FROZEN PREDICTION

Louisiana Tech vs South Alabama

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

Open this immutable run

Louisiana Tech by 0.5

Why this pick?

Game controlModerately leans away

Avoiding bad lossesSmall effect

Close-game gritSmall effect

Defensive toughnessModerately leans away

Scoring punchSmall effect

Transfer portal impactSmall effect

Previous-season performanceSmall effect

Recruiting strengthSmall effect

Returning productionSmall effect

Team talentSmall effect

Big-game winsSmall effect

Recent formSmall effect

Wins away from homeSmall effect

Tough schedulesStrongly leans away

Statement winsSmall effect

WinningSmall effect

Show the technical details

Frozen 2026-10-16T22:50:33.001398-05:00 · Snapshot 516 · Home win probability 0.4841 · 80% margin interval -17.2 to 16.1.

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 · 10:50 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	0.14023457419683835	0.13488016318204998	-0.06602811525381773
Avoiding bad losses	Measured	Measured	0.040541	0.05258796532381438	0.050580061193268744	0.02762544329894169
Close-game grit	Measured	Measured	0.027027	0.03505864354920959	0.033720040795512496	-0.028483999868881806
Defensive toughness	Measured	Measured	0.067568	0.08764660887302397	0.08430010198878124	-0.15604220480216285
Scoring punch	Measured	Measured	0.067568	0.08764660887302397	0.08430010198878124	-0.035587651320889424
Transfer portal impact	Measured	Measured	0.040541	0.010135135135135136	0.015202702702702704	-0.005140147470276928
Previous-season performance	Measured	Measured	0.054054	0.013513513513513514	0.02027027027027027	-0.004833418433901169
Recruiting strength	Measured	Measured	0.067568	0.016891891891891893	0.02533783783783784	0.007545031986780462
Returning production	Measured	Measured	0.054054	0.013513513513513514	0.02027027027027027	0.0019745839634889087
Team talent	Measured	Measured	0.067568	0.016891891891891893	0.02533783783783784	0.01680573156843401
Big-game wins	Measured	Measured	0.081081	0.10517593064762876	0.10116012238653749	-0.048523620307527555
Recent form	Measured	Measured	0.054054	0.07011728709841918	0.06744008159102499	0.02384513166047052
Wins away from home	Measured	Measured	0.040541	0.05258796532381438	0.050580061193268744	0.023435049597208036
Tough schedules	Measured	Measured	0.081081	0.10517593064762876	0.10116012238653749	-0.25928429624421606
Statement wins	Measured	Measured	0.040541	0.05258796532381438	0.050580061193268744	0.03052702384910883
Winning	Measured	Measured	0.108108	0.14023457419683835	0.13488016318204998	0.04103845843413775

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.