twitter / communitynotes

Documentation and source code powering Twitter's Community Notes
https://twitter.github.io/communitynotes
Apache License 2.0
1.42k stars 196 forks source link

Split scoring binary into separate prescoring and final scoring binaries #216

Closed jbaxter closed 5 months ago

jbaxter commented 5 months ago

This PR splits the monolithic scoring binary into two separate scoring binaries (that may still be run sequentially):

  1. Prescoring: do expensive pre-computation to learn user and note parameters
  2. [Final] Scoring: ingest prescoring outputs in order to save computation time, then run scoring like it is today.

In this commit, the final result of scoring is the same. In the future though, this unlocks much work to simplify the final scorer.