Pith Number

pith:L5WJP2YP

pith:2024:L5WJP2YPS3T67AUPDYJN6GDT2G

not attested not anchored not stored refs pending

Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention

Bin Gao, Djordje Jevdjic, Junbo Deng, Pengfei Zuo, Puru Sharma, Qingxuan Kang, Xingkun Yang, Zhou Yu, Zhuomin He

arxiv:2403.19708 v3 · 2024-03-23 · 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{L5WJP2YPS3T67AUPDYJN6GDT2G}

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

10 papers in Pith

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

KernelSight-LM: A Kernel-Level LLM Inference Simulator

ITME: Inference Tiered Memory Expansion with Disaggregated CXL-Hybrid Memories

Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving

KernelSight-LM: A Kernel-Level LLM Inference Simulator

Receipt and verification

First computed	2026-07-05T08:38:07.931273Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5f6c97eb0f96e7ef828f1e12df1873d1afac944c35e8472f5079a5ce3343e3ba

Aliases

arxiv: 2403.19708 · arxiv_version: 2403.19708v3 · doi: 10.48550/arxiv.2403.19708 · pith_short_12: L5WJP2YPS3T6 · pith_short_16: L5WJP2YPS3T67AUP · pith_short_8: L5WJP2YP

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/L5WJP2YPS3T67AUPDYJN6GDT2G \
  | 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: 5f6c97eb0f96e7ef828f1e12df1873d1afac944c35e8472f5079a5ce3343e3ba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "038a86b101e9c62cf668c40270e5aa0cc2f98e89e1df085262abf0a111e2ca51",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-03-23T10:42:49Z",
    "title_canon_sha256": "aaf35dcc51cd5df1174e1992dde2fb728c1010ef91b70c6d98717b5c58a04a42"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2403.19708",
    "kind": "arxiv",
    "version": 3
  }
}