Here we report on a new Early Cretaceous eutherian represented by a partial skeleton from the Jiufotang Formation at Sihedang site, Lingyuan City, Liaoning Province that fills a crucial gap between the earliest eutherians from the Yixian Formation and later Cretaceous eutherians. The new specimen reveals, to our knowledge for the first time in eutherians, that the Meckelian cartilage was ossified but reduced in size, confirming a complete detachment of the middle ear from the lower jaw. Seven hyoid elements, including paired stylohyals, epihyals and thyrohyals and the single basihyal are preserved. For the inner ear the ossified primary lamina, base of the secondary lamina, ossified cochlear ganglion and secondary crus commune are present and the cochlear canal is coiled through 360°. In addition, plesiomorphic features of the dentition include weak conules, lack of pre- and post-cingula and less expanded protocones on the upper molars and height differential between the trigonid and talonid, a large protoconid and a small paraconid on the lower molars. The new taxon displays an alternating pattern of tooth replacement with P3 being the last upper premolar to erupt similar to the basal eutherian
Juramaia
. Parsimony analysis places the new taxon with
Montanalestes
,
Sinodelphys
and
Ambolestes
as a sister group to other eutherians.
This article is part of the theme issue ‘The impact of Chinese palaeontology on evolutionary research’.
Accumulating data have led to the emergence of data-driven paleontological studies, which reveal an unprecedented picture of evolutionary history. However, the fast-growing quantity and complication of data modalities make data processing laborious and inconsistent, while also lacking clear benchmarks to evaluate data collection and generation, and the performances of different methods on similar tasks. Recently, Artificial Intelligence (AI) is widely practiced across scientific disciplines, but has not become mainstream in paleontology where manual workflows are still typical. In this study, we review more than 70 paleontological AI studies since the 1980s, covering major tasks including micro- and macrofossil classification, image segmentation, and prediction. These studies feature a wide range of techniques such as Knowledge Based Systems (KBS), neural networks, transfer learning, and many other machine learning methods to automate a variety of paleontological research workflows. Here, we discuss their methods, datasets, and performance and compare them with more conventional AI studies. We attribute the recent increase in paleontological AI studies to the lowering bar in training and deployment of AI models rather than real progress. We also present recently developed AI implementations such as diffusion model content generation and Large Language Models (LLMs) to speculate how these approaches may interface with paleontological research. Even though AI has not yet flourished in paleontological research, successful implementation of AI is growing and show promise for transformative effect on the workflow in paleontological research in the years to come.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.