Som Subhro Nath

About

Som is an undergraduate researcher, currently pursuing a B.Sc. in Computer Science at the University of Calcutta. With a strong foundation in AI ethics, human-AI interaction, and emotional computing, he has authored multiple research papers, including submissions to Springer Nature. Som is the innovator behind SmartNest, a patented smart home ecosystem designed to integrate intelligent automation with everyday living.

He is passionate about bridging technological innovation with social impact and envisions a future where empathetic AI systems support human well-being without compromising ethical integrity. Som holds certifications from IBM, HackerRank, and several recognized platforms in UI/UX, ethical hacking, and entrepreneurial design thinking. His work integrates academic excellence with real-world problem-solving, aiming toward a direct Ph.D. abroad and global recognition in AI research.

Employment

Employment history is unavailable.

Education

• University of Calcutta Bachelor of Science
  2025 - 2028
• Bhavan's Gangabux Kanoria Vidyamandir Senior Secondary
  2023 - 2025
• Bharatiya Vidya Bhavan Secondary School
  2010 - 2023

Projects & Funding

Projects & funding information is unavailable.

Publications (21)

• Emergent Inter-Agent Conflict in Multi-Agent AI Systems: An Experimental Study of Objective Divergence
  2026 DOI: 10.21203/rs.3.rs-9869041/v1
  +Save
• Affective Misgrounding in Aligned Language Models: A Quantitative Analysis of Emotional Hallucination in LLM Responses
  2026 DOI: 10.21203/rs.3.rs-9583845/v1
  +Save
• A Lightweight Neural Network Compression Pipeline for Resource-Constrained Edge AI Systems
  2026 DOI: 10.21203/rs.3.rs-9295528/v1
  +Save
• A Lightweight Neural Network Compression Pipeline for Resource-Constrained Edge AI Systems
  2026 DOI: 10.22541/au.177507267.71283332/v1
  +Save
• Affective Misgrounding in Aligned Language Models: A Quantitative Analysis of Emotional Hallucination in LLM Responses
  2026 DOI: 10.2139/ssrn.6687098
  +Save
• Algorithmic Intimacy in AI Companionship Systems: Dopamine-Driven Reinforcement and the Emergence of Synthetic Attachment
  2026 DOI: 10.2139/ssrn.6636398
  +Save
• Counterfactual Divergence Singularity: A Theoretical Model of High-Similarity Instability and Micro-Counterfactual Drift in Large Language Models
  2026 DOI: 10.2139/ssrn.6210024
  +Save
• Emergent Inter-Agent Conflict in Multi-Agent AI Systems: An Experimental Study of Objective Divergence
  2026 DOI: 10.2139/ssrn.6853998
  +Save
• Toward a Theory of Semantic Fixed Points: Evidence from Iterative Language Model Self-Refinement
  2026 DOI: 10.2139/ssrn.7095579
  +Save
• Toward a Theory of Semantic Fixed Points: Evidence from Iterative Language Model Self-Refinement
  2026 DOI: 10.21203/rs.3.rs-10319853/v1
  +Save