Pith Number

pith:GHGZHR4S

pith:2024:GHGZHR4SOWGX4TA3PXLCKRLDTD

not attested not anchored not stored refs pending

Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve

Alexey Tumanov, Amey Agrawal, Ashish Panwar, Bhargav S. Gulavani, Jayashree Mohan, Nipun Kwatra, Nitin Kedia, Ramachandran Ramjee

arxiv:2403.02310 v3 · 2024-03-04 · cs.LG · cs.DC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GHGZHR4SOWGX4TA3PXLCKRLDTD}

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

26 papers in Pith

Think Before You Grid-Search: Floor-First Triage for LLM Serving

Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion

Load Testing for Machine Learning Model Serving Systems at Scale

Token-Operations-Oriented Inference Optimization Techniques for Large Models

Receipt and verification

First computed	2026-07-05T08:33:01.323232Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

31cd93c792758d7e4c1b7dd625456398e6251473abcd60e225de119b96fb4e8b

Aliases

arxiv: 2403.02310 · arxiv_version: 2403.02310v3 · doi: 10.48550/arxiv.2403.02310 · pith_short_12: GHGZHR4SOWGX · pith_short_16: GHGZHR4SOWGX4TA3 · pith_short_8: GHGZHR4S

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/GHGZHR4SOWGX4TA3PXLCKRLDTD \
  | 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: 31cd93c792758d7e4c1b7dd625456398e6251473abcd60e225de119b96fb4e8b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "61171ab1ac6d3cc06344843109ff0dde116bddafdf3beb2a4873e09ab5e48647",
    "cross_cats_sorted": [
      "cs.DC"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-03-04T18:47:08Z",
    "title_canon_sha256": "fb6101eaa47cfb38dc7c3b00b9657dc6764af414e743aea0ff6f5b2ba154f349"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2403.02310",
    "kind": "arxiv",
    "version": 3
  }
}