Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents

David N. Olivieri, Roque J. Hernández

arXiv:2605.14033 · 2026-05-16 공개 · arXiv · PDF

ai-agents constraint-violation sheaf-theory local-to-global diagnostic-framework representational-cost theory-shift representation-transport

Abstract

Scientific theory shift in AI agents requires more than fitting equations to data. An artificial scientific agent must detect whether an existing representational framework remains transportable into a new regime, or whether its language has become locally-to-globally obstructed and must be extended. This paper develops a finite sheaf-theoretic framework for detecting theory-shift candidates through transport and obstruction. Contexts are organized as a local-to-global structure in which source, overlap, target, and validation charts are fitted, restricted, and tested for gluing. Obstruction measures failure of coherence through residual fit, overlap incompatibility, constraint violation, limiting-relation failure, and representational cost. We evaluate the framework on a controlled transition-card benchmark designed to separate deformation within a source language from extension of that language. The main result is direct obstruction ranking: the intended deformation or extension is usually the lowest-obstruction candidate, and transition type is separated in the benchmark. A constellation kernel over the same signatures is included only as a secondary representational-similarity probe. The aim is not to reconstruct historical paradigm shifts or solve open-ended autonomous theory invention, but to isolate a finite diagnostic subproblem for AI agents: detecting when representational transport fails and extension becomes the coherent next move.

한국어 요약

📋 한 줄 요약

**[AI for Science / Theory Shift Detection]** 시프(sheaf) 이론 기반의 transport/obstruction 프레임워크로, AI 에이전트가 기존 표현 언어로 새로운 영역으로 옮겨갈 수 있는지 vs 언어 자체를 확장해야 하는지를 진단한다.

🎯 핵심 기여도

💡 핵심 아이디어

AI 에이전트가 새로운 과학 데이터를 만났을 때, 기존 이론을 "더 잘 맞도록 변형"할지 아니면 "언어 자체를 확장"할지를 구분하는 것이 핵심이다. 이를 sheaf 이론의 국소→전역 일관성과 그 실패(obstruction)로 형식화하면, 정량적 진단 지표로 만들 수 있다.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 자율적 과학 에이전트가 패러다임 전환의 후보 지점을 정량적으로 감지할 수 있는 finite diagnostic subproblem을 제시. **한계**: 역사적 패러다임 시프트의 완전한 재구성이나 open-ended theory invention은 다루지 않으며, 통제된 카드 벤치마크 위주의 평가.

🚀 실용적 활용