collaborators

5 papers

cs.AI2026

Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling

Muntaser Syed, Markus Zanker, Marius Silaghi

In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses which arguments each voter sees, acquiring much of the decision; practice delegates…

cs.AI2026

TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning

Rwaida Alssadi, Muntaser Syed, Balaji Kasula +6

Contemporary LLM-based coding agents produce code as black-box outputs: the rationale behind each line is hidden, the evolution of the code through benchmark-driven repair is ephem…

cs.LG2026

Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation

Muntaser Syed, Marius Silaghi, Sheikh Abujar +1

Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all re…

cs.CY2026

The Environmental Cost of Digital Sovereignty: Water, Energy, and Emissions Impacts of Sovereign AI Infrastructure in the Global South

Muntaser Syed, Marius C. Silaghi, Sheikh Abujar +2

Sovereign AI has become a strategic priority across the Global South, with over $200 billion in state-led commitments announced between 2024 and 2026. Yet the physical infrastruct…

cs.CY2026

Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic Simulator

Rwaida Alssadi, Khulud Alawaji, Balaji Kasula +4

Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote. Yet ensuring that every voter encounter…