FROZEN PREDICTION

SMU vs Louisville

My CFB Baseline · 2026 Week 3 · revision 3 · Independent

Open this immutable run

SMU by 0.3

Why this pick?

Game controlSmall effect

Avoiding bad lossesSmall effect

Close-game gritModerately leans away

Defensive toughnessSmall effect

Scoring punchSmall effect

Transfer portal impactSmall effect

Previous-season performanceSmall effect

Recruiting strengthSmall effect

Returning productionSmall effect

Team talentSmall effect

Big-game winsModerately leans away

Recent formSmall effect

Wins away from homeModerately leans away

Tough schedulesSmall effect

Statement winsNeutral effect

WinningModerately leans away

Show the technical details

Frozen 2026-09-17T22:12:41.560235-05:00 · Snapshot 104 · Home win probability 0.4901 · 80% margin interval -17.0 to 16.3.

Provisional calibration: real-season accuracy is not established.

Model configuration used

Configuration: Revision 3
Engine version: 3.8.0-kickoff-chronology
Evidence cutoff: Sep 17, 2026 · 11:28 AM CDT

Factors unavailable across the whole snapshot are excluded. Their weight is redistributed among available factors, so the effective model can differ from the configured sliders. Missing evidence for just one team remains neutral. The tables show saved weights; omitted factors are not reconstructed from current model settings.

Factor key	Normalized share
`adj_margin`	0.108108
`avoid_bad_losses`	0.040541
`close_game_wins`	0.027027
`defense_ppg`	0.067568
`offense_ppg`	0.067568
`preseason_portal`	0.040541
`preseason_previous_performance`	0.054054
`preseason_recruiting`	0.067568
`preseason_returning`	0.054054
`preseason_talent`	0.067568
`quality_wins`	0.081081
`recent_form`	0.054054
`road_neutral_wins`	0.040541
`sos`	0.081081
`statement_wins`	0.040541
`win_pct`	0.108108

Retained calibration/context	Frozen value
`version`	provisional-all-slates-policy-v1
`calibration_kind`	documented_policy
`validation_status`	not_historically_validated
`applied_home_field_points`	2.5
`applied_fcs_baseline_z`	-1.5
`residual_scale`	13.0
`residual_scale_source`	documented_policy_not_validated
`intercept`	0.0
`difference_coefficient`	7.0
`home_field_coefficient`	2.5

These values came from this immutable run, not the model’s current settings.

Factor	Home evidence	Away evidence	Normalized share	Home effective share	Away effective share	Weighted difference
Game control	Measured	Measured	0.108108	0.11881693013768486	0.11881693013768486	0.014024006126227825
Avoiding bad losses	Measured	Measured	0.040541	0.044556348801631826	0.044556348801631826	-0.013041826861769655
Close-game grit	Measured	Measured	0.027027	0.029704232534421216	0.029704232534421216	-0.05987058317649781
Defensive toughness	Measured	Measured	0.067568	0.07426058133605304	0.07426058133605304	-0.044585359501859656
Scoring punch	Measured	Measured	0.067568	0.07426058133605304	0.07426058133605304	0.04916806246447002
Transfer portal impact	Measured	Measured	0.040541	0.030405405405405407	0.030405405405405407	0.014540911254537903
Previous-season performance	Measured	Measured	0.054054	0.04054054054054054	0.04054054054054054	-0.00575195672621958
Recruiting strength	Measured	Measured	0.067568	0.05067567567567568	0.05067567567567568	-0.003718510111309345
Returning production	Measured	Measured	0.054054	0.04054054054054054	0.04054054054054054	-0.034423817448315325
Team talent	Measured	Measured	0.067568	0.05067567567567568	0.05067567567567568	-0.024941111165850974
Big-game wins	Measured	Measured	0.081081	0.08911269760326365	0.08911269760326365	-0.0755319340342897
Recent form	Measured	Measured	0.054054	0.05940846506884243	0.05940846506884243	-0.012287342660557445
Wins away from home	Measured	Measured	0.040541	0.044556348801631826	0.044556348801631826	-0.06750328932138404
Tough schedules	Measured	Measured	0.081081	0.08911269760326365	0.08911269760326365	0.047351378154291676
Statement wins	Measured	Measured	0.040541	0.044556348801631826	0.044556348801631826	0.0
Winning	Measured	Measured	0.108108	0.11881693013768486	0.11881693013768486	-0.18649637761982382

Missing team data was represented neutrally in the calculation; it was not a measured neutral result. Measured equal or offsetting inputs can also have zero effect.

This is the exact saved prediction. Current model settings and current prediction selection are not used here.