Setlist prediction — 2026-07-18
Merriweather Post Pavilion · Columbia · based on 1988 prior shows · 46 recently-played songs rotation-suppressed · model v3.0.0 · actual setlist known
Predicted vs. actual
Predicted
Set 1: Cars Trucks Buses [5:37] · The Moma Dance [8:43] ★21% · Back on the Train [8:17] · Axilla (Part II) [6:19] ★23% · Funky Bitch [6:45] · No Men In No Man's Land [10:09] · Tube [8:09] ★23% · Reba [12:41] · Chalk Dust Torture [9:38] ★31%
Set 2: Oblivion [15:02] ★31% · Down with Disease [16:11] ★39% · Ruby Waves [16:13] ★52% · Lonely Trip [6:41] · Possum [9:04] · What's the Use? [7:08] · Everything's Right [13:08] ★26%
Encore: A Life Beyond The Dream [7:54] · First Tube [7:10]
Actual — MERRIWEATHER POST PAVILION
Set 1: What's Going Through Your Mind [13:42], Contact [9:59], You Enjoy Myself [17:17] > Axilla (Part II) [11:47] -> McGrupp and the Watchful Hosemasters -> Have Mercy [3:15] > McGrupp and the Watchful Hosemasters > Shade [4:11], Runaway Jim [12:13]
Set 2: Life Saving Gun [24:23] > Gotta Jibboo [12:09] -> Ether Edge [14:04] > Lifeboy [6:24], Boogie On Reggae Woman [8:05] > Free [9:35]
Encore: Monsters [7:28], If I Could [5:43], Run Like an Antelope [9:42]
Score vs. what they actually played
The raw score is graded against a perfect setlist call, which never happens. Phish rotate deliberately and go out of their way to be unpredictable, so 100 is unreachable — over the last 60 shows the score runs from about 2 to 42.09, with a median near 19.3. That is why the headline ranks this night against the ones actually achieved rather than against an imaginary ceiling. The number that means something is Skill: how much of the headroom above a baseline that just guesses the most-played songs this prediction captured. 0% is “no better than guessing the hits”; anything above it is real signal. On this night it captured 4.7% of that headroom. Difficulty is the average rarity of the songs they actually played (4.16 bits) — a night of deep cuts scores lower for the same skill, which is why the headline is normalised against a perfect prediction of this show.
Sub-scores
Each is out of 100 and rarity-weighted: picking the song at all earns the most, putting it in the right set earns more, landing it near the right slot earns the rest.
Precision & recall
| Metric | Value | What it means | |
|---|---|---|---|
| precision | 5.6% | Of what it predicted, how much got played | |
| recall | 5.9% | Of what got played, how much it predicted | |
| f1 | 5.7% | Harmonic mean of the two | |
| precision (rarity-weighted) | 6.5% | Precision, weighted by how rare each song is | |
| recall (rarity-weighted) | 5.0% | Recall, weighted by how rare each song is | |
| top5 hit rate | 0.0% | Of the top-5 shortlist, how much got played |
18 songs predicted, 17 played. The rarity-weighted variants are the interesting ones: calling a warhorse is easy, calling a bustout is not, and the weighted numbers pay out accordingly.
Sequence
| Adjacent pairs called right | 0 of 15 predicted |
| Adjacent pairs actually played | 15 |
| Longest correct run | 1 song |
Getting two songs adjacent in the right order is much harder than getting both somewhere in the show.
Structure
| Set | Predicted | Actual |
|---|---|---|
| Set 1 | 9 | 9 |
| Set 2 | 7 | 6 |
| Encore | 2 | 3 |
| Total | 18 | 18 |
Biggest win
The rarest song it called correctly — 3.511 bits (uncommon). Right set, too.
Biggest miss
The rarest song it didn't see coming — 8.702 bits (bustout).
By rarity
How it did across rarity bands. The warhorses are supposed to be easy; the deep cuts are where a model earns its keep.
| Tier | Played | Called | Hit rate | |
|---|---|---|---|---|
| staple | 0 | 0 | — | |
| common | 7 | 0 | 0.0% |
|
| uncommon | 6 | 1 | 16.7% |
|
| rare | 3 | 0 | 0.0% |
|
| bustout | 1 | 0 | 0.0% |
|
Song by song
Everything they played, rarest first.
| Song | Rarity | Tier | Called? | Right set? | Credit |
|---|---|---|---|---|---|
| Have Mercy | 8.702 bits | bustout | miss | — | 0.0 |
| Contact | 6.996 bits | rare | miss | — | 0.0 |
| If I Could | 5.539 bits | rare | miss | — | 0.0 |
| Lifeboy | 5.091 bits | rare | miss | — | 0.0 |
| McGrupp and the Watchful Hosemasters | 4.607 bits | uncommon | miss | — | 0.0 |
| Shade | 4.367 bits | uncommon | miss | — | 0.0 |
| Ether Edge | 4.018 bits | uncommon | miss | — | 0.0 |
| Boogie On Reggae Woman | 3.962 bits | uncommon | miss | — | 0.0 |
| Gotta Jibboo | 3.822 bits | uncommon | miss | — | 0.0 |
| Axilla (Part II) | 3.511 bits | uncommon | hit | yes | 0.85 |
| Monsters | 3.191 bits | common | miss | — | 0.0 |
| Runaway Jim | 3.142 bits | common | miss | — | 0.0 |
| What's Going Through Your Mind | 2.883 bits | common | miss | — | 0.0 |
| Life Saving Gun | 2.853 bits | common | miss | — | 0.0 |
| You Enjoy Myself | 2.769 bits | common | miss | — | 0.0 |
| Run Like an Antelope | 2.664 bits | common | miss | — | 0.0 |
| Free | 2.533 bits | common | miss | — | 0.0 |
Predicted but not played
Reported, but never subtracted from the headline: penalising bold calls by rarity would teach the model that rare songs are never worth predicting, which is the opposite of what this is for.
Predicted by model v3.0.0 · scored by v3.1.0 rules.
Top 5 most likely songs
- Chalk Dust Torturein heavy recent rotation; due back by gap; gap 7 (usual ~3)
- Possumin heavy recent rotation; due back by gap; gap 6 (usual ~4)
- The Moma Dancein heavy recent rotation; due back by gap; gap 6 (usual ~4)
- First Tubein heavy recent rotation; due back by gap; gap 6 (usual ~4)
- No Men In No Man's Landin heavy recent rotation; due back by gap; gap 6 (usual ~5)
Predicted full setlist
Set 1: Cars Trucks Buses [5:37] · The Moma Dance [8:43] · Back on the Train [8:17] · Axilla (Part II) [6:19] · Funky Bitch [6:45] · No Men In No Man's Land [10:09] · Tube [8:09] · Reba [12:41] · Chalk Dust Torture [9:38]
Set 2: Oblivion [15:02] · Down with Disease [16:11] · Ruby Waves [16:13] · Lonely Trip [6:41] · Possum [9:04] · What's the Use? [7:08] · Everything's Right [13:08]
Encore: A Life Beyond The Dream [7:54] · First Tube [7:10]
Ordering is heuristic (openers/encore placed by role); treat it as a likely song pool with structure, not an exact sequence.
Predicted lengths & jam odds
| Song | Set | Likely length | Range (q10–q90) | P(jam chart) |
|---|---|---|---|---|
| Cars Trucks Buses | Set 1 | 5:37 | 5:29 – 6:09 |
5.7%
|
| The Moma Dance | Set 1 | 8:43 | 7:37 – 12:28 |
20.8%
|
| Back on the Train | Set 1 | 8:17 | 6:48 – 9:05 |
12.0%
|
| Axilla (Part II) | Set 1 | 6:19 | 5:47 – 17:42 |
22.9%
|
| Funky Bitch | Set 1 | 6:45 | 5:58 – 7:59 |
11.1%
|
| No Men In No Man's Land | Set 1 | 10:09 | 7:56 – 13:28 |
12.3%
|
| Tube | Set 1 | 8:09 | 6:13 – 12:04 |
22.7%
|
| Reba | Set 1 | 12:41 | 11:32 – 13:44 |
11.8%
|
| Chalk Dust Torture | Set 1 | 9:38 | 3:18 – 16:35 |
31.3%
|
| Oblivion | Set 2 | 15:02 | 7:27 – 17:39 |
31.1%
|
| Down with Disease | Set 2 | 16:11 | 7:49 – 24:54 |
38.9%
|
| Ruby Waves | Set 2 | 16:13 | 11:40 – 29:51 |
52.0%
|
| Lonely Trip | Set 2 | 6:41 | 6:11 – 8:00 |
5.6%
|
| Possum | Set 2 | 9:04 | 8:01 – 10:16 |
13.8%
|
| What's the Use? | Set 2 | 7:08 | 5:53 – 8:38 |
8.2%
|
| Everything's Right | Set 2 | 13:08 | 9:02 – 16:55 |
26.4%
|
| A Life Beyond The Dream | Encore | 7:54 | 7:10 – 8:19 |
0.9%
|
| First Tube | Encore | 7:10 | 6:29 – 8:03 |
0.8%
|
Lengths are recency-weighted medians conditioned on the set — the q10–q90 band is where the honesty lives. P(jam chart) is the chance curators later flag this version; it is deliberately estimated from curated history only, since the last year of shows hasn't been written up yet.
Bustout watch
Model backtest: top-5 hit rate 39.5%, setlist recall 31.4% over 40 shows. Full scoring history →