Pith Number

pith:LD4OE2G3

pith:2026:LD4OE2G3EG2WRSA3GMZG5LZYJD

not attested not anchored not stored refs resolved

EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering

Chenhui Mao, Dajun Chen, Jingxuan Xu, Ming Liang, Wei Jiang, Yong Li, Yuanting Lei, Zhixiang Wang, Zhixiang Wei

Entropy-guided scaling boosts code generation success rates by 5-10% and cuts token use by 28%.

arxiv:2602.05242 v1 · 2026-02-05 · cs.SE · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LD4OE2G3EG2WRSA3GMZG5LZYJD}

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

EGSS consistently boosts performance by 5-10% across all evaluated models. Specifically, it increases the resolved ratio of Kimi-K2-Intruct from 63.2% to 72.2%, and GLM-4.6 from 65.8% to 74.6%. Furthermore, when paired with GLM-4.6, EGSS achieves a new state-of-the-art among open-source large language models. In addition to these accuracy improvements, EGSS reduces inference-time token usage by over 28% compared to existing TTS methods.

C2weakest assumption

That entropy reliably signals the quality of candidate solutions and that the test-suite augmentation produces robust verification without introducing selection bias or new failure modes.

C3one line summary

EGSS uses entropy to guide adaptive search and test-suite augmentation in LLM test-time scaling, raising resolved rates on SWE-Bench-Verified by 5-10% and cutting tokens by 28%.

References

24 extracted · 24 resolved · 0 Pith anchors

[1] Carefully analyze the user’s request

[2] Use available tools to gather necessary information

[3] Propose clear, well-thought-out solutions

[4] Execute changes carefully and verify results When modifying files: - Always read files before modifying them - Make precise, targeted changes - Explain what you’re doing and why Be concise, accurate,

[5] Score Criteria 0 Inconsistent 1 Basically Consistent 2 Partially Consistent 3 Fully Consistent

Receipt and verification

First computed	2026-05-18T02:45:05.462194Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

58f8e268db21b568c81b33326eaf3848d611049511d43b604168d9609886b67b

Aliases

arxiv: 2602.05242 · arxiv_version: 2602.05242v1 · doi: 10.48550/arxiv.2602.05242 · pith_short_12: LD4OE2G3EG2W · pith_short_16: LD4OE2G3EG2WRSA3 · pith_short_8: LD4OE2G3

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/LD4OE2G3EG2WRSA3GMZG5LZYJD \
  | 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: 58f8e268db21b568c81b33326eaf3848d611049511d43b604168d9609886b67b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8edb4a4e281d5d82cd4f691d106a7956ec52c6b7980350c4bacc9de15ed7f0d9",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-02-05T03:02:54Z",
    "title_canon_sha256": "baca9e371d52873011a190fd54b2e0bc443edcf78ed47ba4d51a690d5dc4b1e7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.05242",
    "kind": "arxiv",
    "version": 1
  }
}