Backcheck
Pick club
Motion-blurred skater in a gold and black sweater
← Thu, Feb 26 · the slate
Breakdown · CBJ at BOS

Bruins hold off the Blue Jackets

FinalThu, Feb 26
CBJColumbus Blue Jackets2BOSBoston Bruins4
The verdict · stolen

The Bruins stole one. They lost the expected-goals battle 4.66–3.86 and won anyway.

CBJ 2 · BOS 4
◆ By the ModelSep 21, 10:36 AMxG: xgboost-0.758Raw model copyDrafted from NHL play-by-play by Backcheck's model. Nobody at Backcheck was at the rink. How this works

The Bruins beat the Blue Jackets 4-2 in a game the underlying numbers called close to even — expected goals split 3.86–4.66, a slight edge to the Blue Jackets.

The numbers behind the result. The Bruins held 36% of shot attempts (23–40 on goal). Expected goals finished 3.86–4.66 (45–55% split), and high-danger chances went 4–2.

Variance watch. The Blue Jackets underperformed their xG by 2.66 goals.

Turning point. Viktor Arvidsson's snap shot from the point (P3, 19:27).

Goaltending

  • E. Merzlikins (CBJ): 19/22 saves, 0.864 SV% (+0.86 vs expected)
  • J. Korpisalo (BOS): 36/38 saves, 0.947 SV% (+2.42 vs expected)
  • M. DiPietro (BOS): 2/2 saves, 1.000 SV%

Storylines

  • CBJ generated higher-quality looks than the shot total suggests.
  • J. Korpisalo (BOS) stopped 2.4 goals above expected.
  • BOS was lethal off the rush — 2 goals on 27 rush chances.
  • CBJ was lethal off the rush — 2 goals on 34 rush chances.
  • BOS created 3 rebound opportunities (0 converted) — crashing the net effectively.
  • CBJ created 6 rebound opportunities (0 converted) — crashing the net effectively.
  • CBJ underperformed xG by 2.7 — wasted quality chances.
  • J. Korpisalo (BOS) saved 2.7 goals above expected — stole the show.
  • M. DiPietro (BOS) saved 4.7 goals above expected — stole the show.

Final: CBJ 2 – BOS 4

Data: NHL API, MoneyPuck xG model

The breakdown in twelve frames

Swipe it

Every number is from this page
Final · Feb 26
CBJ
2
BOS
4

Bruins hold off the Blue Jackets

Chances 4.7 – 3.9Did they deserve it? →
Did they deserve it?

The Blue Jackets deserved better.

Expected goals · chance value
CBJ
4.66
BOS
3.86
55% of the chances45%

The board read CBJ 2, BOS 4. The chances read CBJ 4.7, BOS 3.9.

Our xG model · NHL play-by-play · all situations
Luck check
BOS
+0.1
goals above expected
BOS3.86 expected · 4 scored
Expected
Scored
CBJ4.66 expected · 2 scored
Expected
Scored

The Blue Jackets left 2.7 goals on the table against what their chances were worth.

PDO = sh% + sv% · drifts to 1.000 over a season
Every goal, in order
  1. P1 04:32CBJK. Marchenko1–0
  2. P1 15:51BOSV. Arvidsson1–1
  3. P2 06:54BOSM. GeekiePP1–2
  4. P3 11:15BOSS. Kuraly1–3
  5. P3 13:45CBJA. Fantilli2–3
  6. P3 19:27BOSV. ArvidssonEN2–4
NHL play-by-play · chance value from our xG model
Where the shots came from
CBJ
55 shots
2
Final
97 shots
BOS
42 shots
4
CBJ attackBOS attack
CBJ BOS Goal
55
shots · 2 in
42
shots · 4 in
Every unblocked shot · press play to replay it
Chances by danger
CBJBOS
0 / 2
0.44 xG
High danger
1 / 4
1.24 xG
1 / 28
3.53 xG
Medium
2 / 17
2.07 xG
1 / 47
0.68 xG
Low
1 / 37
0.55 xG

High-danger looks: CBJ 0 of 2, BOS 1 of 4.

Danger tiers by our xG model · high ≥ 20% chance
In the net
A+
M. DiPietro
+4.7
BOS · 2/2
A+
J. Korpisalo
+2.7
BOS · 36/38
+1 more on the full breakdown
Report card
CBJBOS
OffenseA+A-
DefenseFF
TransitionA-D-
Special teamsD-B
GoaltendingBA+
DisciplineDB
LuckD-A+
Seven dimensions, A+ to F · basis on the breakdown
Why it went the way it went
Why BOS won
  1. 01J. Korpisalo stole it
  2. 02Dangerous off the rush
  3. 03Power play cashed in
Why CBJ lost
  1. 01Cold finishing night
  2. 02Rush defense leaked all night
  3. 03Paraded to the penalty box
Our storyline model · reasoning on the breakdown
The numbers, checked
BACKCHECK

Bruins hold off the Blue Jackets

A model, not a newsroom. Every number on these frames comes from the NHL's play-by-play and our own models. Nothing was watched, guessed or heard from anyone.

Read the full breakdown
backcheckreport.com
01 / 10 · Final
Every goal, in order

How it happened

NHL play-by-play
1stshots 20–10
  1. 04:32CBJK. Marchenko(M. Marchment, A. Fantilli)1–0
  2. 15:51BOSV. Arvidsson(J. Aspirot)1–1
2ndshots 9–8
  1. 06:54BOSM. Geekiepower play(D. Pastrnak, E. Lindholm)1–2
3rdshots 11–5
  1. 11:15BOSS. Kuraly(T. Jeannot)1–3
  2. 13:45CBJA. Fantilli(M. Marchment, Z. Werenski)2–3
  3. 19:27BOSV. Arvidssonempty net(C. McAvoy, C. Mittelstadt)2–4

score reads CBJ–BOS

Source · NHL play-by-play (api-web.nhle.com)
Process vs result

The numbers

XGBoost xG · NHL play-by-play
3.86
BOS chances
Goals their shots were worth
+0.1
Finishing
Goals above what those chances were worth
1.043
BOS puck luck
Above 1.000 — the bounces went their way
43.0%
Shot attempts
Under half — they were outshot
Split by club

Who controlled the game

4.66Expected goals3.86
CBJ 55% of the chance quality
40Shots on goal23
2High-danger chances4
77All attempts (Corsi)58
Adjusted for score: CBJ 58% · BOS 42%
Faceoffs · BOS won50%off69%neu61%def
Source · NHL play-by-play · XGBoost xG
How the game was won

The danger ladder

shotsgoalsexpected
High dangerslot & crease
CBJ0 / 2 · 0.44 xG
BOS1 / 4 · 1.24 xG
Medium dangermid-range
CBJ1 / 28 · 3.53 xG
BOS2 / 17 · 2.07 xG
Low dangerperimeter & point
CBJ1 / 47 · 0.68 xG
BOS1 / 37 · 0.55 xG

CBJ went 1-for-28 from medium danger on 3.53 expected goals — 2.5 left on the table.

Source · Backcheck xG model · NHL play-by-play
The luck layer

Finishing vs expected

expectedactual
CBJ
2 G · 4.66 xG · -2.7
BOS
4 G · 3.86 xG · +0.1
012345

CBJ finished -2.7 against expected, BOS +0.1.

Source · Backcheck xG model
Shot types · rush and rebound chancesopen +
What they shot — and what went in

Shot diet

goalsshots
CBJ
WRIST0/34
SNAP2/7
BACKHAND0/6
SLAP0/2
TIP IN0/4
WRAP AROUND0/1
DEFLECTED0/1
OTHER0/22
BOS
WRIST0/24
SNAP2/8
BACKHAND0/2
SLAP2/6
TIP IN0/2
WRAP AROUND0/0
DEFLECTED0/0
OTHER0/16
CBJ
BOS
Off the rush
2 G on 34
3.16 xG
2 G on 27
2.01 xG
Off rebounds
0 G on 6
0.80 xG
0 G on 3
0.46 xG

Wrist shots carried the volume: CBJ went 0-for-34, BOS 0-for-24. CBJ scored 2 of theirs off the rush.

Source · Backcheck xG model · NHL shot types
New to these numbers?

Two things happened in this game: who created the better chances, and who put the puck in the net. They are not the same thing, and this page separates them on purpose.

The one to watch is expected goals— the best single read on who deserved to win. When it disagrees with the scoreboard, that disagreement is usually the story. Nothing here is a projection; every figure is computed from this game's play-by-play. Full glossary →

xG
Expected goals. Every shot scored by how often that exact look goes in. 2.5 xG means the chances were worth about two and a half goals.
HD
High-danger chances — shots from the slot and the crease, where shots actually become goals.
Corsi
Every shot attempt, including the ones that missed or got blocked. A rough read on who had the puck.
Adj.
Score-adjusted. Teams that trail shoot more and teams that lead sit back, so this corrects the attempt count for the scoreboard.
GSAx
Goals saved above expected. A positive number means the goalie stopped more than an average goalie would have on those shots.
PDO
Shooting % plus save % — a luck gauge. It sits near 1.000 over a season, so a game far from it usually means the bounces decided it.
Shot by shot

In the net

Graded on goals saved above expected
E. Merzlikins
CBJ · 19/22 · .864
+0.9
saved above expected
B+
the night
By dangerG/attxGsaved
High danger1/41.2+0.2
Medium2/172.1+0.1
Low1/370.6-0.5

A+ ≥ +2.5 saved above expected · A ≥ +1.5 · B+ ≥ +0.75 · B ≥ +0.25 · C ≥ −0.25 · D ≥ −0.75 · F below −1.5

J. Korpisalo
BOS · 36/38 · .947
+2.7
saved above expected
A+
the night
By dangerG/attxGsaved
High danger0/20.4+0.4
Medium1/283.5+2.5
Low1/470.7-0.3

A+ ≥ +2.5 saved above expected · A ≥ +1.5 · B+ ≥ +0.75 · B ≥ +0.25 · C ≥ −0.25 · D ≥ −0.75 · F below −1.5

M. DiPietro
BOS · 2/2 · 1.000
+4.7
saved above expected
A+
the night
By dangerG/attxGsaved
High danger0/20.4+0.4
Medium1/283.5+2.5
Low1/470.7-0.3

A+ ≥ +2.5 saved above expected · A ≥ +1.5 · B+ ≥ +0.75 · B ≥ +0.25 · C ≥ −0.25 · D ≥ −0.75 · F below −1.5

Graded against a league-average game

Report card

Seven dimensions · A+ to F
DimensionCBJBOS
Offense
▸Basis

CBJ Created 4.66 xG against a ~2.70 league-average game; 2 high-danger shots (0.44 xG) and 34 rush shots (3.16 xG).

BOS Created 3.86 xG against a ~2.70 league-average game; 4 high-danger shots (1.24 xG) and 27 rush shots (2.01 xG).

A+
100
A-
92
Defense
▸Basis

CBJ Allowed 3.86 xG against a ~2.70 league-average game; conceded 4 high-danger shots (1.24 xG) and 27 rush shots (2.01 xG).

BOS Allowed 4.66 xG against a ~2.70 league-average game; conceded 2 high-danger shots (0.44 xG) and 34 rush shots (3.16 xG).

F
58
F
48
Transition
▸Basis

CBJ Rush shots 34–27, rush xG 3.16–2.01 (rush-based; public data has no zone entries).

BOS Rush shots 27–34, rush xG 2.01–3.16 (rush-based; public data has no zone entries).

A-
90
D-
60
Special teams
▸Basis

CBJ 0-for-1 on the power play (0%; league ≈21%) with 0.33 PP xG.

BOS 1-for-3 on the power play (33%; league ≈21%) with 0.26 PP xG.

D-
61
B
85
Goaltending
▸Basis

CBJ +0.86 goals saved above expected on 22 shots against.

BOS +2.66 goals saved above expected on 40 shots against.

B
84
A+
100
Discipline
▸Basis

CBJ Took 3 penalties for 6 PIM vs 1 for 2 on the other side.

BOS Took 1 penalties for 2 PIM vs 3 for 6 on the other side.

D
65
B
85
Luck

Grades bounces, not skill — C is neutral

▸Basis

CBJ Finishing -2.66 goals vs xG plus +0.86 GSAx of save luck = -1.80 total. This grades luck, not skill — C is neutral, A is very lucky.

BOS Finishing +0.14 goals vs xG plus +2.66 GSAx of save luck = +2.80 total. This grades luck, not skill — C is neutral, A is very lucky.

D-
61
A+
97
Source · NHL play-by-play · xG engine · luck graded separately
What the model flagged
WARNINGBOS

Rush defense leaked all night

Gave up 34 rush shots worth 3.16 xG (2 goals) — transition gaps were there every period.

Tighten neutral-zone structure and keep D gaps closed on entries.

STRENGTHBOS

J. Korpisalo stole it

J. Korpisalo stopped 36 of 38 (0.947) — +2.42 goals saved above expected in a 2-goal game.

STRENGTHCBJ

Dangerous off the rush

2 goals on 34 rush shots worth 3.16 xG.

LUCKCBJ

Cold finishing night

Scored 2 on 4.66 xG — -2.66 vs expected. The looks were there; the finish will come back.

WARNINGCBJ

Rush defense leaked all night

Gave up 27 rush shots worth 2.01 xG (2 goals) — transition gaps were there every period.

Tighten neutral-zone structure and keep D gaps closed on entries.

STRENGTHBOS

Dangerous off the rush

2 goals on 27 rush shots worth 2.01 xG.

97 shots · press play to watch the game back

Where the shots came from

NHL play-by-play coordinates
CBJ
55 shots
2
Final
97 shots
BOS
42 shots
4
CBJ attackBOS attack
CBJ BOS Goal

Each club shoots toward its own end — CBJ left, BOS right — the way you would watch it. A dot's size is how dangerous the look was, from distance and angle; it is a proxy for shot quality, not the xG model the article is written from. Hover a dot for the shooter and the clock.

Ranked from the box score

Three stars

Points first
Three stars · computed, not voted
A. Fantilli
#19 · C · CBJ
1 G · 1 A · 5 SOG · 19:09 on ice
M. Marchment
#17 · L · CBJ
0 G · 2 A · 0 SOG · 18:32 on ice
V. Arvidsson
#71 · L · BOS
2 G · 0 A · 3 SOG · 14:29 on ice · +1
Ranked from the box score — points first · Backcheck
What the model said beforehand

Before the game

Written Thu, Feb 26
Open the pre-game read
Written from the numbers

The read

Edited for clarity
◆ By the ModelJul 12, 4:30 AMEdited for clarityDrafted from NHL play-by-play by Backcheck's model, worded for clarity by an AI editor that may not change a number. Nobody at Backcheck was at the rink. How this works

The model projects a 2.6-2.5 Columbus victory with the Blue Jackets at 52% win probability—about as close to a pick'em as you'll find.

Columbus dominates the underlying play. At 5v5, the Blue Jackets out-shoot Boston 52.0% to 47.0% by expected goals and lead 51.0% to 49.0% in Corsi. That edge at the mechanics level is significant. But the Bruins are running hot on a PDO of 1.023; Boston should expect some regression. Columbus, at 1.003, sits much closer to league average.

The offense reveals where the teams diverge. Boone Jenner leads Columbus at 0.98 xG/60 with 11 goals, 21 assists, and 2 high-danger goals. Mathieu Olivier adds 0.89 xG/60, 12 goals, 9 assists, and 1 high-danger goal. Viktor Arvidsson, at 1.04 xG/60, matches Jenner's offensive profile but converts more efficiently—18 goals, 24 assists, and 2 high-danger goals. Tanner Jeannot, at 0.75 xG/60, posts 6 goals, 14 assists, and 2 high-danger goals.

Neither team has unlocked deep scoring from difficult areas. Columbus has converted at 0% from high-danger chances and 0% from rebounds this season; Boston's conversion rates sit at 0% as well. That cannot persist through a full game. Whoever catches the first bounce gains real leverage.

Shooting rates show a gap between output and underlying play. Jenner's 9.6% and Olivier's 13.3% suggest Columbus may be underperforming its volume. Arvidsson's 13.0% and Jeannot's 8.3% reveal more equilibrium on Boston's side. In a true pick'em, that variance becomes the deciding variable.

Defensively, Conor Garland represents a liability for Columbus, while Elias Lindholm does the same for Boston. Minimize that gap, win the game.

What the model said beforehand

The model's lean

CBJ 52%
52%
CBJ
Model favorite
52%
48%
CBJ50BOS

CBJ by 4 points of win probability — effectively a coin flip. Projected score CBJ 2.6–2.5 BOS; 18% chance it's tied after 60.

Source · Backcheck Poisson projection · season scoring rates
Season rates · 5v5

Tale of the tape

NHL stats API · our xG
CBJ← edge
edge →BOS
52.0%47.0%
51.0%49.0%
2.632.39
2.432.67
2.122.22
1.981.82
1.0031.023

CBJ holds 4 of 6 process categories — and the luck row (1.003 vs 1.023) says BOS has been getting the bounces, which tends not to last.

Source · NHL stats API + our xG · 5v5
Form · Last 10
CBJ
9-1-0
+18 GD · 21d rest
BOS
6-1-3
+4 GD · 21d rest
1.003
CBJ PDO
Luck gauge · drifts to 1.000
1.023
BOS PDO
Luck gauge · drifts to 1.000
What decides it

Keys to the game

Where the edges live
  • The Blue Jackets own the underlying play — 52.0% 5v5 xG vs 47.0%.
Regression watch
  • The Bruins' PDO is 1.023 — running hot, expect some regression.
Things to watch
  • The Blue Jackets own the underlying play — 52.0% 5v5 xG vs 47.0%.
  • The Bruins' PDO is 1.023 — running hot, expect some regression.
Last game's lineup · confirmed at warm-up

Lineups

NHL box score
CBJ
Expected in goal
J. Greaves
21 days rest1.000 last start
Backup Jet Greaves · +16.5 GSAx this season

No completed game on file for this club yet.

BOS
Expected in goal
J. Korpisalo
21 days rest.846 last start
Backup Jeremy Swayman · +28.8 GSAx this season

No completed game on file for this club yet.

Lineups are the players who dressed in each club's last game, with their minutes; clubs confirm tonight's at warm-up. Every player this preview names was in that lineup.

Computed danger · scouting

Players to watch

NHL stats API · our xG
CBJ
Boone Jenner11G 21A
0.98 xG/60 · 2 HD · 9.6% sh
Mathieu Olivier12G 9A
0.89 xG/60 · 1 HD · 13.3% sh
BOS
Viktor Arvidsson18G 24A
1.04 xG/60 · 2 HD · 13.0% sh
Tanner Jeannot6G 14A
0.75 xG/60 · 2 HD · 8.3% sh
Keep going

Where to next

Back to the front page