Pith Number

pith:VUD7OM6Q

pith:2024:VUD7OM6QMRD67TAVPKPACSIKX4

not attested not anchored not stored refs pending

QAQ: Quality Adaptive Quantization for LLM KV Cache

Jiayu Qin, Shichen Dong, Wei Wang, Wen Cheng

arxiv:2403.04643 v2 · 2024-03-07 · 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{VUD7OM6QMRD67TAVPKPACSIKX4}

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.

Cited by

8 papers in Pith

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation

Minimal-Intervention KV Retention via Set-Conditioned Diversity

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Receipt and verification

First computed	2026-07-05T08:07:14.981725Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ad07f733d06447efcc157a9e01490abf2291155d5c6ae93dfddf985166d4501c

Aliases

arxiv: 2403.04643 · arxiv_version: 2403.04643v2 · doi: 10.48550/arxiv.2403.04643 · pith_short_12: VUD7OM6QMRD6 · pith_short_16: VUD7OM6QMRD67TAV · pith_short_8: VUD7OM6Q

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/VUD7OM6QMRD67TAVPKPACSIKX4 \
  | 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: ad07f733d06447efcc157a9e01490abf2291155d5c6ae93dfddf985166d4501c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6ce304b989dc4189fc3b2487a2074d40576379814a603d1da1e92faec8fa1103",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-03-07T16:42:37Z",
    "title_canon_sha256": "4dbc0865d79fe30f5c843c5b43015fa52aafd6c0f15d6bd686c966cdb964c717"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2403.04643",
    "kind": "arxiv",
    "version": 2
  }
}