Working memory (WM) is an executive function that orchestrates the use of a limited amount of information, referred to as working memory capacity (WMC), in cognitive functions. In humans, Cannabis exposure impairs WM; however, it is unclear if Cannabis facilitates or impairs rodent WM. Existing literature also fails to address the effects of Cannabis exposure on rodent WMC using exposure paradigms that closely mirror patterns of human use. In the present study, WMC of rats was inferred by novelty preference after a short delay in spontaneous recognition-based tests. Either object or odor-based stimuli were used in different variations of the tests that present identical (IOT) and different (DOT) sets of stimuli (3 or 6) for low- and high-cognitive loads, respectively. Additionally, we present a human-machine hybrid (HYB) behavioral quantification approach which supplements stopwatch-based scoring with supervised machine learning (SML)-based classification, enabling behavioral data to be made publicly available. After validating the spontaneous tests, 6-item IOT and DOT tests with the HYB method were used to evaluate the impact of acute exposure to high-THC or high-CBD Cannabis smoke on novelty preference. Under control conditions, rats showed novelty preference in all test variations. We found that high-THC, but not high-CBD, Cannabis smoke exposure impaired novelty preference for objects under a high-cognitive load. Odor-based recognition deficits were seen under both low-, and high-cognitive loads only following high-THC smoke exposure. Ultimately, these data show that Cannabis smoke exposure impacts novelty preference in a load-dependent, and stimuli-specific manner.