Pith Number

pith:46JVBM74

pith:2023:46JVBM74ZEMMPP7PMFYYP6LMPN

not attested not anchored not stored refs pending

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Carlo C Del Mundo, Dmitry Belenko, Iman Mirzadeh, Karen Khatamifard, Keivan Alizadeh, Mehrdad Farajtabar, Minsik Cho, Mohammad Rastegari

arxiv:2312.11514 v3 · 2023-12-12 · cs.CL · cs.AI · 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{46JVBM74ZEMMPP7PMFYYP6LMPN}

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

5 papers in Pith

EnerInfer: Energy-Aware On-Device LLM Inference

Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

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

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Technology solutions targeting the performance of gen-AI inference in resource constrained platforms

Receipt and verification

First computed	2026-07-05T08:50:26.426499Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012

Aliases

arxiv: 2312.11514 · arxiv_version: 2312.11514v3 · doi: 10.48550/arxiv.2312.11514 · pith_short_12: 46JVBM74ZEMM · pith_short_16: 46JVBM74ZEMMPP7P · pith_short_8: 46JVBM74

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/46JVBM74ZEMMPP7PMFYYP6LMPN \
  | 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: e79350b3fcc918c7bfef617187f96c7b5201c576aa6f362c985d5191acdbd012

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bb9d88d62cbdf82435c6d4da7319c19524c296e9ddeb5267dd63d44dad8a7734",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-12-12T18:57:08Z",
    "title_canon_sha256": "e6bf99ac86993acf29ba676c3385ac647f2975d0e550d5369015a9d38d9b8fb0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2312.11514",
    "kind": "arxiv",
    "version": 3
  }
}