FROZEN PREDICTION

South Florida vs Army

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

Open this immutable run

Army by 9.3

Why this pick?

Game controlStrongly leans home

Avoiding bad lossesSmall effect

Close-game gritNot used — data unavailable

Defensive toughnessModerately leans home

Scoring punchModerately leans home

Transfer portal impactSmall effect

Recruiting strengthModerately leans away

Returning productionModerately leans home

Team talentModerately leans away

Big-game winsModerately leans home

Recent formModerately leans home

Wins away from homeNeutral effect

Tough schedulesHome data unavailable

Statement winsModerately leans home

WinningSmall effect

Show the technical details

Frozen 2026-09-09T06:26:39.256689-05:00 · Snapshot 2 · Home win probability 0.7622 · 80% margin interval -7.4 to 25.9.

Provisional calibration: real-season accuracy is not established.

Model configuration used

Configuration: Revision 2
Engine version: 3.7.0-frozen-classification
Evidence cutoff: Sep 8, 2026 · 6:43 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`	0.114286
`avoid_bad_losses`	0.042857
`close_game_wins`	0.028571
`defense_ppg`	0.071429
`offense_ppg`	0.071429
`preseason_portal`	0.042857
`preseason_recruiting`	0.071429
`preseason_returning`	0.057143
`preseason_talent`	0.071429
`quality_wins`	0.085714
`recent_form`	0.057143
`road_neutral_wins`	0.042857
`sos`	0.085714
`statement_wins`	0.042857
`win_pct`	0.114286

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	0.114286	0.11968253968253968	0.11904761904761904	0.2756463573766594
Avoiding bad losses	Measured	Measured	0.042857	0.04488095238095238	0.044642857142857144	0.045119353622890906
Close-game grit	Data unavailable	Data unavailable	0.028571	0.02857142857142857	0.02857142857142857	0.0
Defensive toughness	Measured	Measured	0.071429	0.0748015873015873	0.0744047619047619	0.1857731184691815
Scoring punch	Measured	Measured	0.071429	0.0748015873015873	0.0744047619047619	0.19636963282095612
Transfer portal impact	Measured	Measured	0.042857	0.0375	0.0375	-0.03124827140811048
Recruiting strength	Measured	Measured	0.071429	0.0625	0.0625	-0.10711279017484306
Returning production	Measured	Measured	0.057143	0.049999999999999996	0.049999999999999996	0.12986553876580134
Team talent	Measured	Measured	0.071429	0.0625	0.0625	-0.0973286871683149
Big-game wins	Measured	Measured	0.085714	0.08976190476190476	0.08928571428571429	0.185871894534187
Recent form	Measured	Measured	0.057143	0.05984126984126984	0.05952380952380952	0.06173066297524433
Wins away from home	Measured	Measured	0.042857	0.04488095238095238	0.044642857142857144	0.0
Tough schedules	Data unavailable	Measured	0.085714	0.08571428571428572	0.08928571428571429	0.03120041113621
Statement wins	Measured	Measured	0.042857	0.04488095238095238	0.044642857142857144	0.09135013130865466
Winning	Measured	Measured	0.114286	0.11968253968253968	0.11904761904761904	0.0004849983173274841

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.