5 papers · 1 filter
Certifying Interventional Agreement Among Observationally Equivalent Causal Models
Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1
Observationally equivalent causal models can still disagree about what happens under intervention, because interventions create inputs that never occur in observational data. We in…
Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution
Veronica Poweska, Ariana Oyanguren, Jessica Pourleyli +2
Dependency conflicts in Python ecosystems arise from incompatible version constraints, missing packages, and undocumented compatibility relationships, causing many real-world code…
Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents
Theo Rusu, Sourena Khanzadeh, Manar Alalfi
Knowledge graphs have been proposed as a structured alternative to flat retrieval-augmented generation for long-term agent memory, on the assumption that representing conversations…
Share No More Than the Request Requires: Federated Disclosure for Perspective-Aware AI
Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1
Modern AI systems bring societal risks such as mass surveillance, extreme concentrations of power, and loss of user autonomy---calling into question a model where third-parties col…
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
Sourena Khanzadeh
As Large Language Model (LLM) agents are increasingly tasked with high-stakes autonomous decision-making, the transparency of their reasoning processes has become a critical safety…