MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-03-31
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 67
Source count: 4
Coverage: 83%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios | Route /signal-canvas/mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios",
    "query_text": "Summarize MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios",
  "normalized_query": "2603.28130",
  "route": "/signal-canvas/mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios",
  "paper_ref": "mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: 67

Proof: Verification pending

Freshness state: computing

Source paper: MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

PDF: https://arxiv.org/pdf/2603.28130v1

Repository: https://github.com/Yuliang-Liu/MultimodalOCR

Source count: 4

Coverage: 83%

Last proof check: 2026-03-31T20:30:24.948Z

Signal Canvas receipt window

Ready for execution: MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

/buildability/mdpbench-a-benchmark-for-multilingual-document-parsing-in-real-world-scenarios

Build Nowready

Subject: MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

Verdict

Build Now

Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.

Preparing verified analysis

GitHub Code Pulse

Trending

Stars

847

Health

Last commit

6/8/2026

Forks

Open repository

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
MDPBench comprises 3,400 document images spanning 17 languages, diverse scripts, and varied photographic conditions...
Implicationpartial
Specific numeric details are provided in the abstract and a data table.
Verificationpartial
partial
Evidencepartial
We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing.
Implicationpartial
Explicitly stated in the abstract and title as a primary contribution.
Verificationpartial
partial
Evidencepartial
However, these benchmarks predominantly focus on digital-born and scanned documents in limited languages. This limitation leads existing document parsing models to exhibit a certain bias toward inputs from standardized, high-resource languages...
Implicationpartial
Directly stated in the analysis section, supported by a comparison table of benchmarks.
Verificationpartial
partial
Evidencepartial
...open-source alternatives suffer dramatic performance collapse, particularly on non-Latin scripts and real-world photographed documents, with an average drop of 17.8% on photographed documents and 14.0% on non-Latin scripts.
Implicationpartial
Specific performance drop percentages are stated in the abstract, and the result is highlighted as a key finding.
Verificationpartial
partial
Evidencepartial
Our comprehensive evaluation of both open-source and closed-source models uncovers a striking finding: while closed-source models (notably Gemini3-Pro) prove relatively robust, open-source alternatives suffer dramatic performance collapse...
Implicationpartial
Directly stated in the abstract and supported by a results table showing performance metrics.
Verificationpartial
partial
Evidencepartial
...with high-quality annotations produced through a rigorous pipeline of expert model labeling, manual correction, and human verification.
Implicationpartial
Explicitly described in the abstract and detailed in a pipeline diagram.
Verificationpartial
partial
Evidencepartial
...captured them under diverse environments and conditions, including indoor and outdoor scenes, physical deformation, image degradation, varying camera orientations, and background variation.
Implicationpartial
Specific conditions are listed in the methodology description.
Verificationpartial
partial
Evidencepartial
We further analyze the key limitations of current document parsing models, including challenges with photographed documents, limited recognition of non-Latin scripts, language-specific reading order issues...
Implicationpartial
Summarized as findings from the evaluation, though specific evidence for each sub-point is spread throughout the analysis.
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface