ALGORITHM LOGIC
Complete visualization of the "For You" recommendation pipeline.
SYSTEM FLOW
Query Hydration
Fetch user context: engagement history, following list, preferences.
Candidate Sources
Thunder (followed accounts) + Phoenix Retrieval (global tweets).
Hydration
Enrich with tweet content, author info, media metadata.
Filters
Remove duplicates, old posts, self-posts, seen posts, blocked/muted authors.
Scoring
Phoenix predicts multi-action probs → weighted sum → diversity decay.
Selection + VF
Take Top-K → visibility filtering → final distribution.
Interactive Pipeline
Explore each stage in detail with our interactive explorer tool.
Ranking Signals
Deep dive into the Attention Mask and candidate isolation logic.
CORE MECHANICS
System predicts P(like), P(reply), P(repost) simultaneously using multi-target Transformers.
Same-author posts are attenuated via Author Diversity heuristics to avoid feed homogenization.
Candidates are scored independently via Attention Masking for stability and efficient caching.
Out-of-network content is decayed based on the Social Graph relationship strength.