pith. sign in
Pith Number

pith:OEHZB7YY

pith:2026:OEHZB7YYIGFOAXVLRBJ7DTUQQI
not attested not anchored not stored refs resolved

FePySR: A Neural Feature Extraction Framework for Efficient and Scalable Symbolic Regression

Wangtao Lu, Xin Lai, Zhiming Yu

A neural network first extracts candidate features to shrink the search space for symbolic regression, recovering more complex equations than direct search.

arxiv:2605.12704 v1 · 2026-05-12 · cs.SC · cs.AI · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{OEHZB7YYIGFOAXVLRBJ7DTUQQI}

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

Across five standard benchmarks, FePySR outperforms state-of-the-art methods by achieving higher equation recovery rates. On a set of 75 highly complex synthesized equations, FePySR recovers 36 equations, while producing substantially smaller mean squared errors on the remaining unrecovered cases, with reduced computation time compared to PySR. Applied to ordinary differential equations governing biological systems, FePySR successfully identifies governing equations in 24 out of 100 tests where PySR recovers none.

C2weakest assumption

That observational data can be reliably constrained by the heterogeneous neural network to a set of valid candidate expressions without systematically excluding critical nonlinear modules or introducing many invalid ones that still expand the search space.

C3one line summary

FePySR uses a neural network to pre-extract valid features before PySR search, recovering more equations than baselines on benchmarks and identifying governing ODEs in 24 of 100 biological cases where PySR finds none.

References

43 extracted · 43 resolved · 1 Pith anchors

[1] MarcoVirgolinandSolonP.Pissis. SymbolicregressionisNP-hard.TransactionsonMachineLearning Research, 2022 2022
[2] Prove symbolic regression is NP-hard by symbol graph.arXiv preprint arXiv:2404.13820, 2024 2024
[3] Koza.Genetic programming 2 - automatic discovery of reusable programs 1994
[4] Distilling free-form natural laws from experimental data.Science, 324(5923):81–85, 2009 2009
[5] La Cava, Lee Spector, and Kourosh Danai 2016

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-18T03:09:49.642788Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

710f90ff18418ae05eab8853f1ce908220d967344cd89f2fe0d174887fb028c3

Aliases

arxiv: 2605.12704 · arxiv_version: 2605.12704v1 · doi: 10.48550/arxiv.2605.12704 · pith_short_12: OEHZB7YYIGFO · pith_short_16: OEHZB7YYIGFOAXVL · pith_short_8: OEHZB7YY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/OEHZB7YYIGFOAXVLRBJ7DTUQQI \
  | 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: 710f90ff18418ae05eab8853f1ce908220d967344cd89f2fe0d174887fb028c3
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "3cc3b9ea1441ccd14fd17d5146aa60348e9a7716a07f92b267e2edc1810136d7",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.SC",
    "submitted_at": "2026-05-12T20:04:59Z",
    "title_canon_sha256": "f0d8dc883b7455148ae50828d219beb5f0cdff82fd651725148346e99300a723"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12704",
    "kind": "arxiv",
    "version": 1
  }
}