Question
Where does authority live?
Research lineConstitutional AI & verifiable trust
FOUNDATIONLegitimacy, public authority, non-unilateral amendment and constraints that bind machine action.
SPQR Research
Here is the thesis.
Here is the evidence.
Here is how to test it.
Our research asks what must be true before autonomous systems can act under policy, produce defensible evidence and improve without escaping governance.
SPQR / RESEARCH OPERATING SYSTEMPUBLIC
S
PROOFSNOT PROMISES
01AuthorityWho is permitted to decide?
02Policy stateWhich reviewed rule is active?
03Action boundaryCan control intervene before effect?
04EvidenceWhat proves the chain held?
PAPERS → ARCHITECTURE → PRODUCTS → PROOFCHALLENGE WELCOME
The research position
We publish the architecture because “trust us” is not a governance model.
Authority, evidence and execution conditions should be separable from the model generating the proposal, then inspectable by people who did not build the system.
Model proposes · authority verifies · runtime enforces · evidence remainsFour research lines. One operational question.
What has to be true before an autonomous system is allowed to cause an effect?
The corpus moves from jurisprudential questions to concrete system boundaries. Each line asks a different part of the same governance problem.
Question
How does policy become executable?
Research lineCryptographic policy enforcement
PRAXISSigned policy state, provenance, active authority and deterministic governance artefacts.
Question
Can governance intervene before effect?
Research lineRuntime action-boundary control
AEGISTrusted provenance, mapped operations, fail-closed execution and per-action verdicts.
Question
How can systems improve without self-authorising?
Research lineGoverned candidate improvement
NEXTAuditable proposals, challenge evidence, containment and held-out evaluation rather than invisible self-modification.
Start with a measured claim
What the runtime evaluation actually reports.
Prompt-policy comparator
79
Risky proposal-leakage rows.
Reported in the prompt-policy comparator path. This is a proposal endpoint, not an executed-side-effect measure.
Governed sandbox path
0 / 2,100
Risky side-effect completions.
Zero observed in the evaluated governed rows. The same path also recorded zero governed mock-tool applications.
Attempted governed decisions
1,832 / 1,832
Trusted provenance retained.
All attempted governed decisions preserved runtime-resolved provenance in this evaluation.
The result is bounded. The next test counts useful work.
6,300 total rows across 42 tasks, five run families, three conditions and ten repeats per family. Different endpoints must not be presented as a percentage reduction. These results do not establish useful allowed-task completion, universal AI safety or production bypass resistance.
Read the methods and limitations · Review the next evaluation protocol
Start here
Three papers that explain the operating thesis.
These works are the shortest path into the architecture: the runtime boundary, the proof model and the governed-improvement problem.
Bounded claims
A controlled result is evidence about the controlled result. Nothing more.
Serious governance research should expose its boundaries rather than smuggling confidence through tone.
NOT A CLAIM OFUniversal AI safety
NOT A CLAIM OFAutomatic legal compliance
NOT A CLAIM OFInfallible classification
THE CLAIM ISThe stated process, authority and evidence can be inspected.
Public research library
Read the corpus. Follow the argument.
Preprints, working papers and whitepapers are labelled by their public source. Use the filters to move through the research lines.
9 public works shown
Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution
A trusted runtime seam between agent proposals and tool effects.
Proofs, Not Promises: Governed Candidate Improvement for Agent Control Runtimes
An auditable candidate lifecycle instead of invisible self-modification.
Cryptographic Runtime Governance for Autonomous AI Systems: The Aegis Architecture for Verifiable Policy Enforcement
Signed policy state and auditable governance artefacts at the execution boundary.
SPQR Whitepaper: A Constitutional Framework for Sovereign AI Governance
The broader constitutional-governance thesis and supporting SPQR architecture.
Lex Aegis: The Living Law ; A Public Blueprint for Constitutional AI Governance
Public participation, action in the absence of authority and plural governance.
Lex Fiducia: Constitutional AI and the Architecture of Verifiable Trust
Verifiable policy state and non-unilateral amendment as a basis for trust.
Lex Digitalis ; The System Finds Itself in Contempt: Immutable Ethics for Autonomous AI
Cryptographically enforced machine constraints as operational legal instruments.
Lex Incipit: A Constitutional Doctrine for Immutable Ethics in Autonomous AI
Binding, verifiable constraints established at system genesis.
Lex Aeterna Machina: Autonomous Ethical Governance in the Age of Artificial Intelligence
Non-discretionary responsibilities before broader operational freedom.
No papers match that search and filter.
From paper to product
The papers are not the product. The products are where the thesis is forced to work.
Praxis and Aegis turn the research questions into concrete assurance and control surfaces.
PRAXIS
Evidence-bound policy assurance.
Test what organisational evidence supports, preserve ambiguity and remediation decisions, and establish approved authority.
Explore Praxis →
AEGIS
Runtime authority before effect.
Verify signed active policy state at the action boundary and preserve a per-action decision receipt.
Explore Aegis →One clear next step
Keep your safeguards.
Bring a testable objection.
Review the proposed protocol before any access is granted. Useful work, false denials, bypass routes and operating cost all belong in the result.
One workflow. Defined scope. A decision about fit.