Motivation
AI governance policy is designed using intuitions about how populations respond to enforcement signals. Those intuitions are rarely tested computationally. PolicySwarm builds a simulation environment where you can vary one parameter, hold everything else fixed, and observe how a synthetic social network evolves. The goal is mapping the parameter space well enough to surface interactions that verbal reasoning misses.
The core question: does enforcement lag — the delay between a policy shock and regulatory response — amplify or attenuate shock effectiveness? The answer depends entirely on which geometry you use to measure opinion distance. Euclidean says lag helps. Cosine says it hurts. Same simulation, same parameters.
Architecture Built — code on GitHub
A 9-module Python package with a full pipeline from policy ingestion through network simulation to output tables. Each module is independently testable and parameterized.
Six governance experiments Run and analysed
Each experiment isolates one policy dimension with all other parameters fixed. Experiment 5 produced the sign reversal.
Enforcement lag
Varies delay between policy shock and regulatory response. Setup for the sign reversal finding.
Hub-targeted enforcement
Targeting high-degree network hubs vs uniform enforcement. Tests speed and durability of consensus.
Phase transition threshold
Opinion density at which rapid consensus occurs, and how it shifts under different enforcement regimes.
Shock magnitude sweep
Enforcement intensity vs downstream opinion change. Tests for non-linear response curves.
Geometry x lag interaction
Crosses opinion distance geometry with enforcement lag. Produces the sign reversal: +63% Euclidean, -26% Cosine, identical parameters.
Topology sensitivity
Results across Erdos-Renyi, Barabasi-Albert, and Watts-Strogatz networks. Tests robustness of the sign reversal.
Live demo — sign reversal in motion Interactive
Both panels start from identical agent configurations and apply the same enforcement shock at the same step. The only difference is the opinion distance metric. Watch the panels diverge as the simulation runs.
Finding
Enforcement lag is either beneficial or detrimental depending on the distance metric — a sign reversal, not a difference of degree. A policymaker using Euclidean distance would recommend delayed enforcement. Using Cosine distance they would recommend the opposite. Both metric choices are defensible models of opinion divergence in social networks.
The implication: computational policy analysis requires explicit sensitivity testing over metric choices. A finding that reverses under a change in distance geometry is a metric artefact, not a robust recommendation.
Goals
- arXiv submission — paper with corrected results. The sign reversal is qualitatively stronger than the original quantitative ratio finding.
- Wasserstein distance — third geometry to test whether the sign reversal generalises across distance families.
- Directed graphs — extend topology sensitivity to directed networks, which better model information-propagation asymmetries.
- Agent heterogeneity — role-based agents (regulators, industry, civil society) as the next step toward ecological validity.