1121. |
1122. Automated grading through contrastive learning : a gradient analysis and feature ablation approachMateo Sokač, Mario Fabijanić, Igor Mekterović, Leo Mršić, 2025, original scientific article Abstract: As programming education becomes increasingly complex, grading student code has become a challenging task. Traditional methods, such as dynamic and static analysis, offer foundational approaches but often fail to provide granular insights, leading to inconsistencies in grading and feedback. This study addresses the limitations of these methods by integrating contrastive learning with explainable AI techniques to assess SQL code submissions. We employed contrastive learning to differentiate between student and correct SQL solutions, projecting them into a high-dimensional latent space, and used the Frobenius norm to measure the distance between these representations. This distance was used to predict the percentage of points deducted from each student’s solution. To enhance interpretability, we implemented feature ablation and integrated gradients, which provide insights into the specific tokens in student code that impact the grading outcomes. Our findings indicate that this approach improves the accuracy, consistency, and transparency of automated grading, aligning more closely with human grading standards. The results suggest that this framework could be a valuable tool for automated programming assessment systems, offering clear, actionable feedback and making machine learning models in educational contexts more interpretable and effective.
Keywords: automated programming assessment systems (APASs), contrastive learning, explainable AI, feature ablation, integrated gradients, machine learning in education, natural language processing (NLP)
Published in DiRROS: 09.09.2025; Views: 309; Downloads: 153
 Full text (4,12 MB)
This document has many files! More... |
1123. |
1124. |
1125. Strength prominence index : a link prediction method in fuzzy social networkSakshi Dev Pandey, Sovan Samanta, Leo Mršić, Antonios Kalampakas, Tofigh Allahviranloo, 2025, original scientific article Abstract: Link prediction is a field within social network studies that aims to forecast future connections based on the structure of a social network. This paper introduces a link prediction method based on the strength and prominence of seed node pairs, referred to as the strength prominence index. In this method, we get a consistent score for any pair of nodes, regardless of whether they share a common neighbour. Several key characteristics have been identified. In our experiments, we used three well-known estimators to evaluate the accuracy of link prediction algorithms: precision, area under the precision-recall curve, and area under the receiver operating characteristic curve. A comparative study with existing methods is also presented, supported by relevant graphs and tables. Validation using Facebook data sets demonstrates the effectiveness of the proposed method.
Keywords: link prediction, similarity indices, fuzzy social network, strength prominence (SP) index
Published in DiRROS: 09.09.2025; Views: 303; Downloads: 87
Full text (2,12 MB) |
1126. |
1127. A mesoionic bis(Py-tzNHC) palladium(II) complex catalyses "green" Sonogashira reaction through an unprecedented mechanismMartin Gazvoda, Miha Virant, Andrej Pevec, Damijana Urankar, Aljoša Bolje, Marijan Kočevar, Janez Košmrlj, 2016, original scientific article Keywords: catalysis, palladium, ligand, carbene, Sonogashira, mechanism, mass spectrometry
Published in DiRROS: 09.09.2025; Views: 252; Downloads: 124
Full text (2,57 MB)
This document has many files! More... |
1128. |
1129. |
1130. |
