Experiment #174 · closed · published 7/22/2026, 3:37:00 PM
Creative features
Confounds the baseline knew
Raw views mostly measure how big the channel already was. The baseline predicts what this channel “should” have earned given the confounds above; the residual is how the post actually landed relative to that prediction — measured in standard deviations.
Observed (168h)
186
Baseline expected
168
Residual reward
+0.17σ
raw 0.17σ · residual sd 0.599 log-views
| Checkpoint | Views | Watch time (min) | Comments | Likes | Follower delta |
|---|---|---|---|---|---|
| 168h (close) | 186 | 2,604 | 1 | 9 | 0 |
| 24h | 102 | 1,432 | 0 | 5 | 0 |
| 72h | 149 | 2,083 | 1 | 7 | 0 |
Post beat its baseline by 0.17σ. Moved: topic_cluster:topic_1 +0.000, format:shorts +0.000, hook_type:question +0.000.