ProductsXberg PlatformOpen SourceXbergCrawlComing soon
PricingUse CasesBenchmarksDocs
Theme
StarApply for partnership
Back to gallery
On the roadmap

Parse Citations & Footnotes

Pull references and footnotes out as structured data, and tie excerpts back to the claims they support.

Enrich
illustrative examplepreview
research page
Transformers improved results[1] across many tasks[2].
[1] Vaswani et al., 2017
[2] Devlin et al., 2019
{
"citations": 9,
"footnotes": 4
}

Illustrative example. This capability is on our roadmap and is not wired to a live demo yet — request early access.

What it is

Parsing of citations and footnotes into structured data, with claims tied back to their sources — for academic, legal, and research documents, and for grounded, citeable AI.

Why it matters

References and footnotes are where credibility lives. Pulled out as structured data, they let you verify claims and build systems that can cite their sources.

What Xberg does

Xberg parses citations and footnotes into structured references and links excerpts back to the claims they support.

  • References and footnotes as structured data.
  • Claim-to-source linking.
  • Built for academic, legal, and research material.
  • Underpins grounded, citeable AI.
On the roadmap. Citation and footnote parsing exists in the engine but isn't exposed through the public API yet, so the example here is illustrative. Talk to us about early access.

More use cases

document
{
"title": "…",
"sections": 3,
"blocks": 24
}

RAG Pipeline Ingestion

Turn a pile of PDFs, Office docs, and HTML into clean, chunked, embedded data for your vector database — in one call.

ExtractEmbed & Retrieve
RAGChunkingEmbeddings
parser.py
def extract(doc):
return parse(doc)
class Reader:
# 306 formats
{
"functions": 12,
"classes": 3
}

Document-Reading Agents

Give your AI agents one tool to read any document — 100+ formats, structured output, every framework.

ExtractEnrich
AgentsStructured JSONLayout
INVOICE#INV-0042
Acme Supply Co.
Brackets ×40$1,200.00
Fasteners$1,280.00
Total due$2,480.00
{
"tables": 1,
"rows": 8,
"columns": 4
}

Replace Legacy IDP

Swap brittle, template-based processing for one API that returns schema-mapped JSON — no templates to maintain.

ExtractEnrich
IDPTablesOCRStructured JSON

Open-source primitives, composed into one backend. Curated cohort of design partners. Apply to work with us.

Apply for partnershipGet the libraries
Cookies

We value your privacy

Xberg uses cookies to improve your experience, personalize content, and analyze traffic. You can manage your preferences at any time.