Pith Number

pith:IV7VH3NC

pith:2026:IV7VH3NCTL2M6JAD44FIMISHCY

not attested not anchored not stored refs resolved

EMO: Frustratingly Easy Progressive Training of Extendable MoE

Chufan Shi, Eric Xing, Huijuan Wang, Linghao Jin, Nuan Wen, Xuezhe Ma, Zhengzhong Liu

Progressive expansion of MoE expert pools matches fixed-expert performance while cutting training time.

arxiv:2605.13247 v2 · 2026-05-13 · 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{IV7VH3NCTL2M6JAD44FIMISHCY}

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

EMO matches the performance of a fixed-expert setup in large-scale experiments while improving wall-clock efficiency.

C2weakest assumption

Early-stage data may not fully utilize large expert capacity, and progressive expansion can be performed without performance loss by deriving stage-wise token budgets from sparsity in scaling laws.

C3one line summary

EMO progressively expands the expert pool in MoE models during training to match fixed-expert performance with improved wall-clock efficiency.

References

15 extracted · 15 resolved · 8 Pith anchors

[1] Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation · arXiv:1308.3432

[2] Training Verifiers to Solve Math Word Problems · arXiv:2110.14168

[3] DeepSeek-V3 Technical Report · arXiv:2412.19437

[4] The Language Model Evaluation Harness,

[5] Fast- moe: A fast mixture-of-expert training system

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-18T02:44:49.458772Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

457f53eda29af4cf2403e70a86224716237debbe07672b45d6b1ba5d65ccea01

Aliases

arxiv: 2605.13247 · arxiv_version: 2605.13247v2 · doi: 10.48550/arxiv.2605.13247 · pith_short_12: IV7VH3NCTL2M · pith_short_16: IV7VH3NCTL2M6JAD · pith_short_8: IV7VH3NC

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/IV7VH3NCTL2M6JAD44FIMISHCY \
  | 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: 457f53eda29af4cf2403e70a86224716237debbe07672b45d6b1ba5d65ccea01

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "7f830fc5909f93eb47fc2eb578ac012f396b781c316285db184f08906136ac87",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T09:31:09Z",
    "title_canon_sha256": "d6c6ab4c1005de22696dae73565f952d6f7bc1c26319ef73905320fe74a436d3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13247",
    "kind": "arxiv",
    "version": 2
  }
}