art of software testing. John Wiley & Sons, 2011 2011
[2] Software testing research: Achievements, challenges, dreams 2007
[3] An orchestrated survey of methodologies for automated software test case generation 1978
[4] Sbft tool competition 2023 - java test case generation track 2023
[5] Understanding llm-driven test oracle generation 2025
Receipt and verification
First computed 2026-07-23T00:23:40.126479Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

a4ff61d18f61483ca22c85488226b41adb2430ee5e2ad455fc39109f8b13fe15

Aliases

arxiv: 2604.19315 · arxiv_version: 2604.19315v1 · doi: 10.48550/arxiv.2604.19315 · pith_short_12: UT7WDUMPMFED · pith_short_16: UT7WDUMPMFEDZIRM · pith_short_8: UT7WDUMP
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UT7WDUMPMFEDZIRMQVEIEJVUDL \
  | 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: a4ff61d18f61483ca22c85488226b41adb2430ee5e2ad455fc39109f8b13fe15
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "1aa30814f2e0ed5bea32eac1f5b652b8c351d2f5e7e743e5f676f9a44e484bb7",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-04-21T10:24:26Z",
    "title_canon_sha256": "03ba168c0eb33fe2b478c054bb3668f4d359ed4504203a30da279834376cccad"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.19315",
    "kind": "arxiv",
    "version": 1
  }
}