Certified Artificial Superintelligence Arrival from Typed Audit Logs

Abstract

This preprint develops a process-neutral, proof-carrying framework for certifying artificial superintelligence arrival under incomplete, fallible, and operationally messy evidence. It treats ASI arrival as a layer-relative statement about sustained capability-producing trial generation, renewal, and viability across models, scaffolds, laboratories, organizations, markets, software ecosystems, regulators, evolutionary systems, and coalitions. The framework uses typed audit logs, compatible-history sets, certified random closed sets, bound certificates, decision semantics, coalition attribution, structural interventions, ledger viability, evaluator noninterference, robust task coverage, and asymmetric three-valued rules so missing or unreliable data widens uncertainty rather than counting as favorable evidence.

Keywords

• ASI
• intelligence explosion
• recursive self-improvement
• self-improving AI
• AI capability evaluation
• AI safety
• typed audit logs
• compatible histories
• proof kernel
• causal attribution
• identifiable coalitions
• interventional semantics
• policy intervention
• ledger viability
• autonomous AI
• agentic AI
• uncertainty quantification

Identifiers and source records

• DOI
• Works entry
• ORCID