> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sint.gg/llms.txt
> Use this file to discover all available pages before exploring further.

# Whitepaper

> SINT Protocol v0.2 — formal specification, threat model, evaluation framework, compliance mappings.

<Note>
  **This is the canonical whitepaper as of April 2026.** The full academic version is maintained in the repo at [github.com/sint-ai/sint-protocol/blob/main/WHITEPAPER.md](https://github.com/sint-ai/sint-protocol/blob/main/WHITEPAPER.md). The arXiv preprint is under submission (cs.CR primary, cs.RO / cs.AI / cs.MA cross-list). The March 2025 "SINT Agentic Platform" whitepaper is archived at [/archive/2025-whitepaper](/archive/2025-whitepaper).
</Note>

<CardGroup cols={2}>
  <Card title="Read in GitHub" icon="github" href="https://github.com/sint-ai/sint-protocol/blob/main/WHITEPAPER.md">
    The canonical Markdown version with full bibliography and citation metadata.
  </Card>

  <Card title="arXiv preprint" icon="file-pdf" href="https://arxiv.org/">
    Academic version with LaTeX typesetting. Under submission as of April 2026.
  </Card>
</CardGroup>

## Abstract

Foundation-model AI agents now perceive, reason, and physically actuate. Coinbase's Agentic Wallets (February 2026) gave them money; ERC-8004 gave them portable on-chain identity; OWASP's Top 10 for Agentic Applications (December 2025) catalogued how they fail; the EU AI Act's high-risk provisions take effect August 2, 2026. None of these infrastructures addresses the full stack of a physical-AI agent — the combined cognition, identity, authorization, actuation, and audit surface that spans software and the physical world.

This paper presents **SINT (Secure Infrastructure for Non-human Transactions)**, a protocol that formalizes physical-AI agents as *governed entities* possessing typed identity, graduated capability rights, and an immutable civic record.

## Contributions

SINT contributes:

1. A formal `SintCapabilityToken` schema with a physical-constraints block, cryptographically bound to a W3C DID and a TEE attestation.
2. A twelve-state deterministic finite automaton governing the full agent authorization lifecycle, mapped to ROS 2 action primitives.
3. A four-tier human oversight model with a provable max-escalation function driven by human-presence, environmental, novelty, and composite-safety signals.
4. A STRIDE-extended threat model — STRIDE+B — whose seventh class formalizes *behavioral non-determinism* across foundation-model backends.
5. A seven-benchmark evaluation framework with per-tier latency budgets and a 157-test conformance suite.
6. Compliance mappings to IEC 62443, EU AI Act Article 13, and NIST AI RMF.

We situate SINT as the security substrate that ROSClaw's executive-layer contract C = ⟨A, O, V, L⟩ explicitly scopes out, complementary to SAGA's inter-agent trust layer, and grounded in the empirical pattern that identical commands issued across frontier model backends produce a 3.4× spread in prompt-level out-of-policy attempt rates.

## Core sections

<CardGroup cols={2}>
  <Card title="Formal specification" icon="book" href="/protocol/spec">
    The normative SintCapabilityToken schema, wire messages, and DFA state transitions.
  </Card>

  <Card title="Tier model" icon="layer-group" href="/protocol/tiers">
    T0–T3 with the max-escalation function and Δ factors.
  </Card>

  <Card title="CSML" icon="chart-line" href="/protocol/csml">
    The Composite Safety-Model-Ledger score, calibrated against ROSClaw data.
  </Card>

  <Card title="Threat model" icon="skull" href="/protocol/threat-model">
    STRIDE+B with worked attack chains for UniPwn and MCP goal hijack.
  </Card>

  <Card title="Invariants" icon="shield-check" href="/protocol/invariants">
    Safety, liveness, non-repudiation, tamper-evidence proofs.
  </Card>

  <Card title="Compliance" icon="clipboard-check" href="/protocol/compliance">
    IEC 62443 / EU AI Act / NIST AI RMF mappings.
  </Card>
</CardGroup>

## Download

<CardGroup cols={3}>
  <Card title="Markdown" icon="file-lines" href="https://github.com/sint-ai/sint-protocol/raw/main/WHITEPAPER.md">
    Raw source on GitHub.
  </Card>

  <Card title="PDF" icon="file-pdf" href="https://github.com/sint-ai/sint-protocol/releases">
    Released alongside each protocol version tag.
  </Card>

  <Card title="BibTeX" icon="quote-left" href="https://github.com/sint-ai/sint-protocol/blob/main/docs/CITATION.bib">
    For academic citation.
  </Card>
</CardGroup>

## Citing SINT

```bibtex theme={null}
@techreport{sint_protocol_2026,
  title        = {{SINT}: A Formal Security Protocol for Governed Physical-{AI} Agents},
  author       = {Pashkov, Illia and {SINT Labs}},
  institution  = {SINT Labs},
  year         = {2026},
  month        = {April},
  note         = {v0.2. Open specification (CC BY 4.0), reference implementation (Apache-2.0).},
  url          = {https://github.com/sint-ai/sint-protocol}
}
```

When the arXiv preprint is public, replace the citation with the arXiv BibTeX entry (same key). Watch the [facts page](/facts) for updates.

<Tip>
  **Implementing SINT from the paper?** Also read the [protocol spec](/protocol/spec) and the [conformance suite](/protocol/conformance). The spec is the normative artifact; the whitepaper is the explanatory one.
</Tip>