FROZEN PREDICTION

Alabama vs Kentucky

My CFB Baseline · 2026 Week 2 · revision 2 · Independent

Open this immutable run

Kentucky by 6.4

Why this pick?

Game controlModerately leans home

Avoiding bad lossesSmall effect

Close-game gritNot used — data unavailable

Defensive toughnessModerately leans home

Scoring punchModerately leans home

Transfer portal impactModerately leans home

Previous-season performanceSmall effect

Recruiting strengthModerately leans away

Returning productionSmall effect

Team talentModerately leans away

Big-game winsModerately leans home

Recent formSmall effect

Wins away from homeNeutral effect

Tough schedulesHome data unavailable

Statement winsSmall effect

WinningSmall effect

Show the technical details

Frozen 2026-09-10T23:46:22.723878-05:00 · Snapshot 4 · Home win probability 0.6881 · 80% margin interval -10.3 to 23.0.

Provisional calibration: real-season accuracy is not established.

Model configuration used

Configuration: Revision 2
Engine version: 3.7.0-frozen-classification
Evidence cutoff: Sep 10, 2026 · 11:46 PM 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.

The complete selected factor list was not retained for this older run. Omitted factors cannot be reconstructed reliably.

Factor	Home evidence	Away evidence	Normalized share	Home effective share	Away effective share	Weighted difference
Game control	Measured	Measured	0.108108	0.11441441441441443	0.1136724960254372	0.24817706231691766
Avoiding bad losses	Measured	Measured	0.040541	0.042905405405405404	0.04262718600953895	-0.00487247655404003
Close-game grit	Data unavailable	Data unavailable	0.027027	0.02702702702702703	0.02702702702702703	0.0
Defensive toughness	Measured	Measured	0.067568	0.07150900900900901	0.07104531001589826	0.12602432621503207
Scoring punch	Measured	Measured	0.067568	0.07150900900900901	0.07104531001589826	0.12757674988953496
Transfer portal impact	Measured	Measured	0.040541	0.03547297297297297	0.03547297297297297	0.06573703629655675
Previous-season performance	Measured	Measured	0.054054	0.0472972972972973	0.0472972972972973	-0.04628029613947293
Recruiting strength	Measured	Measured	0.067568	0.05912162162162163	0.05912162162162163	-0.08329608740140157
Returning production	Measured	Measured	0.054054	0.0472972972972973	0.0472972972972973	-0.012902441381457557
Team talent	Measured	Measured	0.067568	0.05912162162162163	0.05912162162162163	-0.06822302229608312
Big-game wins	Measured	Measured	0.081081	0.08581081081081081	0.0852543720190779	0.17761406503140156
Recent form	Measured	Measured	0.054054	0.05720720720720721	0.0568362480127186	-0.00668627495816658
Wins away from home	Measured	Measured	0.040541	0.042905405405405404	0.04262718600953895	0.0
Tough schedules	Data unavailable	Measured	0.081081	0.08108108108108109	0.0852543720190779	0.029791680331331866
Statement wins	Measured	Measured	0.040541	0.042905405405405404	0.04262718600953895	0.0002674787312331936
Winning	Measured	Measured	0.108108	0.11441441441441443	0.1136724960254372	0.0005667309431410111

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.