Muhammad Huzaifa Sohail

Muhammad Huzaifa Sohail

Auto-generated profile, based on publicly available information

Muhammad Huzaifa Sohail

Department of Computer Science, University of Central Punjab, Lahore, Pakistan

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 February 2026 in VAWKUM Transactions on Computer Sciences
Verified
Journal Article
Open access
PDF file
MSMuhammad Huzaifa Sohail
Muhammad Huzaifa Sohail
ZGZaheer Ahmad Gondal
Zaheer Ahmad Gondal
MAMOHSIN ASHRAF
MOHSIN ASHRAF
The rapid adoption of online examinations has increased the demand for secure, intelligent, and reliable assessment systems. However, existing solutions often lack adaptive evaluation capabilities and formal verification of examination workflows. This paper presents a Context-Aware Evaluation Framework that addresses these limitations through an integrated architecture. The framework combines secure examination management, LLM-based assessment, and formally verified workflow execution. A key contribution is a dynamic rubric ingestion pipeline that transforms evaluation rubrics into structured contextual inputs for the grading model. The proposed rubric representation (R={C,S,W,X}), captures evaluation criteria, scoring scales, contextual weights, and anchor exemplars. This design enables context-aware and rubric-conditioned grading of diverse student responses. Grading consistency is evaluated using the Quadratic Weighted Kappa (QWK) metric. Another contribution is a Petri net-based workflow model that formally represents concurrent and state-dependent examination processes. The model incorporates synchronization mechanisms for complete rubric evaluation and bounded correction loops for reliable LLM output re-parsing. Reachability graph analysis confirms liveness, boundedness, and deadlock-freedom, ensuring mathematically verified workflow correctness. The framework also strengthens examination security through facial recognition, encryption, cryptographic hashing, ActiveX-based anti-cheating mechanisms, and natural language processing-based spoken-text relevance analysis. By integrating intelligent assessment, formal verification, and multi-layer security, the proposed framework provides a reliable foundation for next-generation online examination systems. Future work will investigate real-time instructor intervention and adaptive prompt refinement to further improve grading accuracy and workflow resilience.