Paper Citation Record · LEDGER

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

As of 7 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 3 inbound Pith citation observations for arXiv:2508.07493.

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

pith.paper-citation-record.v1
2508.07493 v2

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T22:10:08.326585Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-08T20:30:59.126121Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-08T20:35:34.394180Z

Reference resolution

66 of 66 outbound references displayed

verified exact2
verified fuzzy31
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cef3d718-2b83-49af-b4eb-40d8a75fdd03 · outbound

This paper cites Ask in any modality: A comprehensive survey on multimodal retrieval-augmented generation, 2025.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Ask in any modality: A comprehensive survey on multimodal retrieval-augmented generation, 2025

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.400345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 49a2697d-b88d-4b04-961d-8c0987481054 · outbound

This paper cites Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.075964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2ffbca-14ff-4c85-b1c6-71f3de933b71 · outbound

This paper cites Scene text visual question answering.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Scene text visual question answering

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.387813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 236003d3-acec-4c0a-b34f-932a000559ec · outbound

This paper cites M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.085053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17ee1c91-bd37-4bdd-b3c7-811c5e3a18e8 · outbound

This paper cites MMR: Evaluating Reading Ability of Large Multimodal Models.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding MMR: Evaluating Reading Ability of Large Multimodal Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:10:08.828773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 427bba16-f186-4e88-8af2-fbe1d210e983 · outbound

This paper cites SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.093349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686aaee8-751d-4f80-adcb-3b263e763ec3 · outbound

This paper cites InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.097589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe50c63-4ed7-409d-a45e-8fe5940338bb · outbound

This paper cites M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.101248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba546d15-0083-4c4f-bd2f-46129c89b4e3 · outbound

This paper cites Mmvqa: A comprehensive dataset for investigating multipage multimodal information retrieval in pdf-based visual question answering.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Mmvqa: A comprehensive dataset for investigating multipage multimodal information retrieval in pdf-based visual question answering

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.376320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bc034659-1053-4925-b18d-9e75c27f4a8b · outbound

This paper cites Mmdocir: Benchmarking multi-modal retrieval for long documents.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Mmdocir: Benchmarking multi-modal retrieval for long documents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.108542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e66d650-7e94-4262-9dba-76ccc06a12bb · outbound

This paper cites PP-OCR: A Practical Ultra Lightweight OCR System.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding PP-OCR: A Practical Ultra Lightweight OCR System

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.112765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb663534-4708-4585-b950-ec34a7f6396c · outbound

This paper cites Colpali: Efficient document retrieval with vision language models, 2024.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Colpali: Efficient document retrieval with vision language models, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.365473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3839b108-bf82-4209-a682-6e971dacc5a3 · outbound

This paper cites Exploring the frontier of vision-language models: A survey of current methodologies and future direc- tions.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Exploring the frontier of vision-language models: A survey of current methodologies and future direc- tions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.120202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67c4d1d6-05bb-4042-900a-2df0fe228000 · outbound

This paper cites GPT-4o System Card.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding GPT-4o System Card

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.124378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25facea2-f7f6-4d1d-ae90-eec21fdc58f4 · outbound

This paper cites FinanceBench: A New Benchmark for Financial Question Answering.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding FinanceBench: A New Benchmark for Financial Question Answering

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.128979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce12ed8f-f79e-4f24-874a-71968cbf950d · outbound

This paper cites Mistral 7B.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Mistral 7B

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.132923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4401a79d-ceba-45eb-bd92-96292f0a2121 · outbound

This paper cites VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.136811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8178269d-3ae0-44d5-9ba9-589d7024731a · outbound

This paper cites Colbert: Efficient and effective passage search via contextualized late interaction over bert.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Colbert: Efficient and effective passage search via contextualized late interaction over bert

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.352324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e254639f-2e33-484c-87c7-28b6ff9e545a · outbound

This paper cites Building and better understanding vision-language models: insights and future directions.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Building and better understanding vision-language models: insights and future directions

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.145820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e85c21d5-6ce7-49c9-a880-20486e152a65 · outbound

This paper cites NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.149428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6a6873c-73af-4d37-b112-bbf862166eb0 · outbound

This paper cites CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-05T22:10:08.541500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f41e5b77-b01d-417b-9af1-f9c64d773573 · outbound

This paper cites Towards visual text grounding of multimodal large language model.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Towards visual text grounding of multimodal large language model

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.156626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c52f217-b39f-4eae-8729-03018f9ad76e · outbound

This paper cites Chatqa: Building gpt-4 level conversational qa models.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Chatqa: Building gpt-4 level conversational qa models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.340001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e2e274e-6fc6-4b8d-b793-bdaac0a7bc63 · outbound

This paper cites Unifying Multimodal Retrieval via Document Screenshot Embedding.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Unifying Multimodal Retrieval via Document Screenshot Embedding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.163447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 539bd716-b703-4f35-bd20-4a0174b3bf81 · outbound

This paper cites MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.166980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c855fdf-38c4-4dc0-989b-5f88e97bf2fe · outbound

This paper cites Chartqa: A benchmark for question answering about charts with visual and logical reasoning, 2022.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Chartqa: A benchmark for question answering about charts with visual and logical reasoning, 2022

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.171236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dab151a3-4749-4307-ac39-70c52a018b2e · outbound

This paper cites V Jawahar.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding V Jawahar

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.322398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d6ba0b1-06cd-4a3d-bcee-703b04a1b437 · outbound

This paper cites Docvqa: A dataset for vqa on document images.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Docvqa: A dataset for vqa on document images

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.310288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6a8bb147-62c3-4461-aaa6-2ede29c9886a · outbound

This paper cites an unresolved cited work.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-05T22:10:09.297590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0991974f-67fc-4a92-8ac9-52703c17303d · outbound

This paper cites Infographicvqa.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Infographicvqa

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.287121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1cbcec69-b295-4927-9eea-018fcc8cdba1 · outbound

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

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Learning transferable visual models from natural language supervi- sion

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.188996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a57f2eb-4f56-45bb-bff0-972b5bc44ece · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.192384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 298f9ed9-afbc-4c2c-9288-e10c7e74780f · outbound

This paper cites The probabilistic relevance framework: Bm25 and beyond.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding The probabilistic relevance framework: Bm25 and beyond

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.197362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 428e2e7d-8199-4a49-9c58-b2f70941b2a0 · outbound

This paper cites CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.200780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fbde0bf-ea6f-4e3a-a360-1a19eabb338c · outbound

This paper cites Textocr: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Textocr: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.263242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d1815816-bec4-4e11-acf0-527dac0a6236 · outbound

This paper cites PaliGemma 2: A Family of Versatile VLMs for Transfer.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding PaliGemma 2: A Family of Versatile VLMs for Transfer

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.208206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b81e0c3e-2dac-4d10-911c-bcf57a3e07fe · outbound

This paper cites Slidevqa: A dataset for document visual question answering on multiple images.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Slidevqa: A dataset for document visual question answering on multiple images

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.249944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bbcbc31f-1536-48bd-b1f5-f15156d55e78 · outbound

This paper cites Hi- erarchical multimodal transformers for multipage docvqa.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Hi- erarchical multimodal transformers for multipage docvqa

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.236420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f00acd49-5a06-4e0f-9e0a-198588d902a5 · outbound

This paper cites Ccpdf: Building a high quality corpus for visually rich documents from web crawl data.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Ccpdf: Building a high quality corpus for visually rich documents from web crawl data

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.224271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 695fa568-86b0-4283-b7cd-fd17737a10ce · outbound

This paper cites Document understanding dataset and evaluation (dude).

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Document understanding dataset and evaluation (dude)

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.212398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 04ba4415-aea9-419e-be8c-4388905b652e · outbound

This paper cites Needle in a multimodal haystack.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Needle in a multimodal haystack

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.200594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 062f3806-bfe6-4314-9aa3-6e8a2fea737c · outbound

This paper cites SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.231807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d4f2a7-320c-4b62-802a-370574976ebb · outbound

This paper cites C-Pack: Packed Resources For General Chinese Embeddings.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding C-Pack: Packed Resources For General Chinese Embeddings

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.236037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb41c3c8-b199-4735-9d7c-a93153a199cf · outbound

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

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.240158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 112787aa-b36f-40d4-8470-18808813eaa1 · outbound

This paper cites Sigmoid loss for language image pre-training.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Sigmoid loss for language image pre-training

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.190017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 174ac9e7-7817-48c3-b7a4-a7056ac16699 · outbound

This paper cites Vision-language models for vision tasks: A survey.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Vision-language models for vision tasks: A survey

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.247951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e84236d5-00f3-42ac-ba1c-8225e3b66a8b · outbound

This paper cites GME: Improving Universal Multimodal Retrieval by Multimodal LLMs.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.251950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dccb1653-7e37-4aff-8044-5805b4604376 · outbound

This paper cites Multilingual Large Language Models: A Systematic Survey.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Multilingual Large Language Models: A Systematic Survey

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T22:10:08.255901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d9415f7-ecb0-4587-bb78-a591530a7ddc · outbound

This paper cites Figure 3.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Figure 3

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.170235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b9f4a5a2-f0a5-4814-9487-29d892cd3f1a · outbound

This paper cites • If multiple figures or tables exist, distinguish them based on their title, description, or content.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding • If multiple figures or tables exist, distinguish them based on their title, description, or content

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.158776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b9ebb48a-fa49-40ae-858f-0310d05fdaa1 · outbound

This paper cites detected_language.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding detected_language

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.146526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5d51418f-cb26-46cf-8bc7-4349fd89146d · outbound

This paper cites an unresolved cited work.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-05T22:10:09.134902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd00dd00-3833-40e2-bddd-9af86d00cae3 · outbound

This paper cites Now, please revise the given question pair according to these guidelines.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Now, please revise the given question pair according to these guidelines

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.123366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 34021eb1-0a6a-4f6c-8f98-691c52fda117 · outbound

This paper cites The question should be about the subject of the page, and the answer needs to be found in the page.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding The question should be about the subject of the page, and the answer needs to be found in the page

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.112226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eb5dcbb4-ca4c-4c51-97f0-c48a0e464fa9 · outbound

This paper cites Generate a question that could be asked by provided infomation in the given page.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Generate a question that could be asked by provided infomation in the given page

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.099368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e23b6640-6fd2-4a3b-baaa-3d32f995ec08 · outbound

This paper cites Please do not generate:.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Please do not generate:

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:09.088464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7eec0267-3ef8-4805-a2e7-f668a91285d7 · outbound

This paper cites What is the page number?.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding What is the page number?

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.965761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 22e9eb5a-af8e-4ac2-823f-e10107f08c61 · outbound

This paper cites detected_language.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding detected_language

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.954615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e62c39ae-2e71-46df-9c17-3d99cbfca7c3 · outbound

This paper cites an unresolved cited work.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-05T22:10:08.942238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b18e7707-7ee6-4b3d-9796-675a1ad0538c · outbound

This paper cites How has X changed over the last five years?.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding How has X changed over the last five years?

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.927041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b538a815-d213-435b-84ec-e0949ce91b60 · outbound

This paper cites The question should be about the subject of the page, and the answer needs to be found in the page.

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.913564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6306bdc0-9729-4865-ac33-a4ced277e330 · outbound

This paper cites Generate a question that could be asked by a user without knowing the existence and the content of the corpus.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Generate a question that could be asked by a user without knowing the existence and the content of the corpus

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.901102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 264377b4-8d4b-4ea4-b12f-189f7c8d60d8 · outbound

This paper cites And the format of the answer should be a list of words answering the question.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding And the format of the answer should be a list of words answering the question

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.889450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9aa26f0b-a847-42a6-8f8a-d692e855d0f6 · outbound

This paper cites an unresolved cited work.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-05T22:10:09.077964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7603cd4e-66a0-410e-9040-c94df6f0891e · outbound

This paper cites What is the page number?.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding What is the page number?

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.876958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6911ac89-10ed-4726-a925-e34863514e1a · outbound

This paper cites detected_language.

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding detected_language

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T22:10:08.863023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation e0b5a8c2-a50f-4d35-8fd4-0f029e609d28 · inbound

MINER: Mining Multimodal Internal Representation for Efficient Retrieval cites this paper.

MINER: Mining Multimodal Internal Representation for Efficient Retrieval VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:06:10.643227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5dc0e3c7-5291-48ee-a3e6-dd165098b149 · inbound

DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents cites this paper.

DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:53:26.555944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 98c99682-c945-41b9-b38b-4462c8e29e6a · inbound

CMDR: Contextual Multimodal Document Retrieval cites this paper.

CMDR: Contextual Multimodal Document Retrieval VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T20:35:34.395414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.