Pith Number

pith:Q7ASRHN6

pith:2025:Q7ASRHN6SCKAWFSKM2XTKE43EL

not attested not anchored not stored refs pending

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning

Ammar Ali, Denis Makhov, Dmitriy Shopkhoev, Magauiya Zhussip, Stamatios Lefkimmiatis

CoSpaDi replaces low-rank factorization with a sparse dictionary model that better preserves LLM accuracy at 20-40 percent compression.

arxiv:2509.22075 v6 · 2025-09-26 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Q7ASRHN6SCKAWFSKM2XTKE43EL}

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 Llama and Qwen model families, CoSpaDi consistently improves the accuracy-compression and perplexity-compression trade-offs over state-of-the-art SVD-based baselines and strong structured pruning baselines at 20-40% compression ratios.

C2weakest assumption

The assumption that minimizing functional reconstruction error on a small calibration set will produce a factorization whose downstream task performance remains close to the original model without any fine-tuning or further adaptation.

C3one line summary

CoSpaDi introduces a training-free sparse dictionary learning framework for post-training LLM compression that optimizes functional reconstruction error via activation-derived orthonormalization and achieves improved accuracy-compression trade-offs over SVD and pruning baselines.

Cited by

1 paper in Pith

Motion-Compensated Weight Compression

Receipt and verification

First computed	2026-06-23T01:11:57.156174Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

87c1289dbe90940b164a66af35139b22eb037a47630948cdb0bd9f968d26af09

Aliases

arxiv: 2509.22075 · arxiv_version: 2509.22075v6 · doi: 10.48550/arxiv.2509.22075 · pith_short_12: Q7ASRHN6SCKA · pith_short_16: Q7ASRHN6SCKAWFSK · pith_short_8: Q7ASRHN6

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/Q7ASRHN6SCKAWFSKM2XTKE43EL \
  | 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: 87c1289dbe90940b164a66af35139b22eb037a47630948cdb0bd9f968d26af09

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bc82722b17729c3ca381508862d7ffaa450d2d34c2fcc91ee4412e4685255600",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-09-26T08:55:09Z",
    "title_canon_sha256": "d6e17c26284705680c617022401148f8074164ae5ff3afd6c70469945f8f3af8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.22075",
    "kind": "arxiv",
    "version": 6
  }
}