Pith Number

pith:H5E4RBVV

pith:2025:H5E4RBVVO73D2O55WUITJ4EDRU

not attested not anchored not stored refs resolved

AIDE: AI-Driven Exploration in the Space of Code

Deniss Jacenko, Dhruv Srikanth, Dixing Xu, Dominik Schmidt, Ian Kaplan, Yuxiang WU, Zhengyao Jiang

AIDE uses large language models to perform tree search in code space and reaches state-of-the-art results on Kaggle, OpenAI MLE-Bench, and METR RE-Bench.

arxiv:2502.13138 v1 · 2025-02-18 · 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{H5E4RBVVO73D2O55WUITJ4EDRU}

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

By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench.

C2weakest assumption

That the tree search guided by LLMs can reliably identify and improve upon promising code variants without the search space becoming intractable or the evaluations becoming unreliable.

C3one line summary

AIDE uses large language models to perform tree search in code space and reaches state-of-the-art results on Kaggle, OpenAI MLE-Bench, and METR RE-Bench.

References

14 extracted · 14 resolved · 1 Pith anchors

[1] Li, Y., Choi, D.H., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., et al., 2022 2019 · doi:10.1126/science.abq1158

[2] Voyager: An Open-Ended Embodied Agent with Large Language Models 2024 · arXiv:2305.16291

[3] Distributed Random Forest (DRF) and Extremely Randomized Trees (XRT)

[4] Generalized Linear Model (GLM) with regularization

[5] H2O Gradient Boosting Machines

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines

SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

An AI system to help scientists write expert-level empirical software

TusoAI: Agentic Optimization for Scientific Methods

Receipt and verification

First computed	2026-05-17T23:38:13.410583Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3f49c886b577f63d3bbdb51134f0838d18b7c4e248340dd84ac6f9815680cecb

Aliases

arxiv: 2502.13138 · arxiv_version: 2502.13138v1 · doi: 10.48550/arxiv.2502.13138 · pith_short_12: H5E4RBVVO73D · pith_short_16: H5E4RBVVO73D2O55 · pith_short_8: H5E4RBVV

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/H5E4RBVVO73D2O55WUITJ4EDRU \
  | 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: 3f49c886b577f63d3bbdb51134f0838d18b7c4e248340dd84ac6f9815680cecb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f5fb737c5d0d23c7b616c2709def8648acee758a13af530cf04429ab1ad9f46c",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-02-18T18:57:21Z",
    "title_canon_sha256": "12ed0c321dfb54715b553cf42ff7c0ef45beb36bcedadc170f2de58489f2b47a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.13138",
    "kind": "arxiv",
    "version": 1
  }
}