Pith Number

pith:RVL2XL3F

pith:2026:RVL2XL3FLHYA5HMII57FZRU6YF

not attested not anchored not stored refs resolved

MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification

Shuhao Chen, Sinno Jialin Pan, Weisen Jiang

MetaMoE unifies domain-specialized experts into a single MoE via diversity-aware public proxy selection that approximates private data distributions for router training and expert alignment.

arxiv:2605.14289 v1 · 2026-05-14 · cs.LG · cs.AI · cs.CL · cs.CR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RVL2XL3FLHYA5HMII57FZRU6YF}

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

Experiments on computer vision and natural language processing benchmarks demonstrate that MetaMoE consistently outperforms recent privacy-preserving MoE unification methods.

C2weakest assumption

Public proxy data selected for domain relevance and diversity can sufficiently approximate inaccessible private data distributions to supervise router learning and expert alignment without introducing large distribution shift.

C3one line summary

MetaMoE unifies domain-specialized experts into a single MoE via diversity-aware public proxy selection that approximates private data distributions for router training and expert alignment.

References

12 extracted · 12 resolved · 1 Pith anchors

[1] Mixture-of-loras: An efficient multitask tuning for large language models

[2] Branch-train-merge: Embarrassingly parallel training of ex- pert language models.arXiv preprint arXiv:2208.03306

[3] The flan collection: Designing data and methods for effective instruction tuning · arXiv:2301.13688

[4] Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities · arXiv:2408.07666

[5] 12 Title Suppressed Due to Excessive Size A. Computation of Relevance Score Following FlexOlmo (Shi et al., 2025), we compute the relevance score g(x,D p) of a public sample x∈ D 0 with respect to a c 2025

Receipt and verification

First computed	2026-05-17T23:39:10.213906Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8d57abaf6559f00e9d88477e5cc69ec14c5bc0c71a7818f05cdcb4dc1b3e09b9

Aliases

arxiv: 2605.14289 · arxiv_version: 2605.14289v1 · doi: 10.48550/arxiv.2605.14289 · pith_short_12: RVL2XL3FLHYA · pith_short_16: RVL2XL3FLHYA5HMI · pith_short_8: RVL2XL3F

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/RVL2XL3FLHYA5HMII57FZRU6YF \
  | 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: 8d57abaf6559f00e9d88477e5cc69ec14c5bc0c71a7818f05cdcb4dc1b3e09b9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3168e50b2f266609e6f77c079ccd113d5d261985456fd3d68a23c56b8de5c1ce",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.CR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T02:48:23Z",
    "title_canon_sha256": "945de5ef473298834c078e322335fed3d5ebf902138f911257bc0e96ae13a74d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14289",
    "kind": "arxiv",
    "version": 1
  }
}