Pith Number

pith:MFCSPPSD

pith:2026:MFCSPPSDL2IWCNPIUB4K3QRHSZ

not attested not anchored not stored refs pending

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling

Anshuman Chhabra, Ocean Monjur, Shahriar Kabir Nahin

Unstructured pruning can enhance test-time scaling performance in reasoning LLMs and sometimes surpass the original full models.

arxiv:2604.25098 v2 · 2026-04-28 · cs.AI · cs.CL · 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{MFCSPPSDL2IWCNPIUB4K3QRHSZ}

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

our extensive experiments across four reasoning benchmarks on two reasoning LLMs: s1.1-7B and Qwen3-8B, consistently show that unstructured pruning augments TTS performance compared to structured pruning, and at times can even outperform the unpruned full-weight LLMs.

C2weakest assumption

That the specific unstructured pruning implementations and layer-wise sparsity allocation strategies chosen do not introduce hidden biases or overfit to the four benchmarks, and that results will generalize beyond the tested models and tasks.

C3one line summary

Unstructured pruning augments test-time scaling reasoning performance in LLMs and can outperform the unpruned model on benchmarks, contrary to expectations from structured pruning studies.

Receipt and verification

First computed	2026-05-29T01:05:10.585343Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

614527be435e916135e8a078adc2279672935fe36c6aac9748396704e7268cd9

Aliases

arxiv: 2604.25098 · arxiv_version: 2604.25098v2 · doi: 10.48550/arxiv.2604.25098 · pith_short_12: MFCSPPSDL2IW · pith_short_16: MFCSPPSDL2IWCNPI · pith_short_8: MFCSPPSD

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/MFCSPPSDL2IWCNPIUB4K3QRHSZ \
  | 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: 614527be435e916135e8a078adc2279672935fe36c6aac9748396704e7268cd9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6f70b08c28aba9830f635b821f12b065ea57ae29d83e77ff0b1b0c109b98463b",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-28T01:04:09Z",
    "title_canon_sha256": "e91c863716a629e04247d0bb4438c0092697100616644fbee312afa49d92d4fd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.25098",
    "kind": "arxiv",
    "version": 2
  }
}