FROZEN PREDICTION

Southern Miss vs Troy

My CFB Baseline · 2026 Week 6 · revision 3 · Independent

Open this immutable run

Troy by 6.6

Why this pick?

Game controlModerately leans home

Avoiding bad lossesModerately leans home

Close-game gritModerately leans home

Defensive toughnessModerately leans home

Scoring punchSmall effect

Transfer portal impactModerately leans away

Previous-season performanceSmall effect

Recruiting strengthSmall effect

Returning productionModerately leans away

Team talentSmall effect

Big-game winsModerately leans home

Recent formModerately leans home

Wins away from homeNeutral effect

Tough schedulesModerately leans home

Statement winsNeutral effect

WinningModerately leans home

Show the technical details

Frozen 2026-10-05T05:00:47.825910-05:00 · Snapshot 378 · Home win probability 0.6950 · 80% margin interval -10.0 to 23.3.

Provisional calibration: real-season accuracy is not established.

Model configuration used

Configuration: Revision 3
Engine version: 3.8.0-kickoff-chronology
Evidence cutoff: Oct 4, 2026 · 5:07 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	0.12952575216726162	0.12952575216726162	0.1165040695270822
Avoiding bad losses	Measured	Measured	0.040541	0.0485721570627231	0.0485721570627231	0.0847915866143721
Close-game grit	Measured	Measured	0.027027	0.032381438041815404	0.032381438041815404	0.07693450783182842
Defensive toughness	Measured	Measured	0.067568	0.0809535951045385	0.0809535951045385	0.1218493389680599
Scoring punch	Measured	Measured	0.067568	0.0809535951045385	0.0809535951045385	-0.03229238358445677
Transfer portal impact	Measured	Measured	0.040541	0.02027027027027027	0.02027027027027027	-0.05653146444930258
Previous-season performance	Measured	Measured	0.054054	0.02702702702702703	0.02702702702702703	0.002421416907463156
Recruiting strength	Measured	Measured	0.067568	0.033783783783783786	0.033783783783783786	0.0064911503006985175
Returning production	Measured	Measured	0.054054	0.02702702702702703	0.02702702702702703	-0.05568558704874539
Team talent	Measured	Measured	0.067568	0.033783783783783786	0.033783783783783786	-0.010259034699074358
Big-game wins	Measured	Measured	0.081081	0.0971443141254462	0.0971443141254462	0.05520154586652167
Recent form	Measured	Measured	0.054054	0.06476287608363081	0.06476287608363081	0.09769430345560942
Wins away from home	Measured	Measured	0.040541	0.0485721570627231	0.0485721570627231	0.0
Tough schedules	Measured	Measured	0.081081	0.0971443141254462	0.0971443141254462	0.05141579357945505
Statement wins	Measured	Measured	0.040541	0.0485721570627231	0.0485721570627231	0.0
Winning	Measured	Measured	0.108108	0.12952575216726162	0.12952575216726162	0.1314359427579837

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.