Pith Number

pith:B7XDWRI4

pith:2026:B7XDWRI47A3YI3JUJJVZDT5III

not attested not anchored not stored refs pending

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training

Bo Zheng, Dayiheng Liu, Liangyu Wang, Rui Men, Shengkun Tang, Siqi Zhang, Xiulong Yuan, Zekun Wang, Zhiqiang Shen, Zihan Qiu

Pruning a pretrained large MoE consistently outperforms training the smaller target architecture from scratch under the same training budget.

arxiv:2605.08738 v2 · 2026-05-09 · cs.LG · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{B7XDWRI47A3YI3JUJJVZDT5III}

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 depth, width, and expert compression, pruning a pretrained MoE consistently outperforms training the target architecture from scratch under the same training budget; progressive pruning schedules outperform one-shot compression.

C2weakest assumption

That the observed convergence of different one-shot expert compression methods after large-scale continual pretraining will generalize beyond the specific Qwen3-Next-80A3B model and the chosen downstream benchmarks.

C3one line summary

Pruning pretrained MoE models outperforms training from scratch, different compression methods converge after continued pretraining, and combining KD with language modeling loss plus progressive schedules yields a competitive 23A2B model from Qwen3-Next-80A3B.

Cited by

1 paper in Pith

ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation

Receipt and verification

First computed	2026-05-20T00:04:34.992568Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0fee3b451cf837846d344a6b91cfa8423e2a12641676538d0577db1ea14f41df

Aliases

arxiv: 2605.08738 · arxiv_version: 2605.08738v2 · doi: 10.48550/arxiv.2605.08738 · pith_short_12: B7XDWRI47A3Y · pith_short_16: B7XDWRI47A3YI3JU · pith_short_8: B7XDWRI4

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/B7XDWRI47A3YI3JUJJVZDT5III \
  | 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: 0fee3b451cf837846d344a6b91cfa8423e2a12641676538d0577db1ea14f41df

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dd75df23f929b8bad3a1878c02869cdebdf0033ee3e365b579a310e61361a38d",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-09T06:50:35Z",
    "title_canon_sha256": "d690173b393dfc6bc5926ee52dd327d38501a6e48b0392e1e7e4e6f3152c0c84"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.08738",
    "kind": "arxiv",
    "version": 2
  }
}