pith. sign in
Pith Number

pith:Z7S4EGPJ

pith:2025:Z7S4EGPJS44PWAI7BF3OJV6QAL
not attested not anchored not stored refs resolved

Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry

Behrooz Tahmasebi, Melanie Weber

Approximate symmetry can be enforced with only logarithmic averaging complexity while exact symmetry requires linear complexity in the group size.

arxiv:2512.11855 v2 · 2025-12-05 · cs.LG · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{Z7S4EGPJS44PWAI7BF3OJV6QAL}

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

under standard conditions, exact symmetry requires linear averaging complexity, whereas approximate symmetry can be attained with only logarithmic complexity in the group size.

C2weakest assumption

The unspecified 'standard conditions' under which the exponential separation holds, and that averaging complexity is the appropriate measure of the cost of enforcing symmetry.

C3one line summary

Approximate symmetry can be enforced with logarithmic averaging complexity while exact symmetry requires linear complexity in the group size.

References

5 extracted · 5 resolved · 1 Pith anchors

[1] Approximately symmetric neural networks for quantum spin liquids.Physical Review Letters, 135 (5):056702, 2025 2025
[2] On the Burnside-Brauer-Steinberg theorem 2022 · arXiv:1409.7632
[3] Complete sets of representations of algebras.Proceedings of the American Math- ematical Society, 13(5):746–747, 1962 1962
[4] User-friendly tail bounds for sums of random matrices.Foundations of computational mathematics, 12(4):389–434, 2012 2012
[5] 1, 3 13 Preprint A BACKGROUND FORPROOFS This appendix collects the background used in our proofs. We briefly review finite groups, group actions, group representations, character theory, and Fourier a 1977

Cited by

1 paper in Pith

Receipt and verification
First computed 2026-05-17T23:39:16.886020Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

cfe5c219e99738fb011f0976e4d7d002c968d4ee4b54d2014dbe39bdc8a88c0a

Aliases

arxiv: 2512.11855 · arxiv_version: 2512.11855v2 · doi: 10.48550/arxiv.2512.11855 · pith_short_12: Z7S4EGPJS44P · pith_short_16: Z7S4EGPJS44PWAI7 · pith_short_8: Z7S4EGPJ
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z7S4EGPJS44PWAI7BF3OJV6QAL \
  | 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: cfe5c219e99738fb011f0976e4d7d002c968d4ee4b54d2014dbe39bdc8a88c0a
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "a9cbbf128fe3283786a526e3b12a463660e220dd63e2ab1b9adc10b578404806",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-12-05T03:18:18Z",
    "title_canon_sha256": "1a3b44eba6d740dca13d946bc3ba1fd512fb76f5ec3b5e4a70e13e53c18cdb8d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.11855",
    "kind": "arxiv",
    "version": 2
  }
}