Pith Number

pith:ATDEY3YC

pith:2026:ATDEY3YCGMFYPYOEOECMIYKX3F

not attested not anchored not stored refs resolved

SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution

Huminhao Zhu, Jiachen Jiang, Zhihui Zhu

SMCEvolve recasts program search as sampling from a reward-tilted target distribution and approximates it with a Sequential Monte Carlo sampler.

arxiv:2605.15308 v1 · 2026-05-14 · cs.AI · cs.LG · cs.MA

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ATDEY3YCGMFYPYOEOECMIYKX3F}

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

SMCEvolve recasts program search as sampling from a reward-tilted target distribution and approximates it with a Sequential Monte Carlo (SMC) sampler, supplying finite-sample complexity analysis that bounds the LLM-call budget required to reach a target approximation error.

C2weakest assumption

That the chosen mutation operators and acceptance probabilities, when combined inside the SMC framework, produce unbiased samples from the intended reward-tilted distribution without requiring additional corrections or domain-specific tuning.

C3one line summary

SMCEvolve applies Sequential Monte Carlo sampling to LLM program search with adaptive resampling, mutation mixtures, and convergence control, delivering finite-sample complexity bounds and benchmark gains over prior systems.

References

36 extracted · 36 resolved · 5 Pith anchors

[1] Reevo: Large language models as hyper-heuristics with reflective evolution, 2024

[2] Evolution of heuristics: Towards efficient automatic algorithm design using large language model 2024

[3] Mathematical discoveries from program search with large language models, 2024

[4] AlphaEvolve: A coding agent for scientific and algorithmic discovery 2025 · arXiv:2506.13131

[5] ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution 2025 · arXiv:2509.19349

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:51.857467Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

04c64c6f02330b87e1c47104c46157d94267afd6f1c37b9213108c328df84fc9

Aliases

arxiv: 2605.15308 · arxiv_version: 2605.15308v1 · doi: 10.48550/arxiv.2605.15308 · pith_short_12: ATDEY3YCGMFY · pith_short_16: ATDEY3YCGMFYPYOE · pith_short_8: ATDEY3YC

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/ATDEY3YCGMFYPYOEOECMIYKX3F \
  | 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: 04c64c6f02330b87e1c47104c46157d94267afd6f1c37b9213108c328df84fc9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d81474f8a9dfaa4756b9375ca1905419eda7d185ebfbe63b5910c9c0e0f6e075",
    "cross_cats_sorted": [
      "cs.LG",
      "cs.MA"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T18:21:08Z",
    "title_canon_sha256": "6046e3748de2f3baff5ad298678eaea239cb760b8353a337b2700668eed0b45b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15308",
    "kind": "arxiv",
    "version": 1
  }
}