Here are the ~2.5K "Unlikely to engage in spammy behavior" (i.e. value = 2) accounts being followed by @bleu.eth (left) vs. the ~6.8K accounts that are following @bleu.eth (right)

There are 40K+ (value = 2) accounts in the map with 8.2 million following/followers relationships between them represented

CEO and Founder of $BLEU

Developing infinite memetics AI Agent @elefant


lebleuelefant.com

FIP: Labels

A data standard to annonate context about accounts like language, humanity, spamminess and other qualities.

Labels will make it easy to generate public datasets that are useful for app developers to categorize casts and users. 

https://github.com/farcasterxyz/protocol/discussions/216

have you considered publishing a public dataset

I like running, poker and oysters | Founder, Social Forensics (SocialForensics.com) | Berkeley & UPenn | Learning to listen

have you considered publishing a public dataset

https://warpcast.com/v/0xa8954bee

Building @warpcast and @farcaster, new dad, like making food

Too much work, too little reward

That said, happy to share my thoughts on Warpcast's current spam detection algorithm with you and others on your team (cc: @akshaan) privately once I have done more analysis