Pith Number

pith:URUH7CGY

pith:2026:URUH7CGY5JSYYLUFN72GO7KPYG

not attested not anchored not stored refs resolved

MARQUIS: A Three-Stage Pipeline for Video Retrieval-Augmented Generation

Alexander Martin, Benjamin Van Durme, Debashish Chakraborty, Dengjia Zhang, Hanting Liu, Hanxiang Qin, Jialiang Jin, Katherine Guerrerio, Reno Kriz, Tyler Skow

MARQUIS is a three-stage pipeline that lifts video retrieval-augmented generation performance on complex queries and long contexts.

arxiv:2605.17640 v1 · 2026-05-17 · cs.IR · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{URUH7CGY5JSYYLUFN72GO7KPYG}

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

On the MAGMaR2026 shared task, we improve retrieval performance from 0.195 to 0.759 (nDCG@10). For article generation, ITER-QA-BASE improves average human score from 3.09 to 3.83 over the CAG baseline, while MARQUIS-RLM achieves a human score of 3.30 and the strongest citation recall among non-QA systems.

C2weakest assumption

The improvements are attributable to the three-stage pipeline design rather than implementation details, baseline choices, or task-specific tuning not described in the abstract.

C3one line summary

MARQUIS is a three-stage pipeline for video RAG that boosts retrieval nDCG@10 from 0.195 to 0.759 and generation human scores on the MAGMaR2026 shared task.

References

65 extracted · 65 resolved · 1 Pith anchors

[1] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks 2018 · arXiv:2005.11401

[2] Streamlining evaluation with ir-measures. In Advances in Information Retrieval - 44th European Conference on IR Research, ECIR 2022, Stavanger , Norway, April 10-14, 2022, Proceedings, Part II, volume 2022

[3] Alec Radford, Jong Wook Kim, Tao Xu, Greg Brock- man, Christine Mcleavey, and Ilya Sutskever 2023

[4] arXiv preprint arXiv:2509.23040 , year= 2026

[5] Do not merge separate information needs into one sub-query

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:04:50.176880Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb

Aliases

arxiv: 2605.17640 · arxiv_version: 2605.17640v1 · doi: 10.48550/arxiv.2605.17640 · pith_short_12: URUH7CGY5JSY · pith_short_16: URUH7CGY5JSYYLUF · pith_short_8: URUH7CGY

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/URUH7CGY5JSYYLUFN72GO7KPYG \
  | 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: a4687f88d8ea658c2e856ff4677d4fc1a9b6b0c91ec3b57072c2704a10da90eb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dbdcec7d7b0396ab89a39f08f277a62bae79d552ff17ac74ba103c97e80cd862",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.IR",
    "submitted_at": "2026-05-17T20:19:04Z",
    "title_canon_sha256": "d7845a728df11776d8f1b0be42546af7c1e0a67091959524c8612dbf44164cd5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.17640",
    "kind": "arxiv",
    "version": 1
  }
}