Tables
Preserve spanning headers, merged cells, footnotes, and captions as real table structure.
AlphaAccuracy-first scientific parsingAccuracy-first parsing for complex scientific PDFs
Scientific document parsing
State-of-the-art parsing for scientific documents.
Turn complex scientific PDFs into structured data without losing the tables, equations, figures, and reading order that carry their meaning.
Original scientific PDF
Reconstructed document logic
Source-linked structured data
Parses the documents science runs on
- Journal articles
- Preprints
- Conference proceedings
- Patents
- Clinical protocols
- Monographs
- Technical reports
- Theses
- Systematic reviews
- Grant proposals
01 / 04Accuracy
Scientific documents are different
A paper is more than the text on its pages. Its meaning lives in structure, notation, and relationships.
Equations
Keep notation, indices, equation boundaries, and numbering intact from page to output.
Reading order
Reconstruct the intended sequence across columns, floating elements, and page boundaries.
Figures & captions
Keep figures, captions, labels, and surrounding discussion connected throughout the paper.
Parser
Reconstruct the complete paper instead of flattening one page at a time.
Source pagep.12
Sections
Tables
Equations
Figures + captions
Every page, assembled into one document
Capabilities
Layout-first analysis
Geometry and element ownership are understood before anything is flattened.
Whole-document assembly
A single representation across every page, not pages parsed in isolation.
Optimization
Accuracy over volume
Tuned for the hardest pages
Coverage
Whole document
Every page, one paper
Representation
Connected structure
Nothing flattened, nothing detached
02 / 04System
How it works
Built for the layouts that break general-purpose parsers.
Complementary models read every page, automated reasoning checks the assembly, and everything is delivered as one coherent model of the paper.
03 / 04Difference
Accuracy, not just throughput
Built for fidelity before volume.
General-purpose parsers are often optimized to make large collections searchable quickly. Amanuensis is built for workflows where a misplaced equation or malformed table changes the data itself.
One model from first page to last
Scientific elements remain first-class structure
Accuracy is prioritized before latency and volume
Primary optimization
- General-purpose parser
- Fast, broad document ingestion
- Amanuensis
- Maximum scientific fidelity
Document model
- General-purpose parser
- Pages, text blocks, and generic markdown
- Amanuensis
- One connected model of each paper
Tables & equations
- General-purpose parser
- Often flattened, simplified, or detached
- Amanuensis
- Preserved as structured scientific elements
Reading order
- General-purpose parser
- Inferred locally from individual pages
- Amanuensis
- Reconstructed across columns and pages
Downstream result
- General-purpose parser
- Extracted text that still needs repair
- Amanuensis
- Structured document data ready for pipelines
| Decision point | General-purpose parser | Amanuensis |
|---|---|---|
| Primary optimization | Fast, broad document ingestion | Maximum scientific fidelity |
| Document model | Pages, text blocks, and generic markdown | One connected model of each paper |
| Tables & equations | Often flattened, simplified, or detached | Preserved as structured scientific elements |
| Reading order | Inferred locally from individual pages | Reconstructed across columns and pages |
| Downstream result | Extracted text that still needs repair | Structured document data ready for pipelines |
04 / 04Use cases
Scientific content infrastructure
One parser for the scientific document lifecycle.
From publishing and repositories to life-science research, Amanuensis turns difficult papers into dependable structured inputs for the systems built on top of them.
Publishers
Turn submissions and backfiles into high-fidelity inputs for production, enrichment, and discovery.
Repositories
Make heterogeneous collections machine-readable without flattening the structure of each paper.
Life-science R&D
Transform literature and scientific reports into dependable data for search, knowledge systems, and analysis.
What it enables
Scientific-document intelligence starts with trustworthy parsing.
Once papers are structured correctly, teams can build search, extraction, indexing, summarization, and authoring workflows on top of them.
Search and discovery
Extraction and enrichment
Indexing at scale
Summarization and authoring
Request a pilot
Test Amanuensis on the papers other parsers struggle with.
Bring representative PDFs and the structure your systems need. We will define the evaluation together and report accuracy element by element.