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

Abstract

Progress in sequential and multi-behavior recommendation depends on more than accumulating favorable results. This critical synthesis connects dissipative Hamiltonian spectral-temporal dynamics for sequential recommendation with hypergraph modeling with contrastive regularization for multi-behavior product recommendation and asks how measurement choices, boundary conditions, and decision costs shape the interpretation of both. Two target papers are triangulated against 11 locally validated publications. The comparison follows behavior graphs, contrastive learning, temporal dynamics, interest decay, offline evaluation and deliberately separates mechanistic interpretation from performance ranking, because the latter can conceal incompatible experimental or operational conditions. Across the evidence base, the decisive issue is alignment: behavior graphs shapes what is observed, contrastive learning shapes how it is compared, and offline evaluation governs whether the conclusion can be transferred. Uncertainty is most informative when reported as part of the result rather than treated as a postscript. The article concludes with a research agenda built around transparent comparators, targeted stress tests, and evidence records that can be reused without overstating causal or practical reach.