Edge Labs EDGE LABS Market intelligence
CFB NFL
← The slate
CFB · Week 2 · Sat, Sep 12 · 3:30 PM ET · Huntington Bank Stadium · FINAL Mississippi State 38, Minnesota 13

Mississippi State at Minnesota. Our picks: Mississippi State -1.5 (low). Under 55.5 (medium).

The picks come first on this page. The market's number, our number and the gap between them sit under them as MODEL CONTEXT: that is the input our analyst panel argued from, not a call of its own. Tiers are how decisively the evidence agreed, never a win probability.

WIN We had Mississippi State -1.5. It cashed.
ATS pick
Mississippi State -1.5
low WIN
locked Thu 1:05pm ET
Mississippi State 38, Minnesota 13
Total pick
Under 55.5
medium WIN
locked 55.5 · closed 53.5
panel 3-0

Panel reasoning

On the spread

Mississippi State at Minnesota, Mississippi State -1.5. The market opened with Minnesota favored by as much as 2.5 points and drifted toward Mississippi State all week; by game week the book split, with some shops still on Minnesota by a point or more and others favoring Mississippi State by a similar margin. Minnesota's backfield took a real hit, with running back Ryan Estrada lost for the season to a knee injury and another back still listed questionable and unresolved. Mississippi State's opener was the more eye-catching of two lopsided wins, with its quarterback throwing for 354 yards and four touchdowns while facing pressure on only a handful of dropbacks. Our own rating model reads this as close to a pick em and carries no lean on the spread either way. Two panels sided with Mississippi State on the injury news and the sharp-side line move; the dissenting panel took Minnesota, arguing Mississippi State's low returning production and negative portal net make this a true toss-up the model is overrating. Take Mississippi State -1.5, best number -1 at Pinnacle.

On the total

Under 55.5. The total opened at 52.5 early in the week and climbed to 55.5 by kickoff, with the under priced slightly better than even at most books. Weather is a non-factor: mild, light wind, no rain in the forecast. Both week one scores were inflated, Minnesota's by two punt-return touchdowns and Mississippi State's by an overmatched Sun Belt opponent it held to thirteen points. Our totals model prints 54.35 against a market near 55.3, a gap well inside its own noise threshold, a soft lean, not a real signal. The counter-case is a healthy Mississippi State passing attack that could push scoring up. Take Under 55.5, best price at FanDuel or BetMGM.

Model context

The numbers the panel argued from. Our models price a game, the panel makes the call, and the picks above are the call. Nothing in this block is a pick.

Locked line
Mississippi State -1.5 · Minnesota +1.5
the spread we locked at, it does not move
Our model number
Mississippi State by 2.1
the calibrated EL CFB rating number, home field included
Spread gap
0.6 points
the distance between our model number and the market. Context for the panel, not a call of its own.
Market total
54.5
consensus of 5 books at the model run, Sep 12, 12:38 PM ET
Our total
53.9
EL CFB Totals v1
Total gap
-0.6
the distance between our model total and the market total. Context for the panel, not a call of its own.

Context, not a call. The spread number is our rating difference plus home field. The totals number is a registered candidate that loses to the closing total: across 2,264 held out games it missed the combined score by 12.862 points on average and the closing total missed by 12.635, ahead of us in all 3 of those seasons, so it never posts to the board and never enters the record on its own.

Over and under splits

Descriptive context on this game, every line with the games it counts. None of it is a reason a pick wins and none of it enters a tier.

  • Early-season total of 53.5 fits the validated under window, unders 55% historically (n=943)
    total · under · moderate · n=943
    H64 (validated): Aug through mid-Sep games with a closing total of 47+ landed under 55% of 943 games, 2015-2025. Recent seasons: 2022: 58% (n=92) · 2023: 53% (n=81) · 2024: 57% (n=103) · 2025: 52% (n=119). 2025 ran soft at 52.1%, below the -110 breakeven, and the 2026 forward test is pre-committed on the early-totals page. Early-season totals are shaded up by public over-action; the market corrects as real form data arrives.
  • Mississippi State games go UNDER 61% on the road (n=62)
    total · under · moderate · n=62
    Multi-season split: Mississippi State on the road landed under 61% of 62 gradable games (2013-2025). A genuine venue tendency, one of several reasons to lean under, not a standalone edge.

The panel

Panel A

Mississippi State +1.5

Under 55.5

Take Mississippi State +1.5, displayed by Action Network on September 10 and consistent with the dossier's DraftKings quote. EL makes State a 2.1-point favorite, nominally a 3.6-point difference, but its validation record does not support treating that as an edge. My lean rests on Taylor's passing-and-running threat and an opener whose offensive production was more substantial than Minnesota's similar scoreboard suggests. State gained 762 yards; Minnesota's 59 points included two punt-return touchdowns. Both faced weak opposition, so substantial regression is necessary. Minnesota's counterarguments are home field, two additional preparation days and Lindsey's ball security. Movement from Minnesota -2.5 toward pick'em already prices some State optimism; inconsistent book directions do not establish a universal sharp-money signal. Estrada's season-ending injury modestly reduces Minnesota's depth, but I assign no speculative adjustment to unconfirmed questionable players. This is a small position, with substantial uncertainty about how State's rebuilt defense translates against better competition.

Total. Under 55.5 is a modest price-based lean. The over case is credible: Taylor produced explosive passing and rushing results, Lindsey opened efficiently, and mild temperatures with limited rain risk should allow normal offense. State's defensive improvement is unproven against stronger opponents. However, Minnesota's two return touchdowns are unlikely to recur, and both offenses now face a substantial competition upgrade. Arnett's arrival creates plausible defensive improvement that a prior-season scoring model misses, although it remains an inference. The dossier's FanDuel total rose from 52.5 to 55.5, leaving a more attractive under entry. EL's 54.35 offers only weak corroboration; its wind deduction is already embedded. I could not verify current neutral-situation pace, so tempo supplies no additional numerical adjustment.

Where our model looks wrong

The final-margin update cannot distinguish Minnesota's two return touchdowns from sustainable offense, while State's large ULM win may exaggerate its improvement. I would shrink the precise State -2.1 assessment toward pick'em. The totals documentation also contradicts its output: it says weather is unseen, yet explicitly subtracts 2.321 points for wind. That adjustment is already included and must not be counted twice. Last year's defensive baseline also misses Zach Arnett's arrival.

Panel B

Minnesota +1.5

Under 55.5

Our number is Mississippi State -2.1, ESPN Analytics has the Bulldogs at 59.9% (ESPN game page, 9/10), and the market has drifted their way all week: DraftKings opened Minnesota -2.5 and sits -1.5, FanDuel opened Minnesota -1.5 and now lays 1.5 with State, Pinnacle has had State -1 since 9/6. Everything points one way, which is why I want the other side at the best price the week has offered. That drift is built on Week 1 box scores: State's record 762 yards came against ULM (hailstate.com, 9/5) and Minnesota's 59-7 included two Javon Tracy punt-return touchdowns (National Football Post, 9/9), so both scores overstate. Underneath, State returns 33.9% production with a -10 portal net and a defense that allowed 30.2 ppg in 2025 under a first-year coordinator; Minnesota returns 64.9%, allowed 22.9, and hosts its first SEC opponent since 1959. Lean home at plus money. Risk: Kamario Taylor is the best player on the field and Minnesota's back-seven has not been tested.

Total. 55.5 is a big number to hang on a Minnesota game. The Gophers averaged 23.0 points for and 22.9 against in 2025 - a 45.9-point average game - and Fleck's teams are among the slowest-paced in the Big Ten, so even against Lebby's tempo Minnesota controls half the possessions and bleeds clock. Both Week 1 explosions came against overmatched opponents (Eastern Illinois, ULM), and Minnesota's 59 was inflated by two punt-return touchdowns and a running clock. Zach Arnett's State defense held ULM to 13 points and 3-of-16 on third down. Our own ridge model prints 54.35 against a 55.3 consensus, and the under is already juiced to -115/-118 at DraftKings, FanDuel and BetMGM, so the market leans the same way. Weather is benign, not a factor. Take 55.5 while it is there.

Where our model looks wrong

Two things. First, a possible convention bug worth checking: raw_margin_home is -1.3 (which under the stated 'negative = home favored' convention reads Minnesota) yet our_number_home comes out +2.1, Mississippi State - the calibration map appears to flip the sign on a near-zero raw margin, which would make gap_points meaningless in exactly the pick'em range this game sits in. Second, the rating is still mostly the preseason prior, and that prior rewards Mississippi State's 4-year blue-chip ratio (.208 vs .121) while ignoring that 33.9% returning production and a -10 portal net mean most of that talent is gone. It also cannot see that Minnesota's 59 points included two punt-return touchdowns, cannot see Estrada's season-ending knee or the thin RB room behind an injury-prone Darius Taylor, and applies a flat 2.5 home field to a stadium hosting its biggest nonconference draw in decades. The honest reading is that this is a pick'em the model has no business calling either way.

Panel C

Mississippi State -1.5

Under 55.5

The market opened with Minnesota favored by up to 2.5 (DraftKings, captured 9/2) and has drifted toward Mississippi State all week; as of 9/10 the book split is basically even-to-MSU-leaning, DraftKings/BetMGM still show Minnesota -1 to -1.5, but Pinnacle (the sharpest book) and FanDuel show Mississippi State -1 to -1.5, a swing independently confirmed by 247Sports' own account of the same move. Two things our model can't see explain it: Minnesota's backfield took a real hit (Estrada out for the season, knee, reported 9/7; Turner questionable, knee, since 9/4, still unresolved), and Mississippi State's week 1 was the more eye-catching of two blowouts, 762 total yards, QB Kamario Taylor 22/34 for 354 and 4 TDs with almost no pressure allowed. Our own rating model reads this as a pick'em after calibration (gap vs market inside its no-lean floor) and carries no proven ATS edge regardless, so I'm leaning on verified injury news and the sharp-side line move rather than the model. Both week 1 wins came against weak competition, which caps my conviction on a genuinely tight number.

Total. Our totals model (54.35) sits modestly under the market (55.3-55.5), but the gap is well inside its own noise band, so this is a soft tiebreaker rather than a real model signal. Weather is a non-factor: mostly sunny, high near 73F, NW wind ~10-12 mph, 0% precipitation chance at kickoff. Both teams' full 2025 scoring (Minnesota 23.0 for/22.9 against; Mississippi State 30.4/30.2, both per game) blends close to the current number, while their 59-7 and 62-13 Week 1 outputs came against an FCS opponent and a clearly weaker Sun Belt program and likely overstate true scoring pace against real competition. Mississippi State's true-sophomore QB was reportedly pressured on nearly half his dropbacks a year ago, and Minnesota's beat coverage frames pass rush against him as the Gophers' specific defensive plan this week; if that pressure shows up, scoring stalls on the side that has driven the total up. Leaning under, lightly.

Where our model looks wrong

The in-season rating after one game is still mostly the preseason prior and has no injury layer at all, so it cannot register that Minnesota's RB2 is done for the year and its RB1 is unresolved-questionable. It also applies a flat 2.5-point home-field bump regardless of roster health, which likely overstates Minnesota's true home edge this week. Separately, the relationship between the model's raw margin (-1.3, home) and its calibrated number (+2.1, home) is hard to square with the underlying ratings (Mississippi State 5.828 vs Minnesota 2.03 post-week-1, favoring the road team), worth Edge Labs double-checking the calibration map's behavior on small in-season samples like this one.

The write-up

The case

Mississippi State at Minnesota, Mississippi State -1.5. The market opened with Minnesota favored by as much as 2.5 points and drifted toward Mississippi State all week; by game week the book split, with some shops still on Minnesota by a point or more and others favoring Mississippi State by a similar margin. Minnesota's backfield took a real hit, with running back Ryan Estrada lost for the season to a knee injury and another back still listed questionable and unresolved. Mississippi State's opener was the more eye-catching of two lopsided wins, with its quarterback throwing for 354 yards and four touchdowns while facing pressure on only a handful of dropbacks. Our own rating model reads this as close to a pick em and carries no lean on the spread either way. Two panels sided with Mississippi State on the injury news and the sharp-side line move; the dissenting panel took Minnesota, arguing Mississippi State's low returning production and negative portal net make this a true toss-up the model is overrating. Take Mississippi State -1.5, best number -1 at Pinnacle.

Confidence: low

Three independent analyst panels (A, B and C) worked the same evidence pack and the week's news independently, each returned a side, and each then ranked its five strongest picks for the week. Two of the three panels were on this side, with the third close behind on the other side. Low is a decisiveness label for how firmly the panel agreed, never a win probability: high means every panel was on this side and ranked it among the week's best; only high picks count on the record and go free.

The total: Under 55.5 (medium)

Under 55.5. The total opened at 52.5 early in the week and climbed to 55.5 by kickoff, with the under priced slightly better than even at most books. Weather is a non-factor: mild, light wind, no rain in the forecast. Both week one scores were inflated, Minnesota's by two punt-return touchdowns and Mississippi State's by an overmatched Sun Belt opponent it held to thirteen points. Our totals model prints 54.35 against a market near 55.3, a gap well inside its own noise threshold, a soft lean, not a real signal. The counter-case is a healthy Mississippi State passing attack that could push scoring up. Take Under 55.5, best price at FanDuel or BetMGM.

Our number

edgelabs EL rating (preseason v1 until a team has played, then the in-season v1 Elo-style refit, Sun 23:00 and Tue 02:00 PT) run through the 2026-09-07 CFB calibration map; home field 2.5. Home perspective: negative = home favored. Ours: Minnesota +2.1; market at synthesis: -0.2. Held-out 2024-2025 reconstructions (9,927 FBS games): 46-50% against the spread in every gap bucket, calibrated margin error 12.7 points. No against-the-spread edge at any gap size. Treat the number as context, not as a priced edge.

written before kickoff, frozen at kickoff

Trends

Descriptive context, every line with the games it counts. Filters like these did not hold up as predictors in our testing, so none of this is in the confidence read and none of it is a reason a pick wins. Situational splits look back 3 seasons and need at least 8 decided games to be shown at all. Records against the number and on the total join these once our closing-line history is restored; the straight-up splits are live now.

Mississippi State
  • won 1 of their last 5 (n=5, 2025 to 2026)
  • 0-8 straight up in home divisional games (n=8, 2024 to 2025)
Minnesota
  • won 3 of their last 5 (n=5, 2025 to 2026)
  • won 3 straight
  • 7-1 straight up in home day games (n=8, 2024 to 2025)
The rest of the splits we can compute on this game
Mississippi State
  • won 2 of their last 10 (n=10, 2025 to 2026)
  • 1-15 straight up in divisional games (n=16, 2024 to 2025)
  • 1-12 straight up in day divisional games (n=13, 2024 to 2025)
  • 1-12 straight up in divisional games after a straight up loss (n=13, 2024 to 2025)
  • 1-7 straight up in road divisional games (n=8, 2024 to 2025)
  • 2-8 straight up in home day games (n=10, 2024 to 2025)
  • 2-8 straight up on the road (n=10, 2024 to 2025)
  • 3-10 straight up in day games after a straight up loss (n=13, 2024 to 2025)
  • 4-12 straight up in day games (n=16, 2024 to 2025)
  • 2-6 straight up on the road after a straight up loss (n=8, 2024 to 2025)
  • 5-14 straight up after a straight up loss (n=19, 2024 to 2026)
  • 3-7 straight up at home after a straight up loss (n=10, 2024 to 2026)
  • 6-9 straight up at home (n=15, 2024 to 2026)
  • 4-6 straight up in night games (n=10, 2024 to 2026)
Minnesota
  • won 6 of their last 10 (n=10, 2025 to 2026)
  • 12-3 straight up at home (n=15, 2024 to 2026)
  • 7-2 straight up in home divisional games (n=9, 2024 to 2025)
  • 7-3 straight up after a straight up loss (n=10, 2024 to 2025)
  • 3-6 straight up on the road (n=9, 2024 to 2025)
  • 10-5 straight up in day games (n=15, 2024 to 2025)
  • 6-3 straight up in divisional games after a straight up loss (n=9, 2024 to 2025)
  • 5-3 straight up in day games after a straight up loss (n=8, 2024 to 2025)
  • 3-5 straight up in road divisional games (n=8, 2024 to 2025)
  • 7-5 straight up in night games (n=12, 2024 to 2026)
  • 10-8 straight up in divisional games (n=18, 2024 to 2025)
  • 6-5 straight up in day divisional games (n=11, 2024 to 2025)

The signals and the work

Members

6 independent signals on this game

The signal tally per side, the totals read, every angle with its sample size, and the line movement from open to now. 3 picks are released free on the slate every week. $24/mo, founder rate.

The two numbers underneath

TeamEL ratingConference
Mississippi State 5.828 SEC
Minnesota 2.03 Big Ten

Rating difference plus 2.5 points of home field is the rating read above. Full board: the power ratings.

Conditions at kickoff

Clear. 72F · wind 14 mph

Provenance: schedule and finals from the Edge Labs database (2026 season); the line is the latest capture for this game with the book named; our number is the EL rating read (in-season once a team has played, preseason before that) plus 2.5 home field, none at neutral sites, and it is context on this page rather than the call. Signals come from the trend engine, each with its real sample; a tier is how decisively the evidence agreed and is never a win probability. Once the game kicks off this page stops computing and reads our pick lock ledger instead: the pick and the spread we were locked at, written once at kickoff, never updated, graded against that same number. Line movement comes from our permanent capture log, one book across both ends and never a capture taken at or after kickoff, so the second number is the last pregame line and after kickoff it is the close; a game the log has captured only once shows no movement rather than an invented one. Weather is the captured forecast for the venue, and the chip appears only when it is worth saying (wind at 12 mph or more, a 50 percent or better chance of rain, or 35F or colder), never on an indoor venue. Injury counts are our latest daily scan, real report rows only, and a team the scan does not cover is left out rather than shown as zero. The write-up is assembled from those same stored rows, never written around them: the case comes from the lock row, the signals from the trend engine with their own samples, the series from our game database from 2013 forward, and the scoring profiles from completed games only, each with the number of games it averages. A section with no data behind it is left out instead of filled in, it refreshes while the game is pregame, and it can never be edited once the game has kicked off. Trends are descriptive only, computed by the same shared module the write-up uses so the two cannot disagree: straight-up splits come from completed games in our database, situational splits look back three seasons and need at least eight decided games, records against the number and on the total arrive with the closing-line restore, and every line carries the games it counts. Filters like these did not hold up as predictors in our testing, so none of them enter the confidence read. The totals block is a read and not a pick: our number is EL CFB Totals v1 (edgelabs.el_cfb_totals, season 2026, model_version v1, docs/el-cfb-totals-v1.md), a registered candidate that loses to the closing total, so it never posts to the board or the record; the market total beside it is the same capture the spread comes from before kickoff and the frozen consensus the model priced against after it, and the gap is measured against whichever number is printed. The totals trends under it are the trend engine's own rows for this game, deduped on the headline, each carrying its sample. On the games the analyst panel works each week (the games our model prices off the market plus the ranked and Power Four games, at most twenty), the pick and the total call are the panel's synthesis: three independent analyst panels, the same evidence pack, their own research, one side each, tiered by how firmly they agreed, never a win probability. A panel majority on a side is what makes a pick; without one the game is a published no-pick, printed as No pick rather than left blank. Research and context, never a guarantee, 21+.