We're making the Warpcast spam dataset public. 

Over 400,000 accounts have been processed by our model, which determines the accounts that are most likely to generate inauthentic content or unwanted notifications.

We're making the Warpcast spam dataset public. 

Over 400,000 accounts have been processed by our model, which determines the accounts that are most likely to generate inauthentic content or unwanted notifications. 

https://github.com/warpcast/labels

Developers can use this to protect their apps from spammy users. 

Spam labels are provided as a JSONL file which follows the FIP: Labels specification (still in review). 

Data will be updated weekly with the latest labels.

Technowatermelon. Elder Millenial. Building Farcaster. 

nf.td/varun

While we've taken a lot of care to correct mistakes, its possible that a small number of legitimate accounts are misclassified. 

If you notice this, please reply to this thread or DM me. We will use these reports to improve the model.

No Channel Channel.

If you might be spammy, i will give you ham for anybody who's 1 for today and tomorrow. Cast a screen shot of your spammy status in the replies.

I believe Einbard was misclassified as potentially spam. They are a comfy caster who has a nice lane primarily playing wordle, gming, and sharing the latest beer or park they are exploring. I interact with accounts I’m pretty sure are spam and can see why the model might be confused but Ein isn’t spam

I believe Einbard was misclassified as potentially spam. They are a comfy caster who has a nice lane primarily playing wordle, gming, and sharing the latest beer or park they are exploring. I interact with accounts I’m pretty sure are spam and can see why the model might be confused but Ein isn’t spam 


https://warpcast.com/einbard/0x2865c221

oh I didn’t notice that before either maybe that’s when the score last got updated

thank you, i just noticed this last update in march 11 2024, i wonder what that means