Setlist prediction — 2026-10-04
Jim Whelan Boardwalk Hall · Atlantic City · Summer Tour 2026 · based on 2005 prior shows · 0 recently-played songs rotation-suppressed · model v3.4.1 · actual setlist known
Predicted vs. actual
Predicted
Set 1: David Bowie [10:44] ★19% · The Moma Dance [8:38] ★19% · Runaway Jim [7:38] ★24% · Cities [16:17] ★49% · Leaves [10:29] · Reba [12:39] ★24% · Hey Stranger [9:00] ★24% · Bouncing Around the Room [3:48]
Set 2: My Friend, My Friend [11:37] ★52% · Tweezer [11:22] ★56% · Down with Disease [15:48] ★40% · Pillow Jets [9:37] ★43% · Light [14:43] ★25% · Also Sprach Zarathustra [7:25] · More [5:11]
Encore: Slave to the Traffic Light [9:24] · Tweezer Reprise [3:21]
Actual — Jim Whelan Boardwalk Hall
Set 1: David Bowie [13:31], The Moma Dance [20:16], Sigma Oasis [14:30], Blaze On [12:51], Halley's Comet [11:54], Wilson [4:14], The Squirming Coil [8:27]
Set 2: Split Open and Melt [14:22], No Men In No Man's Land [17:16], Simple [30:43], Lonely Trip [6:31], You Enjoy Myself [25:15]
Score vs. what they actually played
Each of these is rare on its own — the percentage is measured over the last 60 shows, so it says how unusual the call was rather than just congratulating you.
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 came out -18.6%: the model did worse than the baseline, i.e. its cleverness actively cost it against simply guessing the hits. Difficulty is the average rarity of the songs they actually played (2.99 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 | 11.8% | Of what it predicted, how much got played | |
| recall | 15.4% | Of what got played, how much it predicted | |
| f1 | 13.3% | Harmonic mean of the two | |
| precision (rarity-weighted) | 11.6% | Precision, weighted by how rare each song is | |
| recall (rarity-weighted) | 14.8% | Recall, weighted by how rare each song is | |
| top5 hit rate | 20.0% | Of the top-5 shortlist, how much got played |
17 songs predicted, 13 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 | 1 of 14 predicted |
| Adjacent pairs actually played | 10 |
| Longest correct run | 2 songs |
Getting two songs adjacent in the right order is much harder than getting both somewhere in the show.
Structure
| Set | Predicted | Actual |
|---|---|---|
| Set 1 | 8 | 7 |
| Set 2 | 7 | 5 |
| Encore | 2 | 1 |
| Total | 17 | 13 |
Biggest win
The rarest song it called correctly — 3.132 bits (common). Right set, too.
Biggest miss
The rarest song it didn't see coming — 3.609 bits (uncommon).
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 | 2 | 0 | 0.0% |
|
| common | 9 | 2 | 22.2% |
|
| uncommon | 2 | 0 | 0.0% |
|
| rare | 0 | 0 | — | |
| bustout | 0 | 0 | — |
Song by song
Everything they played, rarest first.
| Song | Rarity | Tier | Called? | Right set? | Credit |
|---|---|---|---|---|---|
| The Squirming Coil | 3.609 bits | uncommon | miss | — | 0.0 |
| Lonely Trip | 3.582 bits | uncommon | miss | — | 0.0 |
| Halley's Comet | 3.398 bits | common | miss | — | 0.0 |
| Wilson | 3.382 bits | common | miss | — | 0.0 |
| David Bowie | 3.132 bits | common | hit | yes | 1.0 |
| Simple | 3.063 bits | common | miss | — | 0.0 |
| Split Open and Melt | 3.02 bits | common | miss | — | 0.0 |
| You Enjoy Myself | 2.925 bits | common | miss | — | 0.0 |
| No Men In No Man's Land | 2.658 bits | common | miss | — | 0.0 |
| The Moma Dance | 2.62 bits | common | hit | yes | 0.843 |
| Sigma Oasis | 2.577 bits | common | miss | — | 0.0 |
| Blaze On | 2.468 bits | staple | miss | — | 0.0 |
| Carini | 2.434 bits | staple | 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 v3.4.1 · scored by v3.4.1 rules.
Top 5 most likely songs
- Tweezer + Tweezer Reprisein heavy recent rotation; played on this date before; gap 1 (usual ~5)
- Also Sprach Zarathustrain heavy recent rotation; due back by gap; gap 8 (usual ~4)
- Runaway Jimdue back by gap; in heavy recent rotation; gap 9 (usual ~5)
- David Bowiein heavy recent rotation; due back by gap; gap 9 (usual ~6)
- Rebain heavy recent rotation; due back by gap; gap 9 (usual ~7)
Predicted full setlist
Set 1: David Bowie [10:44] · The Moma Dance [8:38] · Runaway Jim [7:38] · Cities [16:17] · Leaves [10:29] · Reba [12:39] · Hey Stranger [9:00] · Bouncing Around the Room [3:48]
Set 2: My Friend, My Friend [11:37] · Tweezer [11:22] · Down with Disease [15:48] · Pillow Jets [9:37] · Light [14:43] · Also Sprach Zarathustra [7:25] · More [5:11]
Encore: Slave to the Traffic Light [9:24] · Tweezer Reprise [3:21]
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) |
|---|---|---|---|---|
| David Bowie | Set 1 | 10:44 | 0:49 – 13:11 |
18.7%
|
| The Moma Dance | Set 1 | 8:38 | 7:07 – 11:41 |
19.4%
|
| Runaway Jim | Set 1 | 7:38 | 6:56 – 12:18 |
24.1%
|
| Cities | Set 1 | 16:17 | 6:12 – 19:05 |
48.7%
|
| Leaves | Set 1 | 10:29 | 7:26 – 16:41 |
10.2%
|
| Reba | Set 1 | 12:39 | 11:40 – 13:44 |
23.7%
|
| Hey Stranger | Set 1 | 9:00 | 7:09 – 10:26 |
24.0%
|
| Bouncing Around the Room | Set 1 | 3:48 | 3:38 – 14:40 |
2.4%
|
| My Friend, My Friend | Set 2 | 11:37 | 7:26 – 17:12 |
51.7%
|
| Tweezer | Set 2 | 11:22 | 2:27 – 30:31 |
55.9%
|
| Down with Disease | Set 2 | 15:48 | 1:28 – 34:14 |
40.5%
|
| Pillow Jets | Set 2 | 9:37 | 7:07 – 13:25 |
43.5%
|
| Light | Set 2 | 14:43 | 9:05 – 18:04 |
25.0%
|
| Also Sprach Zarathustra | Set 2 | 7:25 | 5:58 – 11:44 |
14.3%
|
| More | Set 2 | 5:11 | 3:28 – 6:25 |
7.7%
|
| Slave to the Traffic Light | Encore | 9:24 | 8:34 – 10:37 |
6.0%
|
| Tweezer Reprise | Encore | 3:21 | 2:49 – 5:36 |
3.3%
|
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 →