Capturing Misalignment
We introduce and formalize misalignment, a phenomenon of interactive environments perceived from an analyst's perspective where an agent holds beliefs about another agent's beliefs that do not correspond to the actual beliefs of the latter. We demonstrate that standard frameworks, such as type structures, fail to capture misalignment, necessitating new tools to analyze this phenomenon. To this end, we characterize misalignment through non-belief-closed state spaces and introduce agent-dependent type structures, which provide a flexible tool to understand the varying degrees of misalignment. Furthermore, we establish that appropriately adapted modal operators on agent-dependent type structures behave consistently with standard properties, enabling us to explore the implications of misalignment for interactive reasoning. Finally, we show how speculative trade can arise under misalignment, even when imposing the corresponding assumptions that rule out such trades in standard environments.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Equivariant Latent Alignment via Flow Matching under Group Symmetries
Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework fo…
Representation LearningNovel View SynthesisPCReg-Net: Progressive Contrast-Guided Registration for Cross-Domain Image Alignment
Deformable image registration across heterogeneous domains remains challenging because coupled appearance variation and geometric misalignment violate the brightness constancy assumption underlying conventional methods. …
Image RegistrationLost in Time? A Meta-Learning Framework for Time-Shift-Tolerant Physiological Signal Transformation
Translating non-invasive signals such as photoplethysmography (PPG) and ballistocardiography (BCG) into clinically meaningful signals like arterial blood pressure (ABP) is vital for continuous, low-cost healthcare monito…
Learning with noisy labelsAdversarial Examples Are Not Bugs, They Are Features
Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be directly attributed to …
BIG-bench Machine LearningDo We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation
Domain generalization in semantic segmentation faces challenges from domain shifts, particularly under adverse conditions. While diffusion-based data generation methods show promise, they introduce inherent misalignment …
Domain GeneralizationSemantic Segmentation