FORECAST REVISION

My CFB Baseline · 2026 Week 2 · revision 2

2026 · Week 2 · 86 matchups

Download CSV

Experimental picks: the scoring formula is transparent, but its real-season accuracy is not established yet.

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 keyNormalized share
adj_margin0.114286
avoid_bad_losses0.042857
close_game_wins0.028571
defense_ppg0.071429
offense_ppg0.071429
preseason_portal0.042857
preseason_recruiting0.071429
preseason_returning0.057143
preseason_talent0.071429
quality_wins0.085714
recent_form0.057143
road_neutral_wins0.042857
sos0.085714
statement_wins0.042857
win_pct0.114286
Retained calibration/contextFrozen value
versionprovisional-all-slates-policy-v1
calibration_kinddocumented_policy
validation_statusnot_historically_validated
applied_home_field_points2.5
applied_fcs_baseline_z-1.5
residual_scale13.0
residual_scale_sourcedocumented_policy_not_validated
intercept0.0
difference_coefficient7.0
home_field_coefficient2.5

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