Pith. sign in

Paper Citation Record · LEDGER

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents

As of 17 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2607.24748.

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

pith.paper-citation-record.v1
2607.24748 v1

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T13:26:31.987399Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

19 of 19 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved19
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 13ca8334-0769-46b6-bae4-6a11d6ec6ba6 · outbound

This paper cites - Start with meta search using document titles and metadata for fast candidate selection.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Start with meta search using document titles and metadata for fast candidate selection

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.449554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.449554Z digest=sha256:6b3765ccf56bd922a6ed82e42545538c6627883856a3ff5e91e82516280ea3e1

Observation cd5af9bd-2028-41e2-a89c-c26eeef662ca · outbound

This paper cites - Perform semantic search using HyDE embeddings for conceptual similarity.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Perform semantic search using HyDE embeddings for conceptual similarity

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.606217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.606217Z digest=sha256:e90bb6b6daee51d0e5e1b0e36f4668dfbfec31ba3b65c81f7b147b0ec9dc5768

Observation 29cb9329-9009-4bca-847a-5ee70afa8bad · outbound

This paper cites Hu, A., Xu, H., Zhang, L., Ye, J., Yan, M., Zhang, J., Jin, Q., Huang, F., and Zhou, J.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents Hu, A., Xu, H., Zhang, L., Ye, J., Yan, M., Zhang, J., Jin, Q., Huang, F., and Zhou, J

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:29.676884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:29.676884Z digest=sha256:9da0cc61610d9b2bea25f81b3eeb63bc134f92d63aaa2cc745752538b9835c9e

Observation 8ea05033-810f-4109-8777-0960d41aebdd · outbound

This paper cites MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:29.810681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:29.810681Z digest=sha256:e43fda69fa81113bd4f867c0b13c3a9ab31583b96dff3aa1d27637a2f68f8c58

Observation d4a5edc3-07b1-4e7d-8d4c-eefd0038f00a · outbound

This paper cites - Include document metadata and chunk positions for traceability.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Include document metadata and chunk positions for traceability

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.028796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.028796Z digest=sha256:0672fcd98cb777a202e74ce85b57cda1c21259a57f693b7c807361e516446f71

Observation fe02b393-dc29-4800-9b77-4e56c2c67881 · outbound

This paper cites Shi, Y ., Wang, J., Shan, Z., Peng, D., Lin, Z., and Jin, L.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents Shi, Y ., Wang, J., Shan, Z., Peng, D., Lin, Z., and Jin, L

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.159099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.159099Z digest=sha256:d8304d5941edbc561192d849e285e86dc44c466478b172a1d67885a7c7d6508f

Observation f9d19562-1b51-4950-8752-e07749f432ce · outbound

This paper cites - Generate evidence from the final chunks with proper source attribution.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Generate evidence from the final chunks with proper source attribution

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.789058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.789058Z digest=sha256:e790a5e086b2ae829005905cf10b7cff7a19e35d9c80df7f8cdaed5bc90b6b40

Observation d7cd0f3d-5b61-4276-a5eb-2163ad1a64d3 · outbound

This paper cites - Do not repeat the same failed search parameters.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Do not repeat the same failed search parameters

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.937442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.937442Z digest=sha256:5b2f9d9ff313e6e51b815c87d9f8d72920977194d3fe286a733b14a322d11362

Observation e4c3dd45-edc8-4a4a-b65a-b2bdc5af6f9e · outbound

This paper cites - Identify restrictive qualifiers in the original query.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Identify restrictive qualifiers in the original query

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.192196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.192196Z digest=sha256:8c427d20d5f20c2d2fc1c16044a3e1b2062927482f5337eeee88ce7eca16dbe0

Observation f9d1d3b8-7012-4545-8b20-2b108d8301c5 · outbound

This paper cites - Remove numerical constraints if not essential.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Remove numerical constraints if not essential

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.350618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.350618Z digest=sha256:70c14526b8a6388383cf6a9981630863b05c8edc4ec8b02df4cb282938a891b4

Observation ded97a5b-c8b6-48eb-a6b7-62b5b4c2b584 · outbound

This paper cites Generate a HyDE (Hypothetical Document Embedding) query for semantic search.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents Generate a HyDE (Hypothetical Document Embedding) query for semantic search

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.446244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.446244Z digest=sha256:42362cf736043f98e40808801da6c509d01c8d6c4ef7d59efbbda7b33884c914

Observation 9e490cef-901d-487c-99a9-44839ced6d46 · outbound

This paper cites - Generate 1-3 sentences, approximately 100-250 tokens.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Generate 1-3 sentences, approximately 100-250 tokens

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.602117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.602117Z digest=sha256:f4d96e9c96ac6e49af5a43e9fbe6c456924d2ccf4b35a5e57c71c511e6c1f151

Observation 74003f01-ffff-4efc-8131-fa9a564f10f8 · outbound

This paper cites - Describe the type of document that would contain the answer.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Describe the type of document that would contain the answer

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.743963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.743963Z digest=sha256:1b03747c45c7df8c5756ba9b07814d07ad159c729a618c28f53c315f4355725e

Observation 8119981a-6a10-4934-819a-217060ac9883 · outbound

This paper cites - Include related concepts and context that might appear in relevant documents.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Include related concepts and context that might appear in relevant documents

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.868542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.868542Z digest=sha256:6f939413a42c999181844cd1676cc29cdec3212a36aad0fb9c0871514131d71b

Observation 3741cb58-0fa7-4d35-ac0b-9d27198684c0 · outbound

This paper cites - Do NOT use question format.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents - Do NOT use question format

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:31.987399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:31.987399Z digest=sha256:20b7ab63f14c179627de4ea698b8260947e9e1a5ad696b30c0a8edc3f4096834

Observation 5ad0e590-b36d-4834-b898-3d7f258b82e3 · outbound

This paper cites emnlp-main.311/.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents emnlp-main.311/

Reference 311

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.000582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.000582Z digest=sha256:408c15d7e5c842ec3e62e6644214c136a59e595c8a8541c9aab7231fa72511ba

Observation 90e48d1b-acc6-4ed1-8d1d-13fa881ad2bb · outbound

This paper cites Retrieval-Augmented Generation with Graphs (GraphRAG).

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents Retrieval-Augmented Generation with Graphs (GraphRAG)

Reference 735

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:29.578873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:29.578873Z digest=sha256:82344a52d6b81489b232a9b6bf45d057d48b43117f7306478d710ecf01c140f7

Observation c5b73bbf-e22c-4165-9cb5-f1312655973b · outbound

This paper cites VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation

Reference 1166

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:30.298761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:30.298761Z digest=sha256:e5463310ef7f5171efc016b9b95f73ef8a1c6493c3a971a76856eed6d12b59c7

Observation 10edcf7f-3bcc-42de-9138-811916a638e0 · outbound

This paper cites ISBN 979-8-89176-251-0.

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents ISBN 979-8-89176-251-0

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-02T13:26:29.528679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T13:26:29.528679Z digest=sha256:97c0be7f4e2583ca31b77943bdee7b5cf4b5e34c0508f6a2e6269270c012b1f3

Pith citing papers

No inbound Pith citation observations are available.