{"ID":2830914,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10106","arxiv_id":"2512.10106","title":"A Simulation Framework for Studying Recommendation-Network Co-evolution in Social Platforms","abstract":"Studying how recommendation systems reshape social networks is difficult on live platforms: confounds abound, and controlled experiments risk user harm. We present an agent-based simulator where content production, tie formation, and a graph attention network (GAT) recommender co-evolve in a closed loop. We calibrate parameters using Mastodon data and validate out-of-sample against Bluesky (4--6\\% error on structural metrics; 10--15\\% on held-out temporal splits). Across 18 configurations at 100 agents, we find that \\emph{activation timing} affects outcomes: introducing recommendations at $t=10$ vs.\\ $t=40$ decreases transitivity by 10\\% while engagement differs by $\u003c$8\\%. Delaying activation increases content diversity by 9\\% while reducing modularity by 4\\%. Scaling experiments ($n$ up to 5,000) show the effect persists but attenuates. Jacobian analysis confirms local stability under bounded reactance parameters. We release configuration schemas and reproduction scripts.","short_abstract":"Studying how recommendation systems reshape social networks is difficult on live platforms: confounds abound, and controlled experiments risk user harm. We present an agent-based simulator where content production, tie formation, and a graph attention network (GAT) recommender co-evolve in a closed loop. We calibrate p...","url_abs":"https://arxiv.org/abs/2512.10106","url_pdf":"https://arxiv.org/pdf/2512.10106v1","authors":"[\"Gaurav Koley\",\"Sanika Digrajkar\"]","published":"2025-12-10T21:52:38Z","proceeding":"cs.SI","tasks":"[\"cs.SI\",\"cs.MA\"]","methods":"[]","has_code":false}