Fairness perceptions can significantly impact the instigation and resolution of conflicts. To examine how fairness norms shape agreements, we conduct an experiment, where participants first select a preferred rule between equal division, equal gain, and proportional division. When paired with another sharing the same norm, participants decide whether to adhere to the projected division or negotiate a different outcome. Experimental results reveal that participants renege on the agreement more frequently when allocations are perceived as unfair to the self: high contributors in equal division and low contributors in proportional division. Furthermore, attachment to the initial norm is sturdiest for strict equality and weakest for proportionality. Equal gain, coinciding with the Nash bargaining solution, is the most favored at both preselection and negotiation outcomes. We discuss several applications of our findings in resolving international conflicts.

Diagnosing COVID-19 infection through the classification of chest images using machine learning techniques faces many controversial problems owing to the intrinsic nature of medical image data and classification architectures. The detection of lesions caused by COVID-19 in the human lung with properties such as location, size, and distribution is more practical and meaningful to medical workers for severity assessment, progress monitoring, and treatment, thus improving patients’ recovery. We proposed a COVID-19-associated lung lesion detector based on an object detection architecture. It correctly learns disease-relevant features by focusing on lung lesion annotation data of medical images. An annotated COVID-19 image dataset is currently nonexistent. We designed our semi-self-supervised method, which can extract knowledge from available annotated pneumonia image data and guide a novice in annotating lesions on COVID-19 images in the absence of a medical specialist. We prepared a sufficient dataset with nearly 8000 lung lesion annotations to train our deep learning model. We comprehensively evaluated our model on a test dataset with nearly 1500 annotations. The results demonstrated that the COVID-19 images annotated by our method significantly enhanced the model’s accuracy by as much as 1.68 times, and our model competes with commercialized solutions. Finally, all experimental data from multiple sources with different annotation data formats are standardized into a unified COCO format and publicly available to the research community to accelerate research on the detection of COVID-19 using deep learning.