Pith. sign in

Paper Citation Record · LEDGER

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings

As of 12 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 1 inbound Pith citation observation for arXiv:2605.07492.

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

pith.paper-citation-record.v1
2605.07492 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-11T02:28:02.152600Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T04:40:01.433462Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

  • verified exact28
  • verified fuzzy13
  • unresolved0
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ef138282-9d3d-4826-99d7-63aba473cd6d · outbound

This paper cites Document AI: Benchmarks, Models and Applications.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Document AI: Benchmarks, Models and Applications

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.204784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:c47c528a260a9722146941187df4b4aea7407992d27140a44d490780866e65dc

Observation e2db76e9-ed48-406d-9ef5-6d05b5d0c375 · outbound

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

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

Reference 2

Resolution
verified exact
local_arxiv, observed 2026-05-11T03:30:56.226423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:9db4c646a675d650d7f94abb0003c318567e1cd587e6f3fd3e1b8c8d4fc5ca8d

Observation a6335059-2af4-4aef-af6e-32ab659e51cf · outbound

This paper cites Glm-ocr technical report.arXiv preprint arXiv:2603.10910.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Glm-ocr technical report.arXiv preprint arXiv:2603.10910

Reference 3

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.186347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:8bcb8bdab97a2ab98d61d508074d168ae0dec329b38765bc6a6655d943ba951b

Observation 7c18a55d-5e74-4ea7-acbf-fe93182b4c01 · outbound

This paper cites MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-17T13:25:32.206292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:dfbecbdf54c6a77aa145527475b22de8a10343d987cb9491e495e521758b1c88

Observation ca9b7c25-ef23-4b86-ae27-2a74cb67be16 · outbound

This paper cites MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale

Reference 5

Resolution
verified exact
local_arxiv, observed 2026-05-11T03:30:56.318662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:8ab6b22cfc9d7b132f21611fc912cd305c896471fc7094df239df5545c546463

Observation 4efac8ca-ad56-4842-a6d7-b3b0d63fd52b · outbound

This paper cites Dolphin-v2: Universal document parsing via scalable anchor prompting.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Dolphin-v2: Universal document parsing via scalable anchor prompting

Reference 6

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.198693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:c91f3cd1668f1d362d9bb0a6a987b0977851f6786115e862358be196ea613a64

Observation 9f7ed9e7-6b36-4aec-b1cd-18c835765f6d · outbound

This paper cites Firered-ocr technical report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Firered-ocr technical report

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.365081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:e24961f1e198d9d886a4648ac8fb3bee6ad86ce3f1dd9f06b181f7bdacee453c

Observation 30b73253-bc3c-4ca2-bfc4-6401446a8652 · outbound

This paper cites Hunyuanocr technical report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Hunyuanocr technical report

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.289559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:86441a4d28cfd313a62d8441bc5b7085e3a27667091b6f040a0585f95875d0a6

Observation a6b44266-5eaf-4fd6-93d6-8362c8afdf3d · outbound

This paper cites DeepSeek-OCR: Contexts Optical Compression.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings DeepSeek-OCR: Contexts Optical Compression

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-05-12T04:35:50.904687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:6958d4ace3d1aa76c659453eebf4d3fe96ea96158789a902cb00ef745b6cdc90

Observation f81da1d8-4356-4960-96fd-c354b4272d2f · outbound

This paper cites Deepseek-ocr 2: Visual causal flow.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Deepseek-ocr 2: Visual causal flow

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.149544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:f411d03e2c3a14dc9abf8cf895da0c30281231ce296bb6af71a171f9d2f31e06

Observation 5e168126-d970-4529-8df7-35e33f8607b0 · outbound

This paper cites Qwen3-VL Technical Report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Qwen3-VL Technical Report

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-05-11T03:30:56.219664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:b4394da5ae55e33417ecf19ea1580296dac2279fbc9acb4a6bbf9350440417bb

Observation a25ac0d8-fbff-4aa2-aab1-e1e07399c5c4 · outbound

This paper cites Gemini 3.1 Pro: A smarter model for your most complex tasks.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Gemini 3.1 Pro: A smarter model for your most complex tasks

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.359883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:9cb23915f51fd0bb20984015d5c795f30555b0e0226aec4250ca8f5fd6b4b2f0

Observation a1e6547e-4df3-421e-9f5c-95b5e4d2a193 · outbound

This paper cites OmniDocBench: Benchmarking diverse PDF document parsing with comprehensive annotations.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings OmniDocBench: Benchmarking diverse PDF document parsing with comprehensive annotations

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.351589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:89c3dbc2662bc96765da2db23367f7b47c1f5881797c5b2e06f866cb1aa26014

Observation 62e03f24-5ff4-414e-9b5f-9b6598109f95 · outbound

This paper cites Docptbench: Benchmarking end-to-end photographed document parsing and translation.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Docptbench: Benchmarking end-to-end photographed document parsing and translation

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.260483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:523195e7d146b7ad003d31c1f98d85e982b22039bf0fc80730c540cd65c30772

Observation d64133a3-f5d7-4466-83b5-010346d52656 · outbound

This paper cites Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-06-23T03:13:55.135132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:f250f7545dc52a74790d23c76f936d442ad0316115600ffb8122c721829fcf0e

Observation 4c8d8ec5-d949-4ec2-b7a7-69ab781cc1df · outbound

This paper cites Mdpbench: A benchmark for multilingual document parsing in real-world scenarios.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Mdpbench: A benchmark for multilingual document parsing in real-world scenarios

Reference 16

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.246602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:814341bea4455e17b9d5339901174beff2f8f07d6e4f02228b1a1269a9f6bd4f

Observation 1d3e5138-2a74-4901-b3bb-6cfb06f0d6d2 · outbound

This paper cites OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning

Reference 17

Resolution
verified exact
arxiv_id, observed 2026-05-17T20:33:27.157097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:c9f185395c75d7165f86341a53d817d66eb5367b9073afbc3c7bab83ffa84dce

Observation 2911bc02-2b10-4420-a423-aa429d52e968 · outbound

This paper cites olmOCR 2: Unit test rewards for document OCR.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings olmOCR 2: Unit test rewards for document OCR

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.267616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:6ad1cfc6fc7ecc8613d4476f5f505d34a0edbf0505b821709165935ca196e988

Observation fc0c7e8e-792c-48d2-89b5-6b30abd8a336 · outbound

This paper cites OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-27T02:04:28.324233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:aaaaec403c60c48cb0481cb40630a64fde0f1a5ea503ed884295fd50fe20af69

Observation 8624d1ea-f155-4946-bfdf-ce2d252bb684 · outbound

This paper cites Intelligent document processing market size, share & industry analysis.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Intelligent document processing market size, share & industry analysis

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.376310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:22d919716e5dd9db8dbad328f7a00818bc1861801ac28db895666e397bae20a1

Observation 5fea1e6e-42d6-455d-ba9d-7501d45a240e · outbound

This paper cites Intelligent document processing market size report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Intelligent document processing market size report

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.364732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:b8ccdbaaa001bfda71e169feb527e6c677a707c120c5a238d61728db3ec99004

Observation ef55da91-da01-4a83-9ff6-b294195dea43 · outbound

This paper cites Available at https://www.grandviewresearch.com/industry-analysis/ intelligent-document-processing-market-report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Available at https://www.grandviewresearch.com/industry-analysis/ intelligent-document-processing-market-report

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.355305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:937b767239da4fec4c4d74b1571b1b29f359d1a00b33f52dd07dc2f5032ecc3f

Observation 24c47a1e-28f3-4673-bd76-1ac280afba45 · outbound

This paper cites Logics-Parsing-Omni Technical Report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Logics-Parsing-Omni Technical Report

Reference 23

Resolution
verified exact
local_arxiv, observed 2026-05-11T03:30:56.330792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:e1ef4c5a08e7db17eb81486a191c55cb707b23d1638954fd53c1d5af2362670f

Observation 3c9cfd12-d530-4c9f-b9fc-a75a5f4d6faf · outbound

This paper cites Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.347542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:a06f58bb1fe7ac9fb8df19d052fba93026e41692d9e00972c15da93b30523d72

Observation c6dad526-19c6-4bd5-9472-772854bba3e1 · outbound

This paper cites Image-based table recognition: Data, model, and evaluation.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Image-based table recognition: Data, model, and evaluation

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.372335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:5917c54a3c88f41c25ceb4b3b2ee26edfb23f4b9cc8246d6a72673349c0fdacc

Observation feeb462d-2c4a-4c40-9395-32ac363fd760 · outbound

This paper cites Multimodal ocr: Parse anything from documents.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Multimodal ocr: Parse anything from documents

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.211632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:965c5c975a1649ebc794816dc8f762effd5a336dd82f59c32c46c8ab903b214b

Observation 41bd8e22-a238-4374-8e7f-cd171a3283e7 · outbound

This paper cites arXiv preprint arXiv:2506.05218 , year=.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings arXiv preprint arXiv:2506.05218 , year=

Reference 27

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.133284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:06f8490359aea2f4e4ab86b2c555174b45781903fda5bdb23cddff997b56202e

Observation 14021d59-1781-42f0-a013-106d9dd5b04b · outbound

This paper cites Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-07-14T03:21:27.323268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:3250a5b3a179890c92518a86d6f1552df0354403d5abdfac05d06eed7cb2d8f3

Observation 5e6f4550-87b4-4631-a790-4043543cef4d · outbound

This paper cites OpenOCR: An open-source toolkit for general-OCR research and applications.https://github.com/Topdu/OpenOCR.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings OpenOCR: An open-source toolkit for general-OCR research and applications.https://github.com/Topdu/OpenOCR

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.348110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:01afa33292d3166272590847c26f80766bd6702e4b3fa5127bcc00f1dd10471d

Observation 318aef4e-1967-4c54-b4b3-1c21808eca04 · outbound

This paper cites olmocr: Unlocking trillions of tokens in pdfs with vi- sion language models.arXiv preprint arXiv:2502.18443, 2025a.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings olmocr: Unlocking trillions of tokens in pdfs with vi- sion language models.arXiv preprint arXiv:2502.18443, 2025a

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.194257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:02b5eb341ca5f619c92786c15a1a41dbbd632e5fe1697131d1e91c1f8a5cb737

Observation 6c016336-bcbb-48f8-bd59-02cac041ec40 · outbound

This paper cites Reading or reasoning? format decoupled reinforcement learning for document OCR.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Reading or reasoning? format decoupled reinforcement learning for document OCR

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.359415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:1f408fcc1bd9677f0f984bfbe405192bc55f86d8395490a0f04264807fd11f75

Observation 00f04f2a-7e52-4a1a-8b2c-71ab4ec42ab8 · outbound

This paper cites Logics-Parsing-v2.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Logics-Parsing-v2

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.368414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:0dd6c6cdf5fa5819c4a9b8e2eee9cd022df7255b3df7f36d5df19284f0a0abf6

Observation 9d962b7f-3615-40ec-bc5c-863443dabd5e · outbound

This paper cites Ocrverse: Towards holistic ocr in end-to-end vision-language models.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Ocrverse: Towards holistic ocr in end-to-end vision-language models

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.308055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:a58ecd7479e9d8c62f89eb4a5a56330c61bd18faa3333dde2ac81699eb2c35ac

Observation 6fd7350e-5bb2-471d-b504-2d926db6bc63 · outbound

This paper cites Qianfan-ocr: A unified end-to-end model for document intelligence.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Qianfan-ocr: A unified end-to-end model for document intelligence

Reference 34

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.251996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:e140d5fc5b3457283e9c18df6a0fec4fec8e880b7d279d6c8d3beee38d2519d0

Observation ddf9e310-2b83-404e-8a26-4861dd021403 · outbound

This paper cites Nanonets-OCR2: A model for transforming documents into structured markdown with in- telligent content recognition and semantic tagging.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Nanonets-OCR2: A model for transforming documents into structured markdown with in- telligent content recognition and semantic tagging

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.384016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:1a3abc36e9085caab46af19e849456868842775394cfde462d9ce29cd3a9bb15

Observation e63484da-aff1-48dd-9816-a6589f70861a · outbound

This paper cites OCRFlux-3B.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings OCRFlux-3B

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.380264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:66c49be8436176dbcbf62c92718e8da9113ad1201621a4f7ec6208fe0fd7a8b5

Observation eed8e37b-7086-44cb-a30b-fed136d5500e · outbound

This paper cites InICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings InICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5

Reference 37

Resolution
metadata mismatch
arxiv_id, observed 2026-05-11T03:30:56.231839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:b401e2738aa66ae6fa9ef38f5c691381855a79b55b172912987f51203986742b

Observation 9f7ff89d-acc1-4b56-9e1b-86e449ca2ce4 · outbound

This paper cites UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters

Reference 38

Resolution
verified exact
arxiv_id, observed 2026-07-14T02:19:24.298662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:cd5fb2fe38c7d2404392d7a668bc2e6b2bc18a7401a8d63066df3b6e791af37e

Observation 358bf655-c781-436c-a59c-b4f6c6de554b · outbound

This paper cites OpenDoc-0.1B: An ultra-lightweight document parsing system.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings OpenDoc-0.1B: An ultra-lightweight document parsing system

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.340341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:3c7c095cd19035badcea3e1ae15cfc2831b7740efd65f7e4cab60f2ecec56278

Observation 011f0929-0c2e-4ee3-b846-12ffd194f6f0 · outbound

This paper cites Qwen3.5: Towards native multimodal agents.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Qwen3.5: Towards native multimodal agents

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.336618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:47f626f2988662fe0bb9faa8e45e4da487072222bf38fbb254e55b345641aa44

Observation 3589de6a-18c5-4e68-a810-0cf0e02b69d6 · outbound

This paper cites Kimi K2.6.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Kimi K2.6

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-05-14T12:35:15.343982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:b75ead5b86252227a6fd50cb5d366a49dcb8fb4d5b2d74754cb37730e009d762

Observation fb3cb0b8-2f8b-4917-8408-94555c27614b · outbound

This paper cites Step3-vl-10b technical report.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings Step3-vl-10b technical report

Reference 42

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:30:56.239823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:eca662704100813526135d1c0849fd4647a4b39a0bd14186288c430d14cf4874

Observation f2975afc-c8b6-421d-8aff-321d413f206e · outbound

This paper cites MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe.

How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Reference 43

Resolution
malformed identifier
arxiv_id, observed 2026-05-15T17:07:27.685083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-11T02:28:02.152600Z digest=sha256:cd287c619c29ce84bdad375bc0048b1f4cdd0d2f7912db2ef02e8e50f6e808b5

Pith citing papers

Observation 342ac919-ed8a-48c5-8684-8183f6ef5aff · inbound

OvisOCR2 Technical Report cites this paper.

OvisOCR2 Technical Report How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T04:40:01.433462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T04:40:01.433462Z digest=sha256:d5dbb2fa248a523e786704ac0e60b33e86aed208db0a8719a7ac886f2b147089