Temporal RF models typically require fixed-length IQsequences, yet real-world bursts arrive at variable durations andsampling rates. In RF–QUANTUM–SCYTHE, the temporal inputbuilder _create_temporal_input normalizes each complexIQ stream to a configured sequence length before feeding recurrentand transformer-style encoders.This paper compares three practical IQ length normalizationpolicies—evenly spaced downsampling, windowed pooling, andstrided crops—in a shared RF modulation classification stack.We … Continue reading IQ Length Normalization Policies for RF Modulation Classifiers