Pith Number

pith:53ID4WUY

pith:2022:53ID4WUY5AAS75FEMZXSW4LOMZ

not attested not anchored not stored refs resolved

Atlas: Few-shot Learning with Retrieval Augmented Language Models

Armand Joulin, Edouard Grave, Fabio Petroni, Gautier Izacard, Jane Dwivedi-Yu, Lucas Hosseini, Maria Lomeli, Patrick Lewis, Sebastian Riedel, Timo Schick

Atlas, a retrieval-augmented language model, reaches over 42 percent accuracy on Natural Questions with only 64 examples while using 50 times fewer parameters than a 540 billion parameter model.

arxiv:2208.03299 v3 · 2022-08-05 · 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{53ID4WUY5AAS75FEMZXSW4LOMZ}

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.

Claims

C1strongest claim

Atlas reaches over 42% accuracy on Natural Questions using only 64 examples, outperforming a 540B parameters model by 3% despite having 50x fewer parameters.

C2weakest assumption

That the retrieval index supplies accurate, relevant knowledge and that the pre-training plus few-shot setup reliably transfers this knowledge without the model needing to store facts internally.

C3one line summary

Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.

References

232 extracted · 232 resolved · 46 Pith anchors

[1] Re2g: Retrieve, rerank, generate, 2022 · doi:10.48550/arxiv.2207.06300

[2] Proofver: Natural logic theorem proving for fact verification, 2021 · doi:10.48550/arxiv.2108.11357

[3] 2018 , volume = 2018 · doi:10.3233/sw-170273

[4] Robust Disambiguation of Named Entities in Text 2011

[6] T - RE x: A Large Scale Alignment of Natural Language with Knowledge Base Triples 2018

Formal links

2 machine-checked theorem links

Cited by

29 papers in Pith

Retrieval-Augmented Generation for Large Language Models: A Survey

A Survey on Foundation Models for Personalized Federated Intelligence

HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support

A Comprehensive Overview of Large Language Models

Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems

Receipt and verification

First computed	2026-05-17T23:38:47.704051Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

eed03e5a98e8012ff4a4666f2b716e6658dc8194c6f9a0785d56a623555d48f0

Aliases

arxiv: 2208.03299 · arxiv_version: 2208.03299v3 · doi: 10.48550/arxiv.2208.03299 · pith_short_12: 53ID4WUY5AAS · pith_short_16: 53ID4WUY5AAS75FE · pith_short_8: 53ID4WUY

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/53ID4WUY5AAS75FEMZXSW4LOMZ \
  | 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: eed03e5a98e8012ff4a4666f2b716e6658dc8194c6f9a0785d56a623555d48f0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bde059df50fd45afa6a2e95cfc49613066bcd5bc2ceafcdfb683eaec6bc5515a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-08-05T17:39:22Z",
    "title_canon_sha256": "7a9b5aa924eb0af2ec244f3a0898da87f21266d4b237aba1b6ff582e8c4b60bc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2208.03299",
    "kind": "arxiv",
    "version": 3
  }
}