Bibliography
ABBYY. 2020. ABBYY Vantage. Product documentation.
https://www.abbyy.com/vantage/.
Adyen, and Hugging Face. 2025. “DABstep: Data Agent
Benchmark for Multi-Step Reasoning.” arXiv Preprint. https://arxiv.org/abs/2506.23719.
Agentic AI Institute. 2026. Agentic AI Enterprise Adoption 2026:
72. https://agenticaiinstitute.org/agentic-ai-enterprise-adoption-2026-governance-gap/.
AllenAI. 2025a. olmOCR-2: Open OCR with
Reproducible Benchmarking. GitHub / Hugging Face. https://github.com/allenai/olmocr.
AllenAI. 2025b. olmOCR-Bench: A Programmatic Benchmark for OCR
Systems. AllenAI / Hugging Face. https://github.com/allenai/olmocr.
Centers for Medicare and Medicaid Services. 2024. CMS
Interoperability and Prior Authorization Final Rule. https://www.cms.gov/.
Databricks. 2026. Why Frontier Agents Can’t Read Documents — and How
We’re Fixing It. Databricks Blog. https://www.databricks.com/blog/why-frontier-agents-cant-read-documents-and-how-were-fixing-it.
Google. 2005. Tesseract OCR — Open-Sourced by Google in 2005.
GitHub. https://github.com/tesseract-ocr/tesseract.
Huang, Yupan, Tengchao Lv, Lei Cui, et al.
2022. “LayoutLMv3: Pre-Training for Document
AI with Unified Text and Image Masking.” ACM
Multimedia. https://arxiv.org/abs/2204.08387.
Hugging Face. 2025. Supercharge Your OCR Pipelines with
Open Models. Hugging Face Blog. https://huggingface.co/blog/ocr-open-models.
Hyperscience. 2024. Hyperscience Document Automation Platform.
Product documentation. https://www.hyperscience.com/.
IBM. 2026. IBM Granite-Docling: End-to-End Document
Understanding. IBM Research. https://www.ibm.com/new/announcements/granite-docling-end-to-end-document-conversion.
Kim, Geewook, Teakgyu Hong, Moonbin Yim, et
al. 2022. “OCR-Free Document Understanding
Transformer.” European Conference on Computer Vision
(ECCV). https://arxiv.org/abs/2111.15664.
Landing AI. 2026. Agentic Document Extraction (ADE):
Pricing and Features. Landing AI Documentation. https://docs.landing.ai/ade/ade-pricing.
LlamaIndex, and Kaggle. 2026. ParseBench: A Document Parsing
Benchmark for AI Agents. LlamaIndex Blog. https://www.llamaindex.ai/blog/parsebench.
Microsoft. 2026. Transform and Enrich Data with AI
Functions in Microsoft Fabric. Microsoft Learn. https://learn.microsoft.com/en-us/fabric/data-science/ai-functions/overview.
Mistral AI. 2026. Introducing Mistral OCR 3.
Mistral AI. https://mistral.ai/news/mistral-ocr-3.
OpenAI. 2023. GPT-4V(ision) System Card. https://cdn.openai.com/papers/GPTV_System_Card.pdf.
OpenDataLab. 2025a. MonkeyOCR V1.5 Technical Report:
Unlocking Robust Document Parsing for Complex Patterns. arXiv
preprint. https://arxiv.org/abs/2511.10390.
OpenDataLab. 2025b. OmniDocBench: A Comprehensive
Benchmark for Document Parsing and Evaluation. CVPR 2025; updated
v1.7 April 2026. https://github.com/opendatalab/OmniDocBench.
PaddlePaddle. 2025. PaddleOCR-VL and
PP-StructureV3. GitHub. https://github.com/PaddlePaddle/PaddleOCR.
Reducto AI. 2025. Announcing RD-TableBench: An Open-Source Table
Benchmark. Reducto Blog. https://reducto.ai/blog/rd-tablebench.
Reducto AI. 2026. Reducto’s Hybrid Architecture: Technical Deep Dive
into Agentic OCR and Multi-Pass Document Parsing.
Reducto Blog. https://llms.reducto.ai/hybrid-architecture-agentic-ocr-deep-dive.
Seemore Data. 2026. The Hidden Cost of Snowflake Cortex
AI: A $5K Single-Query Wake-up Call.
Seemore Data Blog. https://seemoredata.io/blog/snowflake-cortex-ai/.
Snowflake. 2026. Parsing Documents with
AI_PARSE_DOCUMENT. Snowflake Documentation. https://docs.snowflake.com/en/user-guide/snowflake-cortex/parse-document.
Unstructured.io. 2026. Introducing SCORE-Bench: An Open
Document Parsing Benchmark. Unstructured.io Blog. https://unstructured.io/blog/introducing-score-bench-an-open-benchmark-for-document-parsing.
Various. 2024. OCR-Agent: Agentic OCR with
Capability and Memory Reflection. arXiv preprint. https://arxiv.org/abs/2602.21053.
Various. 2026. Tiny Silent Hallucinations in Agentic
AI: Hidden Failure Modes in Autonomous Systems.
OpenReview. https://openreview.net/forum?id=1KxDazvI6L.