Paper Citation Record · LEDGER

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning

As of 17 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2608.03292.

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

pith.paper-citation-record.v1
2608.03292 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T21:35:43.303783Z

measured 15 of 15 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

15 of 15 outbound references displayed

verified exact0
verified fuzzy6
unresolved9
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0f661bfb-1bc2-4751-84fb-d6d2dcbd2e5c · outbound

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

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.455005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc2da89-720e-4ab2-8e3d-7f44e3e0afee · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.658606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dc58ab6-8dfb-495b-ae39-9dc28f3555c1 · outbound

This paper cites GPT-4o System Card.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning GPT-4o System Card

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.732881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69705777-c023-4fdb-a3b2-528342be616e · outbound

This paper cites In Findings of the Association for Computational Linguistics: ACL 2026, 29770–29783.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning In Findings of the Association for Computational Linguistics: ACL 2026, 29770–29783

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:35:44.676624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b8ad16d1-e425-496d-a611-4f7fe0c239ee · outbound

This paper cites Shi,Y.;Wang,J.;Shan,Z.;Peng,D.;Lin,Z.;andJin,L.2026.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning Shi,Y.;Wang,J.;Shan,Z.;Peng,D.;Lin,Z.;andJin,L.2026

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:35:44.528195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d0afa4b7-1cab-45ea-af69-f8620d555f6c · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.986861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c836335e-ec62-4bf7-838b-c02047eb0f98 · outbound

This paper cites an unresolved cited work.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-05T21:35:44.354662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4ed5549a-4688-4384-b84a-a572ce0890d6 · outbound

This paper cites InProceedings of the 2025 ConferenceonEmpiricalMethodsinNaturalLanguagePro- cessing, 14035–14056.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning InProceedings of the 2025 ConferenceonEmpiricalMethodsinNaturalLanguagePro- cessing, 14035–14056

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:35:44.041980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6ce16c42-f01e-468a-95ff-67aba4594b8b · outbound

This paper cites InInternational Conference on Learning Rep- resentations, volume 2025, 21074–21098.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning InInternational Conference on Learning Rep- resentations, volume 2025, 21074–21098

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:35:43.693140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ebb17e81-2bf9-4634-b55e-f96bcc4c0553 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:43.247202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 477c20e4-4898-4398-95ee-4cd431da8873 · outbound

This paper cites It improves ac- curacyfrom38.5to52.9(+14.4points),whilereducingend- to-end latency by2.1×(15.04s to 7.33s) and prefill tokens by2.3×(35.5K to 15.5K).

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning It improves ac- curacyfrom38.5to52.9(+14.4points),whilereducingend- to-end latency by2.1×(15.04s to 7.33s) and prefill tokens by2.3×(35.5K to 15.5K)

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:35:43.430682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 10ebd9c2-7433-4c55-9a4f-07f730707b2f · outbound

This paper cites Docopilot:Improving multimodal models for document-level understanding.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning Docopilot:Improving multimodal models for document-level understanding

Reference 1159

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T21:35:44.900322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5f465230-3e31-45fe-8448-61d0071e730e · outbound

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

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.381998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff71e82-4df2-4386-a6d8-c565e1718cb6 · outbound

This paper cites Qwen3-VL Technical Report.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning Qwen3-VL Technical Report

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.296444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de7e8b79-77f4-4906-bf21-732ffa98e30c · outbound

This paper cites PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing.

DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-05T21:35:42.513063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.