The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems

Dongxin Guo

arXiv:2605.23024 · 2026-05-25 공개 · arXiv · PDF

information-theory residual-stream transformer-architectures no-free-lunch capacity-invariant circuit-complexity modular-exponentiation zero-knowledge-verification

Abstract

Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Free Lunch theorems, shape what computation can do. This thesis turns such impossibility results from curiosities into design rules. Its flagship result proves an accuracy ceiling set by architecture alone: past a critical reasoning depth, no amount of training moves it, at any adapter rank, sample size, or loss function. Computable before deployment from layer count and embedding width, this Deterministic Horizon is measured between nineteen and thirty-one across twelve transformer architectures, and fine-tuning on optimal-length traces recovers under four percentage points. The mechanism is a capacity invariant of the residual stream, and an information-theoretic conversion yields super-exponential accuracy decay past the horizon. An unconditional circuit-complexity lower bound for modular exponentiation against constant-depth prime-modulus circuits complements this result. The same argument recasts across subfields: preference learning under any misspecified model jumps discontinuously in sample complexity; multi-stage retrieval pipelines require at least as many independent metrics as stages; standard truthful auctions fail for agents with prompt-dependent valuations; and zero-knowledge verification of neural inference pays a measured overhead of one hundred ten to one hundred ninety times per non-linear activation. Together these form a catalogue of sixteen specifications, each pairing a computable boundary, a quantified violation cost, and a constructive design rule: two compositions are proved, one pairing is an honest obstruction, and four remain open. The impossibility-specification methodology is offered for the generative research programme that trustworthy AI may need. Every fundamental limit of AI is also a design rule.

한국어 요약

📋 한 줄 요약

**[Impossibility Result → Design Spec]** Deterministic Horizon — 12 transformer 구조에서 19~31 reasoning depth로 측정되는 architecture-bound accuracy 한계 — 등 16개 impossibility를 trustworthy AI의 설계 사양으로 전환.

🎯 핵심 기여도

💡 핵심 아이디어

모든 fundamental limit는 동시에 설계 규칙이며, impossibility result는 회피해야 할 한계가 아니라 trustworthy AI 시스템을 만들기 위한 사양으로 변환되어야 한다 — 이를 systematically 수행하면 16개의 computable, quantified, constructive 디자인 가이드라인이 도출된다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 이론적 한계를 실무 설계 지침으로 시스템화, trustworthy AI의 generative 연구 프로그램 방법론 제안, 다양 분야 통합 catalog. **한계**: Thesis 형태로 방대 — 검증 부담, 일부 한계의 실측 가능성·도메인 일반화 미완, 4개 미해결 spec.

🚀 실용적 활용