Evidence Alignment and Transfer Boundaries in Sequential And Multi-Behavior Recommendation And Fashion Recommendation

Abstract

Progress in sequential and multi-behavior recommendation and fashion recommendation depends on more than accumulating favorable results. This critical synthesis connects dissipative Hamiltonian spectral-temporal dynamics for sequential recommendation with indirect personal-compatibility modeling for mix-and-match clothing and asks how measurement choices, boundary conditions, and decision costs shape the interpretation of both. The review draws on two focal records and 12 established sources already present in the project evidence cache. Its comparative framework links behavior graphs, contrastive learning, and temporal dynamics to downstream questions of interest decay and offline evaluation. The combined literature indicates that methodological gains become actionable only when behavior graphs and contrastive learning are evaluated together and when limits associated with offline evaluation are explicit. This shifts the emphasis from isolated scores toward traceable chains of evidence and decision relevance. The contribution is a decision-oriented synthesis that connects method selection to failure cost and treats reproducibility, provenance, and bounded generalization as first-order design requirements.