Varun Srinivasan on Farcaster

Varun Srinivasan pfp

Varun Srinivasan

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

36 replies

70 recasts

273 reactions

Varun Srinivasan pfp

Varun Srinivasan

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.

2 replies

0 recast

16 reactions

Pichi pfp

@v Have a couple of users to point out. @matteosan is labeled as spam. This is a user I hand onboard to Farcaster. They stopped using the app because they were labeled as spam incorrectly and couldn’t get unlabeled. Nothing they’ve casted is remotely spammy. @bit-inko is a well respected Japanese caster but these days they cast mostly in Japanese and less in English. They are not spammy. I recently created an AI agent using @jam new toolset. It’s called @kyotoguide and it’s a good bot that I’ve triggered on purpose and it’s got a spam label in less than a few days of casting. Hope these edge cases help.

2 replies

1 recast

2 reactions

Anil T Prabhakar 🦉🎩📸 pfp

Anil T Prabhakar 🦉🎩📸

@aniltprabhakar

I don’t know how it happened, can you help me out from this ?

1 reply

0 recast

0 reaction

Mahesh 🦉🎩 pfp

Mahesh 🦉🎩

Thanks for this. Will make a dune query to make it accessible to all.

0 reply

0 recast

2 reactions

Brenner pfp

Does warpcast have any plan on showing the label on casts? Would love to be able to configure who’s labels I see on all casts One example: zkp’d labels of ownership etc (the way @anonworld does)

0 reply

0 recast

1 reaction

Linda Xie pfp

Thank you so much!! Going to incorporate this for Bountycaster

1 reply

3 recasts

27 reactions

Michael Pfister pfp

Michael Pfister

Huge! Thank you for doing this We will be incorporating this into how we index data at buoy.

0 reply

0 recast

6 reactions

yesyes pfp

>updated weekly Pretty cool Still worried about some people getting mad about receiving the wrong label but I think this is a net +

1 reply

0 recast

4 reactions

Pichi pfp

This is awesome. Thank you all for the transparency.

0 reply

0 recast

2 reactions

Pichi pfp

I think @sheva7.eth is another Japanese caster incorrectly labeled as spam. They are leading the way on what you can do with no code frames and creating tons of original content. https://warpcast.com/sheva7.eth https://warpcast.com/sheva7.eth

0 reply

0 recast

1 reaction

Tiago pfp

@alvesjtiago.eth

thank you for doing this

0 reply

0 recast

1 reaction

Michael Boyle pfp

Love this, thank you

0 reply

0 recast

1 reaction

Pichi pfp

Here’s an artist recently onboarded to Farcaster. Very new account, instant spam label. https://warpcast.com/dobaa

0 reply

0 recast

0 reaction

Haole pfp

thank you for sharing this. very useful!

0 reply

0 recast

0 reaction

mvr 🐹 pfp

Thanks for this, made it a bit easier for people to check their label https://spam.hamst.art/frames/spammer/230238/HfFNoJH8

5 replies

2 recasts

13 reactions

ŁΞℕ♾ℕ ⛃ 🎩 pfp

ŁΞℕ♾ℕ ⛃ 🎩

@v Greetings, I come to report that @cieliss-esdeath is tagged as SPAM, her content not SPAM at all in fact her activity is very similar to mine and I was not tagged as SPAM. I have a channel called /web3appdev she is my moderator and her replies go to the see more replies drawer, being a member and moderator of the channel, she is a good user and has helped and added value in several communities.

0 reply

1 recast

1 reaction

Colin Charles pfp

This is so cool, thank you for doing this. I guess I'm safe, for now! ("Spam labels are updated weekly.") {"provider": 9152, "type": {"target": "user", "fid": 4703}, "label_type": "spam", "label_value": 2, "timestamp": 1737287054}

1 reply

0 recast

2 reactions

Mark pfp

0 reply

0 recast

1 reaction

Schmidtiest.eth 🎩 pfp

Schmidtiest.eth 🎩

@schmidtiest.eth

i got labeled a 1. how am i supposed to know what “behaviors” to change? how do you know what is an irrelevant response to the intended recipient? the github readme doesn’t really shed light on this for me- outside of basically saying “don’t do these few things” which i already don’t do anyway.

0 reply

0 recast

0 reaction