Paper Citation Record · LEDGER

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering

As of 16 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2607.16604.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.16604 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T20:32:18.470918Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4538cbe8-2dbb-475d-a672-4ffbaf2b5c3d · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive NLP tasks,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Retrieval-augmented generation for knowledge-intensive NLP tasks,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.251203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2484dc6-277a-4892-a94f-9a32cfe08242 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.307158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd6590b-41cf-4959-9b21-89f4ffb1fc38 · outbound

This paper cites CRAG – comprehensive RAG benchmark,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering CRAG – comprehensive RAG benchmark,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.383796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aa02689-8a88-4a35-b7de-de4ce9f9e8ad · outbound

This paper cites PixelRAG: Web screenshots beat text for retrieval-augmented generation,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering PixelRAG: Web screenshots beat text for retrieval-augmented generation,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.451693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c41c072-4d1d-4c41-a45b-bcd9ca294923 · outbound

This paper cites MMed-RAG: Versatile multimodal RAG system for medical vision language models,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering MMed-RAG: Versatile multimodal RAG system for medical vision language models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.533879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71cda8c7-be2b-4456-8664-0d00a92680bd · outbound

This paper cites ColPali: Efficient Document Retrieval with Vision Language Models.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering ColPali: Efficient Document Retrieval with Vision Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.609691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38202c8e-1352-40f8-8e5f-49333e582865 · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.683589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2961fbf4-4c70-4e04-b49f-5794a096b1ba · outbound

This paper cites M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.757013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75a98041-c246-4ae1-b583-61b5df60b1d7 · outbound

This paper cites Bench- marking retrieval-augmented multimodal generation for document ques- tion answering,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Bench- marking retrieval-augmented multimodal generation for document ques- tion answering,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.831867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a947caf0-4aec-494c-b325-d19702c61a1c · outbound

This paper cites MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering MKG-RAG-Bench: Benchmarking Retrieval in Multimodal Knowledge Graph-Augmented Generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:16.940686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0df98cbf-d124-4e4b-8a18-b8a3ec85d35a · outbound

This paper cites Multimodal Graph RAG for Long-range Visually Rich Document Understanding.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Multimodal Graph RAG for Long-range Visually Rich Document Understanding

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.046207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c65138aa-1e9e-4bbc-b82e-20bfc427b024 · outbound

This paper cites PubLayNet: Largest dataset ever for document layout analysis,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering PubLayNet: Largest dataset ever for document layout analysis,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.141690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72ea4953-00d7-43b3-bd4c-2f6c05371d90 · outbound

This paper cites Dense passage retrieval for open-domain question an- swering,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Dense passage retrieval for open-domain question an- swering,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.238396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 404be34c-1306-4259-842e-15b540679c4c · outbound

This paper cites RAGAS: Au- tomated evaluation of retrieval augmented generation,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering RAGAS: Au- tomated evaluation of retrieval augmented generation,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.311439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb8ed7eb-211c-4d71-b00d-e290c0d85bb7 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Learning transferable visual models from natural language supervi- sion,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.430209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be24bd1-9b21-478b-9344-169cc01c42d1 · outbound

This paper cites Exploring network structure, dynamics, and function using NetworkX,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Exploring network structure, dynamics, and function using NetworkX,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.554305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 624cf77c-f692-4444-99b6-2579d894742d · outbound

This paper cites GPT-4o System Card.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering GPT-4o System Card

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.719928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 909d2372-3f05-42b9-959b-12b4f5a02110 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Gemini: A Family of Highly Capable Multimodal Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.861687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf9a9633-d9c6-4992-ac86-61c4437cf19e · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering The llama 4 herd: The beginning of a new era of natively multimodal ai innovation,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:17.930733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57c0fbe5-9473-4b98-a96d-02fdcbc34322 · outbound

This paper cites Llama 4 Scout 17B 16E Instruct model card,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Llama 4 Scout 17B 16E Instruct model card,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:18.012147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ee55f96-babc-4f2b-be52-48b64d90d6a6 · outbound

This paper cites Llama 4 Maverick 17B 128E Instruct FP8 model card,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Llama 4 Maverick 17B 128E Instruct FP8 model card,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:18.160411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af91b799-d97e-4683-b29c-3868a71553bc · outbound

This paper cites small-publaynet-wds,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering small-publaynet-wds,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:18.234692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eeaa352-7929-4222-add8-fc5430cbbd2a · outbound

This paper cites New embedding models and api updates,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering New embedding models and api updates,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:18.307058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c29ff7-5178-45d8-acc6-b89a510fde9f · outbound

This paper cites Billion-scale similarity search with GPUs,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering Billion-scale similarity search with GPUs,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:18.430312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7515ff62-6b24-47d0-bf3f-ff1eb4864bff · outbound

This paper cites GPT-4o mini: Advancing cost-efficient intelligence,.

When Do Multimodal and Graph-Augmented RAG Help? A Controlled Evaluation for Document Question Answering GPT-4o mini: Advancing cost-efficient intelligence,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T20:32:18.470918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.