Pith Number

pith:3VKZBUIG

pith:2020:3VKZBUIGMAHOM4ZNT4QNQ2Q2F7

not attested not anchored not stored refs resolved

Dense Passage Retrieval for Open-Domain Question Answering

Barlas O\u{g}uz, Danqi Chen, Ledell Wu, Patrick Lewis, Sergey Edunov, Sewon Min, Vladimir Karpukhin, Wen-tau Yih

Dense vector embeddings from a dual-encoder model outperform BM25 by 9-19 percent in top-20 passage retrieval for open-domain question answering.

arxiv:2004.04906 v3 · 2020-04-10 · 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{3VKZBUIGMAHOM4ZNT4QNQ2Q2F7}

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

our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.

C2weakest assumption

That embeddings learned from a small number of questions and passages will generalize to the full distribution of queries and documents encountered at test time without additional adaptation.

C3one line summary

Dense dual-encoder retrievers outperform BM25 by 9-19% absolute in top-20 passage retrieval accuracy across open-domain QA datasets and enable new state-of-the-art end-to-end QA results.

References

113 extracted · 113 resolved · 8 Pith anchors

[1] Passage Re-ranking with

[2] 2020 , booktitle = 2020

[3] Relevance-guided Supervision for OpenQA with

[4] The probabilistic relevance framework:

[5] Learning to Retrieve Reasoning Paths over

Formal links

1 machine-checked theorem link

Cited by

32 papers in Pith

What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA

Retrieval-Augmented Generation for Large Language Models: A Survey

AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models

MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference

Llemma: An Open Language Model For Mathematics

Receipt and verification

First computed	2026-05-17T23:38:50.118168Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89

Aliases

arxiv: 2004.04906 · arxiv_version: 2004.04906v3 · doi: 10.48550/arxiv.2004.04906 · pith_short_12: 3VKZBUIGMAHO · pith_short_16: 3VKZBUIGMAHOM4ZN · pith_short_8: 3VKZBUIG

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/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7 \
  | 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: dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "179520b17eb7655f708fa8cc17a2d0a7759f710681cf9166587ba099b951d8e4",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2020-04-10T04:53:17Z",
    "title_canon_sha256": "c96f5bf3536a0d3e14c11ae7bba5d82215542e366aca2579cd67c8304bdd8f71"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2004.04906",
    "kind": "arxiv",
    "version": 3
  }
}