FROZEN PREDICTION

USC vs Indiana

My CFB Baseline · 2026 Week 11 · revision 3 · Independent

Open this immutable run

Indiana by 7.9

Why this pick?

Game controlModerately leans home

Avoiding bad lossesSmall effect

Close-game gritSmall effect

Defensive toughnessModerately leans home

Scoring punchSmall effect

Transfer portal impactSmall effect

Previous-season performanceSmall effect

Recruiting strengthSmall effect

Returning productionSmall effect

Team talentSmall effect

Big-game winsModerately leans home

Recent formModerately leans home

Wins away from homeModerately leans home

Tough schedulesModerately leans home

Statement winsSmall effect

WinningNeutral effect

Show the technical details

Frozen 2026-10-17T15:32:44.775165-05:00 · Snapshot 531 · Home win probability 0.7271 · 80% margin interval -8.8 to 24.5.

Provisional calibration: real-season accuracy is not established.

Model configuration used

Configuration: Revision 3
Engine version: 3.8.0-kickoff-chronology
Evidence cutoff: Oct 17, 2026 · 3:31 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.

Factor	Home evidence	Away evidence	Normalized share	Home effective share	Away effective share	Weighted difference
Game control	Measured	Measured	0.108108	0.14558898521162672	0.14558898521162672	0.1842110954333041
Avoiding bad losses	Measured	Measured	0.040541	0.05459586945436003	0.05459586945436003	0.04381854252919537
Close-game grit	Measured	Measured	0.027027	0.03639724630290668	0.03639724630290668	-0.032351347979628735
Defensive toughness	Measured	Measured	0.067568	0.09099311575726671	0.09099311575726671	0.1600568138555076
Scoring punch	Measured	Measured	0.067568	0.09099311575726671	0.09099311575726671	0.0019534551068342565
Transfer portal impact	Measured	Measured	0.040541	0.005067567567567568	0.005067567567567568	0.013319988781776827
Previous-season performance	Measured	Measured	0.054054	0.006756756756756757	0.006756756756756757	0.004540870650117266
Recruiting strength	Measured	Measured	0.067568	0.008445945945945946	0.008445945945945946	-0.01367028848973157
Returning production	Measured	Measured	0.054054	0.006756756756756757	0.006756756756756757	-0.01105923546982076
Team talent	Measured	Measured	0.067568	0.008445945945945946	0.008445945945945946	-0.012753776597428955
Big-game wins	Measured	Measured	0.081081	0.10919173890872005	0.10919173890872005	0.13605872332118657
Recent form	Measured	Measured	0.054054	0.07279449260581336	0.07279449260581336	0.0625595497636401
Wins away from home	Measured	Measured	0.040541	0.05459586945436003	0.05459586945436003	0.051120139240896756
Tough schedules	Measured	Measured	0.081081	0.10919173890872005	0.10919173890872005	0.14092328921456593
Statement wins	Measured	Measured	0.040541	0.05459586945436003	0.05459586945436003	0.03619467023006254
Winning	Measured	Measured	0.108108	0.14558898521162672	0.14558898521162672	0.0

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.