If the methodologically stronger study (Hosseinmardi with off-platform controls) finds against algorithmic radicalization while the weaker study (Ribeiro without such controls) finds for it, the weight of evidence favors the skeptical interpretation.

<iframe
  src="https://www.isonomia.app/embed/claim/7c336a0632859be90a121262497c82102c59b25419eb1d5ff3df9517ea20a500"
  width="600"
  height="280"
  frameborder="0"
  style="border: 1px solid #e5e7eb; border-radius: 8px;"
  title="Isonomia Claim"
  loading="lazy"
></iframe>

Copy and paste into any website or forum that supports HTML.