Pith Number

pith:EI4V2FMT

pith:2024:EI4V2FMTSLXIYEQHFWZYC7SAYN

not attested not anchored not stored refs pending

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore

Akari Asai, Jacqueline He, Luke Zettlemoyer, Pang Wei Koh, Rulin Shao, Sewon Min, Tim Dettmers, Weijia Shi

arxiv:2407.12854 v1 · 2024-07-09 · cs.CL · cs.AI · cs.IR · 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{EI4V2FMTSLXIYEQHFWZYC7SAYN}

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

4 papers in Pith

Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering

Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge Conflicts

Scaling Laws for Cross-Encoder Reranking

Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Receipt and verification

First computed	2026-07-05T08:45:12.635907Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

22395d159392ee8c12072db3817e40c35dc0c46922b445d6e66d369d977c6304

Aliases

arxiv: 2407.12854 · arxiv_version: 2407.12854v1 · doi: 10.48550/arxiv.2407.12854 · pith_short_12: EI4V2FMTSLXI · pith_short_16: EI4V2FMTSLXIYEQH · pith_short_8: EI4V2FMT

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/EI4V2FMTSLXIYEQHFWZYC7SAYN \
  | 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: 22395d159392ee8c12072db3817e40c35dc0c46922b445d6e66d369d977c6304

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "33472807aa0272b4c8c2bb215b64589cf959ee09c53081a9f69a79db9a13827e",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.IR",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-07-09T08:27:27Z",
    "title_canon_sha256": "b2026cea641933523da41a3f245419298ac409758bcd57d5de305bc19a2da68e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2407.12854",
    "kind": "arxiv",
    "version": 1
  }
}