While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our understanding of these pre-trained models is arguably fairly limited. With the goal of advancing our understanding of these models, we perform the first systematic empirical comparison of 19 recently-developed pre-trained models of source code on 13 SE tasks. To gain additional insights into these models, we adopt a recently -developed 4-dimensional categorization of pre-trained models, and subsequently investigate whether there are correlations between different categories of pre-trained models and their performances on different SE tasks.

An energy‐harvesting decode‐and‐forward cooperative system over correlated Rayleigh fading channels is investigated. Simultaneous wireless information and power transfer (SWIPT) technology is employed at the relay to improve energy efficiency. To overcome the spatial correlation among the transmit antennas, precoding spatial modulation (PSM) is formulated. The average bit‐error probability (ABEP) upper bound is derived and it matches closely with the Monte Carlo simulation results. The influence of the parameters, such as the power‐splitting factor and transmit correlation coefficient, on system performance is studied. The results show that the proposed PSM‐SWIPT system can achieve better ABEP performance than SM‐SWIPT, space shift keying‐SWIPT and multiple‐input–multiple‐output‐SWIPT systems under the same spectral efficiency.