On the Foundations of Trustworthy Artificial Intelligence

2026-03-25

AI Summary

This work addresses the fundamental challenge that cross-platform nondeterminism undermines the reliability of AI system verification, thereby eroding the foundation of trustworthy AI. We propose the “Determinism Thesis,” asserting that deterministic inference is both necessary and sufficient for achieving key trustworthiness properties—including fairness, robustness, privacy, security, and alignment. To realize this, we develop a pure integer inference engine that eliminates nondeterminism inherent in IEEE 754 floating-point arithmetic and introduce “trust entropy” to quantify the cost of nondeterminism. Implemented in Rust, our system integrates hash-consistency validation with on-chain blockchain proofs. Across 82 cross-architecture (ARM/x86) tests—using models up to 6.7B parameters—it achieves zero hash mismatches, perfect output consistency across four geographically distributed nodes, and successful verification via 356 on-chain transactions.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Security and Privacy: Data transparency and provenance

Abstract

We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this as the Determinism Thesis and introduce trust entropy to quantify the cost of non-determinism, proving that verification failure probability equals 1 - 2^{-H_T} exactly. We prove a Determinism-Verification Collapse: verification under determinism requires O(1) hash comparison; without it, the verifier faces an intractable membership problem. IEEE 754 floating-point arithmetic fundamentally violates the determinism requirement. We resolve this by constructing a pure integer inference engine that achieves bitwise identical output across ARM and x86. In 82 cross-architecture tests on models up to 6.7B parameters, we observe zero hash mismatches. Four geographically distributed nodes produce identical outputs, verified by 356 on-chain attestation transactions. Every major trust property of AI systems (fairness, robustness, privacy, safety, alignment) presupposes platform determinism. Our system, 99,000 lines of Rust deployed across three continents, establishes that AI trust is a question of arithmetic.

Problem

• trustworthy AI
• platform determinism
• non-determinism
• verification
• floating-point arithmetic

Innovation

• platform-deterministic inference
• Determinism Thesis
• trust entropy
• bitwise identical output
• integer inference engine