Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware SSL

We hypothesize that neurons showing statistical regularity are ideal for effective SSL pretraining. Within our self-supervised learning (SSL) framework, we operationally define this property as predictability--the inherent statistical structure of a neural signal that enables the effective reconstruction of its masked portions. To identify these predictable neurons without using cell-type labels, we leverage per-neuron skewness and kurtosis as simple statistical proxies. Neurons with low skewness and kurtosis exhibit stable, near-Gaussian activity suitable for learning general features, whereas high-skew/kurtosis neurons show sparse, burst-like responses better reserved for task-specific fine-tuning. For rigorous empirical validation of our statistical metric selection, including comparative analysis against first-and second-order statistics and data-driven threshold determination, see Appendix B. 3 To objectively partition the data, we applied a knee-detection algorithm (Satopaa et al. (2011)) to find a data-driven threshold across 13 CRE lines. While this approach failed for lower-order statistics like event rate and Fano factor, it revealed a clear breakpoint for both skewness and kurtosis, providing a principled basis for our split. The resulting data-driven thresholds (skewness 3.51, kurtosis 22.62) identified a "predictable" subset comprising four CRE lines: SST, VIP, PV ALB, and NTSR1. This statistically derived group is also biologically coherent, consisting of three major inhibitory interneuron classes and one regulatory corticothalamic excitatory line (NTSR1), all of which are crucial for stabilizing neural circuits.