Paper Citation Record · LEDGER

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

As of 9 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 4 inbound Pith citation observations for arXiv:2506.04997.

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

pith.paper-citation-record.v1
2506.04997 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:34:50.476017Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T16:20:19.874172Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-16T10:17:44.669084Z

Reference resolution

36 of 36 outbound references displayed

verified exact1
verified fuzzy2
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c4335d3a-6921-4dc5-a871-086db87061c9 · outbound

This paper cites PaliGemma: A versatile 3B VLM for transfer.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings PaliGemma: A versatile 3B VLM for transfer

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:47.967212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 514a11b6-ad70-408e-b90d-c9a9cc9db918 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:52.679562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 973dc096-a943-40f6-ac5c-d5d9728186d4 · outbound

This paper cites Rossi, Changyou Chen, and Tong Sun.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Rossi, Changyou Chen, and Tong Sun

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:52.552822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a987dba7-5de2-4296-aecc-049d4b327ee3 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:52.469558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b5544092-a869-4a6b-9b09-20613d430e27 · outbound

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

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.298867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ff8675f-6b21-4411-b323-6c5dd1997472 · outbound

This paper cites Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.341670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a81aebb-10e6-4c09-b7c2-81ddb657f1d5 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:52.332510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4d6c3dcb-c2cb-46b4-9d59-6eb677129d3f · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.469835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 942c9fa1-6462-49b6-8772-85734335801f · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.514132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ba5de4-fad5-48ef-a921-e17af4e79d6a · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.591704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140cea8c-3e1b-40ec-9232-7fde73b63535 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.660446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5b9740e-7b10-4378-9ce6-af4d37c1780b · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:52.178094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fbf8466b-7f6b-45c8-b7c4-46c31086afc5 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.819379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1413e60-66b2-4474-8cc5-4e90d4930ee2 · outbound

This paper cites TokenPacker: Efficient Visual Projector for Multimodal LLM.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.866029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd4a96a3-e744-4317-88b6-1a3852736fd3 · outbound

This paper cites Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:48.952540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba6c668c-259f-4a66-a4ca-b573e76dfbd1 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.030889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8c716eb-8f34-4fbe-b998-d63c1d26ea2b · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:52.005884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1b0633fa-1f7a-47fe-b24d-34f1789bbd26 · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.164741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d25baf-5494-41e2-b3a6-6f5ee645b6f7 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:51.837276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 58d024bb-4cf7-4fd8-9726-ccae9e18de51 · outbound

This paper cites Manmatha, and C.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Manmatha, and C

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:34:51.631527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c4c44aed-6f8f-40c7-995c-540a58f88b35 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:51.432829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6f29794e-0b4a-4dd2-8f1f-36d6e1d43ecc · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.478388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90de8716-48c5-4eb3-8f7b-035fa594ad38 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.536671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36cfd537-d3b7-4f2a-9163-e58487aba55a · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:34:51.235210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 27f5e534-644c-4f2a-875b-05c548853e35 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.665368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0814261-a18d-4dc3-9d68-ead305cccf77 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 26

Resolution: verified exact; raw_fallback, observed 2026-08-07T10:34:50.883764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ba0db544-a3dc-49a4-99ab-304f93204ed0 · outbound

This paper cites Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.797401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb93546-8eaa-423c-a5cd-b4e8df3ee813 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.838297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 914ecf84-8c46-4d30-b1a2-819367705d34 · outbound

This paper cites AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.916745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 629ba998-3c0a-4abc-9d38-c6eb14cba1c7 · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:49.994840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 905b0ba9-1dd5-4e70-b9d2-c604e5930e05 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:50.085393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44d13d5-7738-4f9a-86ef-9a5e82d9b65f · outbound

This paper cites VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:50.174984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89a7c29f-c639-4e22-ae57-216d82d7ed2d · outbound

This paper cites SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:50.294599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce8dcb9c-3b8f-4db1-a1cc-8ffda0837af3 · outbound

This paper cites an unresolved cited work.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:50.374302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf2edb2-42f3-42e0-bfad-e99caa105cfc · outbound

This paper cites online" 'onlinestring :=.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings online" 'onlinestring :=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:50.415916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f679184-4f66-4d4c-9347-319b15eb8377 · outbound

This paper cites write newline.

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings write newline

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:34:50.476017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 85970e61-20e3-4abb-9f6c-5d709d506f12 · inbound

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding cites this paper.

CausalEmbed: Auto-Regressive Multi-Vector Generation in Latent Space for Visual Document Embedding Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:17:44.671695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5c566db8-93ae-4dd2-b054-73ab1c55c255 · inbound

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval cites this paper.

Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:31:04.261270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3717ba08-d5b5-4052-b99b-43d26e915fa0 · inbound

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval cites this paper.

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T16:32:55.757864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72881047-42d5-48b4-ae9d-5f032e5f9f77 · inbound

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval cites this paper.

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-14T16:20:19.874172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.