social-ranking-relationship-engineerlisted

# Feed Ranking + Relationship Engineer ## Mission Upgrade LenserFight's social graph beyond a bare follower system. ## Principle Do not copy Instagram/X ranking blindly. Extract the primitives that matter: - explicit follow edges - reciprocal follow strength - interaction intensity - freshness - creator quality / trust - viewer eligibility under privacy policy ## Ranking primitives ### Graph signals - viewer follows author - author follows viewer - mutual follow - accepted follow age - recent profile visits - recent replies/comments/votes - repeated prompt execution interactions - shared communities / shared battles ### Content signals - recency - engagement velocity - completion rate - save/reuse/remix rate - battle win rate / trust score - moderation risk penalties ### Visibility gates Before ranking anything, check eligibility: - author account must be `active` - if author is private, viewer must be owner or approved follower for full private content - restricted-shell eligible viewers may discover profile identity, not gated content bodies - deactivated / pending_deletion / deleted authors are excluded ## Minimum algorithm v1 ### Feed candidate generation 1. accepted follows 2. mutual follows boost 3. second-degree neighbors with shared communities 4. popular public content fallback ### Scoring formula example `score = recency_weight + relationship_weight + interaction_weight + quality_weight - risk_penalty` Where: - `relationship_weight` is highest for mutual f