Skip to content

‹ PHI vs WAS

WEEK 1 ·

PHIWAS

PROVISIONAL · LATE-WEEK INPUTS STILL MOVING

DATA STALE

  • DEPTH CHARTS 120 h since ingest, threshold 48 h
  • INJURIES 551 h since ingest, threshold 36 h
  • SCHEDULES 550 h since ingest, threshold 168 h
  • WEATHER 551 h since ingest, threshold 24 h

ARCADIA SCORE

MODERATE CONFIDENCE

Arcadia Score, five hundred sixty-eight out of one thousand, Moderate confidence
How far to trust the tier table. The confidence tiers are not in outcome order on the measured season — Very High 0.806452 over Elite 0.800000, a gap of 0.006452. A higher tier with a lower hit rate is a failure of the monotone criterion, and it is disclosed here because it was not remediated. score_tier_stats, pinned to one persisted run via eval_runs · run exit8-persist-0814-tiers-2025
Moderate is the higher tier but not the better outcome: Pass hit 0.619048 against Moderate's 0.456522 over 250 scored games, a deficit of 0.162526. Tier order and outcome order disagree here; the failure is reported rather than tuned away, and Moderate is not claimed to be distinguishable from Pass on this evidence. score_tier_stats, pinned to one persisted run via eval_runs

Model win probability 62.3% ± 7.9

WHY PHI HAS THE EDGE

  • TEAM FORM +17.5 pts toward the verdict
  • QUARTERBACK EDGE +16.8 pts toward the verdict
  • INJURY ADJUSTMENT −13.4 pts against the verdict
  • LONG-RUN RATING +13.1 pts toward the verdict
  • REST AND TRAVEL +3.0 pts toward the verdict
  • WEATHER +0.9 pts toward the verdict
  • OFFENSIVE MATCHUP +0.0 pts neutral for the verdict
  • MARKET VALUE n/a not measured

Market Value inert in v1 — closing lines are kickoff-gated, so nothing is knowable pregame.

Weather is ruled inert in v1, yet this edition carries a contribution for it. Both are reported; the ruling and the artifact disagree.

CONTRIBUTIONS IN PROBABILITY POINTS · BAR LENGTH IS SHARE OF THE LARGEST

KEY SIGNALS

  • {'components': [{'coef': 0.07123315194541688, 'contribution_logit': 0.06744140620892258, 'feature': 'elo_prob_home', 'higher_is_home_advantage': True, 'is_provenance': False, 'z': 0.9467699289875624}, {'coef': 0.07137124372094657, 'contribution_logit': 0.0619101528578351, 'feature': 'elo_diff', 'higher_is_home_advantage': True, 'is_provenance': False, 'z': 0.8674383355276355}, {'coef': 0.009371095193614449, 'contribution_logit': 0.0011230587580697093, 'feature': 'elo_mean', 'higher_is_home_advantage': None, 'is_provenance': False, 'z': 0.11984285026097824}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'elo_diff_missing', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'elo_mean_missing', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'elo_prob_home_missing', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}], 'family_contribution_logit': 0.1304746178248274, 'feature_value': 0.7161704115260998, 'oriented_to': 'home', 'provenance_contribution_logit': 0.0, 'representative_is_provenance': False} LONG-RUN RATING · +3.1 pts
  • {'components': [{'coef': 0.05693385868221376, 'contribution_logit': 0.053793423909610165, 'feature': 'qb_experience_diff', 'higher_is_home_advantage': True, 'is_provenance': False, 'z': 0.9448406476340822}, {'coef': 0.02196500682331482, 'contribution_logit': 0.03228143457598706, 'feature': 'qb_uncertainty_mean', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 1.4696755997235493}, {'coef': -0.012106979968260365, 'contribution_logit': 0.02680306995336642, 'feature': 'qb_uncertainty_diff', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': -2.2138526720646516}, {'coef': -0.012478648777462076, 'contribution_logit': 0.02561052249928539, 'feature': 'qb_is_backup_diff', 'higher_is_home_advantage': False, 'is_provenance': False, 'z': -2.0523474100449914}, {'coef': 0.05496744586677124, 'contribution_logit': 0.022637920023537043, 'feature': 'qb_cpoe_diff', 'higher_is_home_advantage': True, 'is_provenance': False, 'z': 0.4118423126009217}, {'coef': 0.005326189691059842, 'contribution_logit': 0.00690535220791495, 'feature': 'qb_is_backup_mean', 'higher_is_home_advantage': None, 'is_provenance': False, 'z': 1.296490100513276}, {'coef': 0.04849809981481904, 'contribution_logit': 0.0022418309257733124, 'feature': 'qb_value_diff', 'higher_is_home_advantage': True, 'is_provenance': False, 'z': 0.0462251291150236}, {'coef': 0.0247205567183512, 'contribution_logit': -0.0020310372511551994, 'feature': 'qb_diff_inputs_absent', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': -0.08215985077906711}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'qb_away_expected_id_missing', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'qb_chart_is_offseason_diff', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'qb_chart_is_offseason_mean', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}, {'coef': 0.0, 'contribution_logit': 0.0, 'feature': 'qb_home_expected_id_missing', 'higher_is_home_advantage': None, 'is_provenance': True, 'z': 0.0}], 'family_contribution_logit': 0.16824251684431915, 'feature_value': 1.1647614697922153, 'oriented_to': 'home', 'provenance_contribution_logit': 0.05705346727819828, 'representative_is_provenance': False} QUARTERBACK EDGE · +2.6 pts

RISK FACTORS

  • the feature frame was thin

DATA QUALITY

PUBLICATION GATE PASSED

DEGRADED INJURIES STALEWEATHER MISSINGODDS OUTDATEDDATA THIN

FLAGS DATA THIN

LIVE GATE PUBLISHABLE INJURIES FRESHWEATHER AVAILABLEDATA COMPLETE

no features computed for this game at this as_of

PREDICTION HISTORY

Arcadia Score across model runs
  1. 585 Moderate PHI v1-logreg-mf-2026.08c
  2. 568 Moderate PHI v1-logreg-mf-2026.08c