Zero-Observation User Reactivation with Gap-Driven Dimensional Gating

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Sequential recommendation (SR) models capture continuously observed behavior, but a returning user may have no interactions for months or years. We define this setting as Zero-Observation Reactivation: the user has a pre-gap history, while the platform observes no behavioral signals during a macro-gap Δt. Using a chronologically aligned Gap-Synthesize Protocol on three Amazon datasets (Video Games, CDs & Vinyl, and Movies & TV), we first show that the central failure mode is systematic: Hit@10 decreases monotonically across the evaluated gap buckets and reaches its lowest level beyond one year. This decay appears across recurrent, unidirectional, and bidirectional SR backbones.