Characterizes the distributional mean-field limit of co-evolving latent space networks with feedback, including empirical measures and graphon convergence, via a conditional propagation of chaos result.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
BOUNDARY_SYNC defines CAF as the ratio of conditional to baseline Jensen-Shannon divergence to quantify communication-induced representational coupling in multi-agent LLMs, reporting homogenization from text communication (CAF=0.803).
Embedding epidemic contact networks via Johnson-Lindenstrauss projections allows estimating the infection source as the node nearest the centroid of infected nodes, achieving meaningful accuracy in simulations on Erdős-Rényi graphs.
Code embeddings combined with the Expressed-Private Opinion model produce trajectories that quantify developer influence and consensus formation across three open-source repositories.
citing papers explorer
-
Mean-Field Analysis of Latent Variable Process Models on Dynamically Evolving Graphs with Feedback Effects
Characterizes the distributional mean-field limit of co-evolving latent space networks with feedback, including empirical measures and graphon convergence, via a conditional propagation of chaos result.
-
BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems
BOUNDARY_SYNC defines CAF as the ratio of conditional to baseline Jensen-Shannon divergence to quantify communication-induced representational coupling in multi-agent LLMs, reporting homogenization from text communication (CAF=0.803).
-
Finding Patient Zero via Low-Dimensional Geometric Embeddings
Embedding epidemic contact networks via Johnson-Lindenstrauss projections allows estimating the infection source as the node nearest the centroid of infected nodes, achieving meaningful accuracy in simulations on Erdős-Rényi graphs.
-
Social Life of Code: Modeling Evolution through Code Embedding and Opinion Dynamics
Code embeddings combined with the Expressed-Private Opinion model produce trajectories that quantify developer influence and consensus formation across three open-source repositories.
- Topology-Aware LLM-Driven Social Simulation: A Unified Framework for Efficient and Realistic Agent Dynamics