> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/twitter/the-algorithm/llms.txt
> Use this file to discover all available pages before exploring further.

# CR Mixer

> Candidate Retrieval and Mixing service for fast iteration on candidate generation

## Overview

CR-Mixer (Candidate Retrieval Mixer) is a candidate generation service designed to speed up iteration and development of candidate generation and light ranking for Twitter's recommendation systems. It acts as a lightweight coordinating layer that delegates candidate generation tasks to underlying compute services.

## Purpose

CR-Mixer was proposed as part of Twitter's Personalization Strategy to:

* **Speed up iteration** on candidate generation pipelines
* **Centralize candidate fetching** from multiple sources
* **Provide light ranking** capabilities before heavy ranking
* **Simplify testing** of new candidate sources and mixing strategies
* **Deliver more value** to users through faster experimentation

## Architecture

CR-Mixer acts as a **configurator and delegator**, providing abstractions for the challenging parts of candidate generation:

<CardGroup cols={2}>
  <Card title="1-Stop-Shop" icon="shop">
    Centralized platform for fetching and mixing candidate sources
  </Card>

  <Card title="Managed Platform" icon="server">
    Shared, performant infrastructure for candidate generation
  </Card>

  <Card title="Light Ranking" icon="ranking-star">
    Initial ranking layer before heavy ML models
  </Card>

  <Card title="Common Filtering" icon="filter">
    Shared filtering logic across use cases
  </Card>
</CardGroup>

## Pipeline Structure

CR-Mixer's pipeline consists of 4 main steps:

<Steps>
  <Step title="Source Signal Extraction">
    Fetch source signals externally from stores like:

    * **UserProfileService** - User profile and preference data
    * **RealGraph** - User interaction and engagement graphs
    * Other signal stores for context and personalization
  </Step>

  <Step title="Candidate Generation">
    Call external candidate generation services and cache results:

    * Tweet candidate sources
    * User candidate sources
    * Content-based recommendations
    * Collaborative filtering sources
  </Step>

  <Step title="Filtering">
    Apply filters for:

    * Deduplication across sources
    * Pre-ranking quality filters
    * Basic eligibility checks
    * Content policy filtering
  </Step>

  <Step title="Light Ranking">
    Initial ranking using lightweight models and heuristics before passing to heavy rankers
  </Step>
</Steps>

## Key Features

### Peripheral Tooling

CR-Mixer provides comprehensive tooling for monitoring and debugging:

* **Scribing** - Detailed logging of candidate generation pipeline
* **Debugging** - Tools to trace candidate flow through the system
* **Monitoring** - Real-time metrics and alerting
* **Version Control** - Track changes to candidate sources and configurations
* **Feature Switches** - Co-owned feature flag system for gradual rollouts

### Performance Optimization

CR-Mixer handles performance issues through:

* **Caching** - Results from expensive candidate generation calls
* **Batching** - Efficient batch calls to downstream services
* **Parallel Fetching** - Concurrent calls to multiple candidate sources
* **Timeouts** - Graceful degradation when sources are slow

## Use Cases

CR-Mixer supports various Twitter recommendation use cases:

<CardGroup cols={2}>
  <Card title="Home Timeline" icon="house">
    Generate tweet candidates for For You timeline
  </Card>

  <Card title="Notifications" icon="bell">
    Find tweets for push notification recommendations
  </Card>

  <Card title="Search" icon="magnifying-glass">
    Supplement search results with recommended content
  </Card>

  <Card title="Explore" icon="compass">
    Power content discovery in Explore tab
  </Card>
</CardGroup>

## Integration Pattern

Services integrate with CR-Mixer to fetch mixed candidates:

```scala theme={null}
// Example: Fetching candidates from CR-Mixer
val crMixerRequest = CrMixerRequest(
  userId = targetUserId,
  product = ProductType.Home,
  maxResults = 500,
  excludedTweetIds = previouslySeenTweets
)

val candidates = crMixerClient.getCandidates(crMixerRequest)
```

<Note>
  CR-Mixer acts as an intermediary between high-level product surfaces (Home, Notifications) and low-level candidate sources, simplifying the integration complexity.
</Note>

## Signal Extraction

CR-Mixer extracts various signals to inform candidate generation:

### User Signals

* Recent engagements (likes, retweets, replies)
* Follow graph and interests
* Search history and browsing patterns
* Language and location preferences

### Context Signals

* Time of day and day of week
* Device type and platform
* Current trends and topics
* Real-time events

## Candidate Sources

CR-Mixer coordinates fetching from multiple candidate sources:

* **Social Graph** - Tweets from followed accounts
* **User Tweet Entity Graph (UTEG)** - Graph-based recommendations
* **Topic-based Sources** - Content matching user interests
* **Collaborative Filtering** - Similar user recommendations
* **Trend-based Sources** - Trending and viral content

## Filtering Layer

Common filtering logic applied across all use cases:

```scala theme={null}
// Deduplication
val dedupedCandidates = candidates.distinctBy(_.tweetId)

// Pre-ranking filters
val filtered = dedupedCandidates
  .filter(isNotBlocked)
  .filter(isNotMuted)
  .filter(meetsQualityThreshold)
  .filter(isNotPreviouslySeen)
```

## Light Ranking

Before sending candidates to heavy ML rankers, CR-Mixer applies light ranking:

* **Heuristic scores** based on recency, engagement velocity
* **Simple ML models** with low latency
* **Rule-based boosting** for certain content types
* **Diversity scoring** to ensure variety

<Warning>
  Light ranking must maintain low latency (p99 \< 50ms) to avoid blocking the overall recommendation pipeline.
</Warning>

## Benefits

### For Engineers

* Faster experimentation with new candidate sources
* Centralized configuration and monitoring
* Reduced integration complexity
* Shared infrastructure and best practices

### For Users

* More relevant recommendations through better candidate mixing
* Fresher content from faster iteration cycles
* Better diversity through multi-source blending

## Related Services

* [Home Mixer](/services/home-mixer) - Uses CR-Mixer for tweet candidates
* [Pushservice](/services/pushservice) - Uses CR-Mixer for notification candidates
* [Follow Recommendations Service](/services/follow-recommendations) - Complementary user recommendations
* [Timeline Ranker](/services/timelineranker) - Provides ranked candidates from search index