Specialty
A tabular foundation model called TFM4POP reportedly beat the tested baselines at forecasting future growth in social-media cascades. The results come from an arXiv preprint and do not show that the model changes how information spreads.
Scientific publication4 min read
Across 46 mostly rural communities in 28 countries, wealthier sharing units generally had more support ties and connections to relatively wealthier units. Communities with greater wealth inequality also showed more separation between wealth groups in their networks, but the cross-sectional evidence cannot establish cause and effect.
Scientific publication4 min read
A finite mathematical model separates perception lag from concealment, finding that expressive bias can remain at equilibrium while some hierarchical responses amplify only temporarily.
Scientific publication4 min read
An arXiv preprint reports that DOCG-AS produced larger gains in a model’s predicted diffusion score than Designed2Spread on Movie- and SpaceX-focused Twitter/X data. A small Movie-focused preference study also favored the generated versions, but the work did not measure actual reposting or establish causal effects in human audiences.
Scientific publication3 min read