pith. sign in
Pith Number

pith:D75WCTB2

pith:2025:D75WCTB2CP474E6L4EUUYGZAON
not attested not anchored not stored refs resolved

ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution

Edoardo Cetin, Robert Tjarko Lange, Yuki Imajuku

ShinkaEvolve evolves programs with far fewer samples by balancing exploration, rejecting non-novel code, and dynamically choosing which LLM to use for mutations.

arxiv:2509.19349 v1 · 2025-09-17 · cs.CL · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{D75WCTB2CP474E6L4EUUYGZAON}

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

ShinkaEvolve discovers a new state-of-the-art circle packing solution using only 150 samples, designs high-performing agentic harnesses for AIME mathematical reasoning tasks, identifies improvements to ALE-Bench competitive programming solutions, and discovers novel mixture-of-expert load balancing loss functions that illuminate the space of optimization strategies.

C2weakest assumption

That the three innovations (parent sampling balancing exploration/exploitation, code novelty rejection-sampling, and bandit-based LLM ensemble selection) are the primary drivers of the reported gains in sample efficiency and solution quality rather than other unstated factors such as the choice of base LLMs or task-specific tuning.

C3one line summary

ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.

References

234 extracted · 234 resolved · 51 Pith anchors

[1] American Invitational Mathematics Examination, 2023 , year = 2023
[2] American Invitational Mathematics Examination, 2024 , year = 2024
[3] American Invitational Mathematics Examination, 2025 , year = 2025
[8] 2025 , publisher = 2025
[10] The AI CUDA engineer: Agentic CUDA kernel discovery, optimization and composition , author=. 2025 , institution= 2025

Formal links

2 machine-checked theorem links

Cited by

28 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:47.679435Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

1ffb614c3a13f9fe13cbe1294c1b20736893b91e031adc8ea7abc4af6b4b6062

Aliases

arxiv: 2509.19349 · arxiv_version: 2509.19349v1 · doi: 10.48550/arxiv.2509.19349 · pith_short_12: D75WCTB2CP47 · pith_short_16: D75WCTB2CP474E6L · pith_short_8: D75WCTB2
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/D75WCTB2CP474E6L4EUUYGZAON \
  | 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: 1ffb614c3a13f9fe13cbe1294c1b20736893b91e031adc8ea7abc4af6b4b6062
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "82b9818d0590bdbd8c1078ef5b31b91b1624d25d9cf1282acd50cff1c28183f2",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-09-17T17:49:02Z",
    "title_canon_sha256": "a5885ffdc658a1f4228115a196e2dc48bd0bc60296caaf90a3bdf356b0af778b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.19349",
    "kind": "arxiv",
    "version": 1
  }
}