FROZEN PREDICTION

Michigan vs Rutgers

My CFB Baseline · 2026 Week 9 · revision 3 · Independent

Open this immutable run

Michigan by 1.9

Why this pick?

Game controlModerately leans away

Avoiding bad lossesModerately leans away

Close-game gritSmall effect

Defensive toughnessModerately leans away

Scoring punchModerately leans home

Transfer portal impactSmall effect

Previous-season performanceSmall effect

Recruiting strengthSmall effect

Returning productionSmall effect

Team talentSmall effect

Big-game winsModerately leans away

Recent formModerately leans away

Wins away from homeNeutral effect

Tough schedulesModerately leans home

Statement winsNeutral effect

WinningModerately leans away

Show the technical details

Frozen 2026-10-16T22:28:36.912781-05:00 · Snapshot 515 · Home win probability 0.4424 · 80% margin interval -18.5 to 14.8.

Provisional calibration: real-season accuracy is not established.

Model configuration used

Configuration: Revision 3
Engine version: 3.8.0-kickoff-chronology
Evidence cutoff: Oct 16, 2026 · 10:28 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	0.13488016318204998	0.13488016318204998	-0.08796385095111706
Avoiding bad losses	Measured	Measured	0.040541	0.050580061193268744	0.050580061193268744	-0.10470008034921016
Close-game grit	Measured	Measured	0.027027	0.033720040795512496	0.033720040795512496	-0.04359692813163066
Defensive toughness	Measured	Measured	0.067568	0.08430010198878124	0.08430010198878124	-0.15910753824682589
Scoring punch	Measured	Measured	0.067568	0.08430010198878124	0.08430010198878124	0.09915148888160562
Transfer portal impact	Measured	Measured	0.040541	0.015202702702702704	0.015202702702702704	0.027265585582491002
Previous-season performance	Measured	Measured	0.054054	0.02027027027027027	0.02027027027027027	-0.0117745035733979
Recruiting strength	Measured	Measured	0.067568	0.02533783783783784	0.02533783783783784	-0.031010087689598557
Returning production	Measured	Measured	0.054054	0.02027027027027027	0.02027027027027027	-0.019314721102222168
Team talent	Measured	Measured	0.067568	0.02533783783783784	0.02533783783783784	-0.041253127725003905
Big-game wins	Measured	Measured	0.081081	0.10116012238653749	0.10116012238653749	-0.08281001425684967
Recent form	Measured	Measured	0.054054	0.06744008159102499	0.06744008159102499	-0.0552943510073407
Wins away from home	Measured	Measured	0.040541	0.050580061193268744	0.050580061193268744	0.0
Tough schedules	Measured	Measured	0.081081	0.10116012238653749	0.10116012238653749	0.11776218631061858
Statement wins	Measured	Measured	0.040541	0.050580061193268744	0.050580061193268744	0.0
Winning	Measured	Measured	0.108108	0.13488016318204998	0.13488016318204998	-0.23356027597724732

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.