AI RESEARCH
The UNDO Flip-Flop: A Controlled Probe for Reversible Semantic State Management in State Space Model
arXiv CS.LG
•
ArXi:2604.05923v1 Announce Type: new State space models (SSMs) have been shown to possess the theoretical capacity to model both star-free sequential tasks and bounded hierarchical structures Sarrof. However, formal expressivity results do not guarantee that gradient-based optimisation will reliably discover the corresponding solutions. Existing benchmarks probe either monotonic state tracking, as in the standard Flip-Flop task, or structural nesting, as in the Dyck languages, but neither isolates reversible semantic state retrieval. We