How Posts Actually Get Scored
Phoenix predicts probabilities for many actions — not one relevance score
The Scoring Model
Phoenix doesn't produce a single "relevance score." It predicts the probability that you'll take each of several specific actions on a post:
| Action | Weight (as of 2026-08-14) | What it means |
|---|---|---|
| Favorite | 0.5 | You'll like the post |
| Reply | 5.0 | You'll reply to the post |
| Retweet | 1.0 | You'll repost it |
| Quote | 5.0 | You'll quote it |
| Share (via DM) | 5.0 | You'll DM it to someone |
| Share (via copy link) | 20.0 | You'll copy the link |
| Profile click | 0.0 | You'll click the author's profile |
| Follow author | 4.0 | You'll follow the author |
| Dwell time | 0.0 | How long you spend on the post |
| Not interested | -43.2 | You'll mark "not interested" |
| Block author | -31.2 | You'll block the author |
| Mute author | -58.8 | You'll mute the author |
| Report | -234.0 | You'll report the post |
The Final Score
A weighted sum of these predicted probabilities produces the final ranking score:
score = Σ (weight_i × P(action_i))Critical Correction (Aug 14, 2026)
The repo explicitly warns: these weights multiply predicted probabilities, not raw engagement counts. It's incorrect to say "1 report cancels out 468 likes" — the weights scale *your predicted likelihood* of each action, not the count of actions taken.
The baseline probability of a Report is more than 1000x lower than a Like, so it's weighted heavily to ensure the prediction can actually affect ranking. But a report from a bad actor primarily affects recommendations for users *similar to that bad actor*, not the post's ranking for everyone.
Check Your Understanding
1. What does Phoenix predict for each post?
- A. A single relevance score
- B. Probabilities for many separate actions✓ correct
- C. A sentiment score
- D. A quality rating
Why: Phoenix predicts the probability of each action (favorite, reply, repost, quote, dwell, block, report, etc.) — not one score.
2. What is the base weight of a Reply vs a Favorite?
- A. Reply is 2x a Favorite
- B. Reply is 10x a Favorite (5.0 vs 0.5)✓ correct
- C. They are equal
- D. Reply is 100x a Favorite
Why: ReplyWeight = 5.0, FavoriteWeight = 0.5 — a reply is weighted 10x a favorite in the base config.
3. Is it correct to say "1 report cancels out 468 likes"?
- A. Yes, that's exactly right
- B. No — weights multiply predicted probabilities, not raw counts✓ correct
- C. Only for verified accounts
- D. It depends on the time of day
Why: The repo explicitly warns against this interpretation. Weights scale predicted probabilities, not raw engagement counts.
Exercise
Look at your last 5 posts. Which ones got replies vs only likes? The ones with replies were weighted ~10x higher in your followers' feeds. This is why reply-bait works.
Hint: A post that gets 10 likes and 0 replies scores lower than a post that gets 2 likes and 1 reply.