Pith Number

pith:74UNZO64

pith:2026:74UNZO64LBQTVYXH53TQ6BCMWJ

not attested not anchored not stored refs pending

UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization and Distillation

Andreas Geiger, Jonathan von Rad, Yong Cao

Compressed language models preserve factual recall but lose multi-step reasoning, multilingual ability, and instruction following.

arxiv:2602.09130 v5 · 2026-02-09 · 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{74UNZO64LBQTVYXH53TQ6BCMWJ}

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

Through evaluation of six compression techniques across 40 datasets, we observe (i) a consistent knowledge bias, where factual recall is largely preserved while multi-step reasoning, multilingual, and instruction-following capabilities degrade; (ii) a decoupling between performance and reliability, indicating that retained performance does not consistently imply preserved reliability; and (iii) that task-specific calibration can yield up to 50% relative improvement of reasoning performance in pruned models.

C2weakest assumption

The selected benchmarks and compression techniques are representative of general behavior, and the chosen reliability metrics accurately capture real-world safety and consistency issues without hidden selection effects.

C3one line summary

UniComp finds that LLM compression preserves factual recall but degrades multi-step reasoning, multilingual ability, and reliability, while task-specific calibration recovers up to 50% of lost reasoning performance in pruned models.

Receipt and verification

First computed	2026-05-26T01:03:24.997648Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ff28dcbbdc58613ae2e7eee70f044cb248477f5bdd50487758d89f62a967cb24

Aliases

arxiv: 2602.09130 · arxiv_version: 2602.09130v5 · doi: 10.48550/arxiv.2602.09130 · pith_short_12: 74UNZO64LBQT · pith_short_16: 74UNZO64LBQTVYXH · pith_short_8: 74UNZO64

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/74UNZO64LBQTVYXH53TQ6BCMWJ \
  | 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: ff28dcbbdc58613ae2e7eee70f044cb248477f5bdd50487758d89f62a967cb24

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e8e643c8cf05faf8ddc3b076fdaaf3a8df66a9875148d0a653318fcbac0d25eb",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-02-09T19:20:56Z",
    "title_canon_sha256": "37e31a3254c39434f8c64973d10a84c1fc62da8385b019e3b8f3e137135e0ea0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.09130",
    "kind": "arxiv",
    "version": 5
  }
}