How each matchup alert has done once the game finished, checked against the final score and the sportsbook number.
Games with no posted sportsbook number are left out of the win-loss counts.
What the model total has meant in tracked games.
| We said | Call | Record |
|---|---|---|
| 38 or less | Under 41Strongest | 8–0 (100%) |
| 44 or less | Under 45 | 14–1 (93%) |
| 45 to 54 | Over 45 | 6–1 (86%) |
| 55+ | Skip | 5–4 |
The first two rows overlap. Every game at 38 or less is also in the 44-or-less row. When both apply, Under 41 is the stronger play.
The record each badge leads with on a card: the hit rate the badge strength sliders read. Card chips and matchup alerts are graded finals this season; pattern, trend, combo and diamond badges show their backtest or live record, as their pill says. Sharp patterns and leans come from the Oct 18 study against the closing price; badges it found no edge for on the seasons their own study never saw are retired to this list (records only), and the borderline ones carry a watch label.
Loading records…
This season only — small sample. Each week we search this season's finished games, and nothing older: pairs and triples of the card's own pregame badges (stat trends, tail leans, sharp patterns, our pick, our number vs the line), the line itself and pregame facts (roof, rest, QB, last result), against six results (favorite / underdog wins, covers, over, under). A combo becomes a 💎 with 8+ games (10+ for three conditions), a hit rate 12+ points above the no-vig closing price, a Wilson lower bound above that price, a winning record on the earlier weeks and no losing one on the latest two, and only if the whole search clears a luck check: rerun on 100 seasons simulated from the closing prices, the simulated passes must be at most 20% of the real ones. Cards of week W only use weeks before W, and a combo that stops clearing the bar drops off the next week by itself. Records only, not advice · 21+.
The weekly search has not loaded.
Every 🔥 combo leads with one of the board's own tag chips (Favorite holds, Coin flip, Upset alert, Shootout, Low scoring, Blowout brewing, Model leans over / under, Off the market, the stat-trend chips and the matchup alerts, all as they stood before kickoff), plus one or two more pregame factors; per tag only its most successful combos (biggest edge over the price) show. A refinement replaces the plainer version only when its record is at least as strong. Combos from this season's games that cleared the same per-combo bar as a 💎 (8+ games, 12+ points over the no-vig price, Wilson low above the price, held on the latest two weeks) but not the luck check: a perfectly priced season produces runs like these often, so each one could be luck. Near-duplicates are collapsed; a card shows at most two, strongest first. Searched again every week on earlier weeks only; one that stops holding drops off. Records only, not advice · 21+.
The weekly search has not loaded.
Combinations that held up over every 2016–25 regular-season game, not just this season: 40+ games, at least 4 points above games on similar closing lines, one-sided p under 0.05, above base in both 2016–20 and 2021–25, and (for combos with a stat trend or tail lean) in 2023–25 too. Inputs are pregame only: our walk-forward number after the October 2026 totals recalibration, the card chip rules, the stat trends and tail leans, and the nflverse closing line. Cards grade each one on the final against the card's closing line. These were picked from a search of 74 games in 2026, so even the diamonds are weak evidence. Records only, not advice · 21+.
When: Tail lean: Rain or snow in the forecast
When: Stat trend: Underdog goes for it on 4th down more
When: Stat trend: Underdog goes for it on 4th down more + our total 42.1 to 46
When: Stat trend: Aggressive underdog in a low-possession game
When: Stat trend: Favorite's offense punts more
When: Tail lean: Wind 10+ mph, open air
When: Tail lean: Two hot teams
Popular runs this season with no long-run edge. Cards show them as small chips that say so.
When: Favorite holds + home team favored + we're within 1 point of the spread
Hot in 2026 only: no edge over similar lines in 2016–25. Never a diamond.
When: Shootout (our total 50+) + book total 48+
Hot in 2026 only: no edge over similar lines in 2016–25. Never a diamond.
When: Shootout (our total 50+) + our total 49+ + book total 49+ + no favorite bigger than 7.5 (home spread −7.5 to +7)
Hot in 2026 only: no edge over similar lines in 2016–25. Never a diamond.
These read our total. Since October 2026 our total is pulled halfway toward the market total, so the same bands now pick different games, and on the new number these combos no longer clear the bar.
When: Super trend: One side projects 140+ rushing yards + our total 1 to 3 points above the book (edge +1 to +3)
Misses the long-run bar on the current number (p not under 0.05, not above base in 2023–25). Not shown on cards.
When: Stat trend: Underdog goes for it on 4th down more + our total 1 to 3 points above the book (edge +1 to +3)
Misses the long-run bar on the current number (not above base in both 2016–20 and 2021–25). Not shown on cards.
When: book total 41.5 or lower + our total 42.1 to 46 + our margin 2.5 to 6
Misses the long-run bar on the current number (p not under 0.05, not above base in both 2016–20 and 2021–25). Not shown on cards.
When: Model leans over (our total 3+ above the book) + we're 2+ points higher on the underdog than the spread
Misses the long-run bar on the current number (fewer than 40 games, under 4 points above similar lines, p not under 0.05, not above base in both 2016–20 and 2021–25). Not shown on cards.
When: Favorite holds + our total 46.1 to 49.9 + our margin 6 to 10
Misses the long-run bar on the current number (under 4 points above similar lines, p not under 0.05). Not shown on cards.
When: Coin flip + book total 45 to 47.5 + our total 42.1 to 46
Misses the long-run bar on the current number (p not under 0.05). Not shown on cards.
Loading records…
The EXPECTED chips on every game card, graded from the number we froze before kickoff.
The four stat badges, graded only when they were frozen before kickoff.
Situations that finished one way more often than games on similar closing spreads in our walk-forward backtest: our model's pregame numbers for 2020–25 (each built only from earlier games) against nflverse closing lines. Picked on 2020–24, checked on 2025.
A broad scan of 12,288 situation × result combinations turned up no more "winners" than shuffled results do, so only patterns with a football reason that also held in 2025 are kept. A 👀 Watching pattern becomes a ⚡ Pattern alert only after 25+ live games (after it was written down) with a 90% lower bound above the base by 3 points, and drops back when that stops being true.
Records only, not advice. 21+ only where legal.
Loading patterns…
Team-stat matchups (each team's season-to-date numbers from before kickoff, blended with last season in weeks 1–4) checked against nflverse results and closing lines, 2016–2025. Each rule was picked on 2016–22 only, then had to hold in 2023–24 and in the 2025 holdout, with no more than 2 losing seasons of 10. "Base" is the same result's rate in games on similar closing lines, so a lift is on top of what the market already priced (run- and pass-heavy games have no market; their base is the league rate on similar lines).
Multiple comparisons: we tried 40,566 rules (407 features × thresholds on round percentiles, plus two-condition combos) across 15 results. With that many tries, dozens pass by luck, so the whole search was re-run on shuffled results (shuffled within season and line band). Only results whose real rules clearly beat the shuffles keep any rule; the rest are listed below as "nothing beat chance". 🔥 Super trend = 2025 holdout lift of 8+ points, 2016–24 interval above the base and 7+ winning seasons. A trend is promoted live after 25+ games with a 90% lower bound 3 points above its base, and drops back (or off the cards) when its live record trails the base.
Live records start Sep 27; this season's earlier weeks are graded as backtest. Analysis and entertainment, not betting advice. 21+ only where legal.
When: The favorite punts at least 0.56 more times per game than the underdog (top 20% of games).
Why it could be real: The spread leans on the favorite's record and reputation, but its offense stalls more often than the underdog's; drive-by-drive production points to a closer game than the number.
2016–24 combined: 90% interval 55%–62% vs base 52%
Met the super-trend bar but kept at 👀 Watching: the model cross-check found no underdog-cover signal beyond the line, so only its live record can promote it.
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 10 of 10 seasons beat the base.
When: The underdog tries 0.8+ more fourth downs per game than the favorite (top 10%).
Why it could be real: Aggressive underdog coaches turn punts into extra possessions and points, and cautious favorites leave margin on the table, so these games tend to stay inside the number.
2016–24 combined: 90% interval 53%–63% vs base 50%
Met the super-trend bar but kept at 👀 Watching: the model cross-check found no underdog-cover signal beyond the line, so only its live record can promote it.
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 10 seasons beat the base.
When: The underdog tries 0.8+ more fourth downs per game than the favorite; and the two offenses average 22.25 or fewer drives per game combined (bottom third).
Why it could be real: Fewer possessions leave the better team fewer chances to pull away, and the aggressive underdog squeezes more out of each one: a shortened game helps the side getting points.
2016–24 combined: 90% interval 58%–71% vs base 50% · each condition alone (2016–22): 61% vs 52%, 57% vs 53%
Met the super-trend bar but kept at 👀 Watching: the model cross-check found no underdog-cover signal beyond the line, so only its live record can promote it.
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 10 seasons beat the base.
When: Both offenses project an explosive-play rate of about 10%+ against the other defense (top 20%).
Why it could be real: Explosive plays make results swingy: one long touchdown can keep an underdog in the game or produce a late back-door score, which favors the side getting points.
2016–24 combined: 90% interval 56%–63% vs base 52%
Kept at 👀 Watching: the model cross-check found no underdog-cover signal beyond the line, so only its live record can promote it.
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: Each team's rushing yards per game plus what the other defense allows add up to 252+ projected rushing yards (top 10%).
Why it could be real: When both rushing offenses meet run defenses that give up yards, both teams keep running; the betting total prices points, not how they are scored.
2016–24 combined: 90% interval 42%–51% vs base 27%
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: One team's rushing average and the opponent's rushing yards allowed average out to 140+ (top 10%).
Why it could be real: A strong ground game against a leaky run defense usually gets fed, and a team that is running well leans on it even more as it leads.
2016–24 combined: 90% interval 42%–52% vs base 27%
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: Both sides project 26.9+ carries (top 10%); and combined opponent-adjusted rushing efficiency in the top third.
Why it could be real: Two play-callers who run a lot, meeting defenses that can't stop it efficiently, pile up carries on both sides of the ball.
2016–24 combined: 90% interval 42%–56% vs base 25% · each condition alone (2016–22): 35% vs 25%, 42% vs 26%
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 10 seasons beat the base.
When: The underdog's yards per carry and the favorite's yards per carry allowed average 3.75 or less (bottom 10%).
Why it could be real: An underdog that can't run against this defense falls behind and has to throw, and the favorite answers through the air too, so passing yards pile up.
2016–24 combined: 90% interval 35%–45% vs base 30%
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 10 of 10 seasons beat the base.
When: Both sides project 24.1 or fewer carries (bottom third); and both sides project 3.8 yards per carry or less (bottom 20%).
Why it could be real: When neither offense runs often and neither can run efficiently in this matchup, both games plans go through the quarterback.
2016–24 combined: 90% interval 38%–49% vs base 31% · each condition alone (2016–22): 43% vs 37%, 38% vs 32%
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: Both sides project a 54%+ pass rate on early downs in neutral game states (top 10%).
Why it could be real: Early-down pass rate is a play-caller's habit; when both sides throw first even in neutral spots, the yardage goes through the air.
2016–24 combined: 90% interval 44%–55% vs base 39%
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 10 of 10 seasons beat the base.
Rules passing every check on the real results vs the average on shuffled results, and a cross-check model (regularised logistic regression, season-by-season cross-validation) with and without the team stats, scored on the 2025 holdout (AUC: 0.5 = no skill).
| Result | Passed | Shuffled avg | p | 2025 AUC line → +stats | Verdict |
|---|---|---|---|---|---|
| Low-scoring (≤37 and under the total) | 6 | 9.7 | 0.677 | 0.66 → 0.62 | Nothing beat chance |
| Under the closing total | 8 | 13.1 | 0.728 | 0.50 → 0.44 | Nothing beat chance |
| High-scoring (51+ and over the total) | 9 | 10.8 | 0.522 | 0.59 → 0.60 | Nothing beat chance |
| Over the closing total | 5 | 11.6 | 0.848 | 0.50 → 0.44 | Nothing beat chance |
| Upset (underdog wins outright) | 14 | 10.3 | 0.229 | 0.64 → 0.61 | Nothing beat chance |
| Underdog covers | 39 | 14.3 | 0.018 | 0.52 → 0.51 | 4 kept |
| FG-heavy (5+ made or 6+ tried) | 11 | 8.6 | 0.298 | 0.53 → 0.55 | Nothing beat chance |
| Run-heavy (300+ combined or a team 175+) | 152 | 12.5 | 0.001 | 0.44 → 0.67 | 3 kept |
| Pass-heavy (550+ combined or a team 325+) | 26 | 7.8 | 0.015 | 0.65 → 0.66 | 3 kept |
| Blowout (17+) | 14 | 8 | 0.159 | 0.60 → 0.64 | Nothing beat chance |
| One-score game (8 or less) | 23 | 11.2 | 0.070 | 0.58 → 0.56 | Nothing beat chance |
| Defensive or special-teams TD | 10 | 8.2 | 0.279 | 0.49 → 0.50 | Nothing beat chance |
| 4+ combined turnovers | 5 | 8.7 | 0.719 | 0.45 → 0.52 | Nothing beat chance |
| First half 13 or fewer points | 5 | 3.4 | 0.284 | 0.59 → 0.55 | Nothing beat chance |
| First half 28+ points | 12 | 11.6 | 0.378 | 0.59 → 0.60 | Nothing beat chance |
Popular ideas, tested the same way (thresholds on 2016–22 percentiles). None cleared the bar.
A second, wider search aimed at the rare ends of games: market structure (key numbers, moneyline vs spread, juice, opening vs closing line where history exists), referee crews, quarterback changes and backups, injured starters, rest, byes, travel, cold, wind, rain, altitude, late-season motivation, rematches, bounce-backs after extreme results, over/under and cover streaks, scoring luck, 4th-down aggressiveness and coach tenure — at extreme thresholds (top and bottom 2.5–10%) and in pairs.
The bar is lower than for stat trends, on purpose: at least 25 games in 2016–22, a lift of 8+ points over games on similar lines there, the same direction in 2023–24 and in the 2025 holdout, a football reason, and either the whole search beating shuffled results (permutation p ≤ 0.2) or a shrunk estimate still 4+ points above the base. That makes these small samples that may be noise. Only the best three per result show on game cards; each is demoted off the cards if its live record trails its base after 15 games.
77,100 rules tried across 12 results. Live records start Sep 27. Analysis and entertainment, not betting advice. 21+ only where legal.
Broad search: 6,425 rules, 26 passed the tail bar vs 39.3 on shuffled results (p 0.809, 1000 shuffles) · Theory list: 24 written-down hypotheses, 0 passed vs 0.05 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. Wind, rain, cold, backup quarterbacks, injured starters, under-leaning referee crews, under streaks, slow pace and conservative 4th-down coaches were all tested; rain/snow helps the plain under (see Under), but nothing moved the 37-or-fewer low-scoring result beyond chance.
Broad search: 6,425 rules, 51 passed the tail bar vs 64.5 on shuffled results (p 0.712, 1000 shuffles) · Theory list: 24 written-down hypotheses, 1 passed vs 0.07 (p 0.075) · family-wide shrinkage prior 4,866 games · holdout games in kept leans 15
When: rain or snow at an outdoor stadium (backtest: nflverse game-day weather; live: the kickoff forecast, 50%+ chance or rain/snow in the forecast).
Why it could be real: A wet ball means more fumbles and drops, shorter passes and more running, which runs the clock. Totals are set days ahead and move only partly with the forecast. Written down as a hypothesis before testing (theory family).
Shrunk estimate (100-game prior toward the base): 59% vs base 52% (+7 pts) · family-wide shrinkage: 52% · 2023–25 combined 28/43 vs 51% · theory-list permutation p 0.075
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 10 seasons beat the base.
Broad search: 6,425 rules, 7 passed the tail bar vs 14.7 on shuffled results (p 0.851, 1000 shuffles) · Theory list: 24 written-down hypotheses, 0 passed vs 0.01 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. The line alone already explains the 30-or-fewer games; every extra condition was at or below what shuffled results produce.
Broad search: 6,425 rules, 59 passed the tail bar vs 64.3 on shuffled results (p 0.545, 1000 shuffles) · Theory list: 20 written-down hypotheses, 0 passed vs 0.08 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. Dome + fast pace, over-leaning crews, depleted defenses, over streaks, aggressive coaches, heat, altitude, week 18 and scoring-luck regression were all tested: fewer rules passed on the real results than on shuffled ones.
Broad search: 6,425 rules, 63 passed the tail bar vs 69.5 on shuffled results (p 0.555, 1000 shuffles) · Theory list: 20 written-down hypotheses, 0 passed vs 0.10 (p 1.000) · family-wide shrinkage prior 4,866 games · holdout games in kept leans 0
Nothing, even at the tail level. Same inputs as high scoring; nothing beat the shuffles.
Broad search: 6,425 rules, 23 passed the tail bar vs 32.6 on shuffled results (p 0.706, 1000 shuffles) · Theory list: 20 written-down hypotheses, 0 passed vs 0.03 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. Nothing beat the shuffles; the 60+ games were no more common where any tested condition (or the variance model) said they should be.
Broad search: 6,425 rules, 78 passed the tail bar vs 52.7 on shuffled results (p 0.127, 1000 shuffles) · Theory list: 28 written-down hypotheses, 1 passed vs 0.15 (p 0.143) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 149
When: the favorite's defense allows 0.20+ fewer EPA per play than the underdog's, opponent-adjusted (biggest 5% of gaps); and it allows 5.6+ fewer points per game, opponent-adjusted (biggest 20%).
Why it could be real: Defensive numbers are much less stable week to week than offensive ones, yet the spread leans on them. A favorite whose whole edge is its defense is priced on something that tends to regress, so the underdog wins outright more often than the line implies.
Shrunk estimate (100-game prior toward the base): 35% vs base 26% (+9 pts) · family-wide shrinkage: 27% · 2023–25 combined 8/25 vs 27% · broad-search permutation p 0.127
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: the underdog is one of the most-followed franchises (Cowboys, Chiefs, Packers, Steelers, Patriots, 49ers, Eagles); and its quarterback started 15+ of the team's last 16 games.
Why it could be real: Popular teams are rarely underdogs; when they are, it is usually after a short bad stretch the market overreacts to. With their established starter they are closer to their true level than the price.
Shrunk estimate (100-game prior toward the base): 45% vs base 38% (+7 pts) · family-wide shrinkage: 38% · 2023–25 combined 24/48 vs 35% · broad-search permutation p 0.127
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 10 seasons beat the base.
When: the underdog's red-zone touchdown rate, averaged with what the favorite's defense allows, is 41.5% or lower (bottom 2.5%).
Why it could be real: Red-zone touchdown rate is one of the noisiest team stats and snaps back toward average. An underdog whose scoring is dragged down by settling for field goals is better than its points say, and the spread partly prices the points.
Shrunk estimate (100-game prior toward the base): 38% vs base 32% (+7 pts) · family-wide shrinkage: 32% · 2023–25 combined 17/33 vs 33% · broad-search permutation p 0.127
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: the two offenses average 33.4 or fewer points per game combined (bottom 2.5%).
Why it could be real: When neither side can score, a few plays (a turnover, a long field goal, a special-teams swing) decide the game and the talent gap the spread measures matters less.
Shrunk estimate (100-game prior toward the base): 43% vs base 37% (+6 pts) · family-wide shrinkage: 37% · 2023–25 combined 13/25 vs 40% · broad-search permutation p 0.127
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: both offenses are slow between snaps: 60.6+ seconds per play combined (slowest 10%).
Why it could be real: Fewer snaps mean fewer possessions and a noisier result: the better team has fewer chances for its edge to show. Written down as a hypothesis before testing (theory family).
Retired by owner 2026-10-10: the underdog won 7 of 29 in 2026 (4 of 15 since Sep 27, 32% vs a base near 37%).
Shrunk estimate (100-game prior toward the base): 39% vs base 34% (+5 pts) · family-wide shrinkage: 34% · 2023–25 combined 76/214 vs 32% · theory-list permutation p 0.143
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 10 seasons beat the base.
When: the underdog won its previous game this season by 25+ points (top 2.5%).
Why it could be real: A team that just routed someone is often better than the season-long numbers the line leans on, and the market moves only part of the way.
Shrunk estimate (100-game prior toward the base): 43% vs base 37% (+6 pts) · family-wide shrinkage: 38% · 2023–25 combined 16/28 vs 35% · broad-search permutation p 0.127
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 7 of 10 seasons beat the base.
Broad search: 6,425 rules, 34 passed the tail bar vs 33.5 on shuffled results (p 0.413, 1000 shuffles) · Theory list: 28 written-down hypotheses, 0 passed vs 0.08 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. Nothing beat the shuffles for underdog wins by 7+.
Broad search: 6,425 rules, 44 passed the tail bar vs 47.7 on shuffled results (p 0.510, 1000 shuffles) · Theory list: 15 written-down hypotheses, 0 passed vs 0.03 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. Kicker-friendly domes, stout red-zone defenses, conservative coaches, field-goal referee crews and long-kick teams were tested; nothing beat the shuffles for 5+ made / 6+ tried.
Broad search: 6,425 rules, 21 passed the tail bar vs 10.3 on shuffled results (p 0.090, 1000 shuffles) · Theory list: 15 written-down hypotheses, 0 passed vs 0.00 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 7
When: the two offenses average 10.5 or fewer yards per play combined (bottom 20%); and the matchup projects 55.9+ combined carries (top 10%).
Why it could be real: Run-first offenses that don't gain chunk yardage move the chains but stall between the 20s, and conservative play-callers kick there: drives end in field-goal range far more often than in the end zone.
Shrunk estimate (100-game prior toward the base): 15% vs base 9% (+5 pts) · family-wide shrinkage: 9% · 2023–25 combined 9/48 vs 10% · broad-search permutation p 0.090
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 10 seasons beat the base.
Broad search: 6,425 rules, 29 passed the tail bar vs 44.7 on shuffled results (p 0.820, 1000 shuffles) · Theory list: 18 written-down hypotheses, 0 passed vs 0.07 (p 1.000) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 0
Nothing, even at the tail level. Backup QBs, injured starters, eliminated or resting teams, week 18, travel, and collapsing underdogs were tested; fewer blowout rules passed than on shuffled results (p 0.82).
Broad search: 6,425 rules, 65 passed the tail bar vs 72.8 on shuffled results (p 0.583, 1000 shuffles) · Theory list: 15 written-down hypotheses, 1 passed vs 0.06 (p 0.059) · family-wide shrinkage prior 5,000 games · holdout games in kept leans 24
When: the two offenses average 37.2 or fewer points per game combined (bottom 10%).
Why it could be real: Low-scoring teams rarely build big leads, so more of these games are decided by one score than the spread alone suggests. Held in 2016–22 and 2023–24 but was flat in the 2025 holdout. Written down as a hypothesis before testing (theory family).
Shrunk estimate (100-game prior toward the base): 60% vs base 54% (+7 pts) · family-wide shrinkage: 54% · 2023–25 combined 63/103 vs 55% · theory-list permutation p 0.059
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 10 of 10 seasons beat the base.
A second pass over nflverse games: picked on 2015–21, checked on 2022–25, live from Oct 10 2026. 194,737 situations (1,547 single facts, 38,800 pairs, 154,390 triples, each with 50+ discovery games) across 11 results. 9 / 379 / 1,762 passed the discovery bar against 6 / 313 / 1,540 on shuffled results, and 5 / 100 / 364 also held in 2022–25 against 1.6 / 59 / 219, so most survivors are still chance. The real excess sat in the under, the underdog's team-total under and blowouts; spread results (underdog or favorite covers) showed none. On the cards: Wind 10+ mph, open air; the rest are records only until their live record earns more.
When: an open-air game (no dome or closed roof) with wind of 10+ mph at kickoff (the kickoff forecast before the game, the recorded reading after it).
Why it could be real: Wind of 10 mph or more makes deep passes and long field goals less reliable, so drives stall and kicks miss more often. Totals move a little for wind, but in 2015-25 these games still went under well above the rate for similar lines, in 8 of 11 seasons.
Shrunk estimate (100-game prior toward the base): 57% vs base 51% (+6 pts) · 2022–25 holdout 120/207 vs 51% · deep-search permutation p for this result 0.030
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 11 seasons beat the base.
When: an open-air game (no dome or closed roof) at 40°F or colder at kickoff.
Why it could be real: Cold hurts ball handling and the passing game, and an underdog usually has to throw to keep up. Its implied team total has been too high in cold open-air games: above the base in 10 of 11 seasons.
Shrunk estimate (100-game prior toward the base): 56% vs base 50% (+6 pts) · 2022–25 holdout 79/146 vs 49% · deep-search permutation p for this result 0.010
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 10 of 11 seasons beat the base.
When: both teams have won 60%+ of their games this season (3+ played) and won their last game.
Why it could be real: Two winning teams that both won last week tend to be playing well on offense at the same time; the total has not fully caught up with two in-form attacks.
Shrunk estimate (100-game prior toward the base): 57% vs base 48% (+9 pts) · 2022–25 holdout 57/92 vs 47% · deep-search permutation p for this result 0.109
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 8 of 11 seasons beat the base.
When: the favorite is the home team; and it has 3+ more days of rest than the underdog.
Why it could be real: A home favorite with several extra days to prepare (often off a bye or a Thursday game) brings a fuller game plan and fresher legs, and its offense has scored more than the total expects.
Shrunk estimate (100-game prior toward the base): 56% vs base 49% (+8 pts) · 2022–25 holdout 52/84 vs 50% · deep-search permutation p for this result 0.109
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 10 of 11 seasons beat the base.
When: the underdog lost its last game by 20+; and an open-air game (no dome or closed roof).
Why it could be real: After a blowout loss the underdog's defense gets a week of hard film work and the market marks it down; the favorite has scored below its implied team total more often than games on similar lines.
Shrunk estimate (100-game prior toward the base): 58% vs base 51% (+7 pts) · 2022–25 holdout 50/83 vs 50% · deep-search permutation p for this result 0.055
Bars: hit rate each season (green = beat its base, red = didn't); line: base on similar lines. 9 of 11 seasons beat the base.
Machine-learning tails. Gradient boosting and logistic regression on every pregame input, judged only on the games they rated most likely (top 5% by predicted rate minus the line base). A model can miss overall and still find a real extreme slice; these didn't: in 2016–22 (season-by-season cross-validation) the top 5% hit about the base rate for every result.
| Result | Top 5% · 2016–22 | 2023–24 | 2025 |
|---|---|---|---|
| Low scoring (37 or fewer, under the total) | 22/96 (23% vs 26%) | 1/7 (14% vs 34%) | 3/8 (38% vs 26%) |
| Under the total | 37/95 (39% vs 51%) | 13/31 (42% vs 41%) | 18/41 (44% vs 37%) |
| 30 or fewer total points | 10/96 (10% vs 15%) | 2/28 (7% vs 12%) | 0/15 (0% vs 9%) |
| High scoring (51+, over the total) | 29/96 (30% vs 30%) | 8/15 (53% vs 23%) | 2/7 (29% vs 32%) |
| Over the total | 42/95 (44% vs 46%) | 13/39 (33% vs 44%) | 1/2 (50% vs 46%) |
| 60+ total points | 14/96 (15% vs 18%) | 2/20 (10% vs 10%) | 0/1 (0% vs 19%) |
| Upset (underdog wins) | 38/96 (40% vs 34%) | 22/50 (44% vs 34%) | 10/38 (26% vs 27%) |
| Underdog wins by 7+ | 16/96 (17% vs 19%) | 5/33 (15% vs 11%) | 2/19 (11% vs 10%) |
| FG-heavy (5+ made or 6+ tried) | 23/96 (24% vs 25%) | 14/46 (30% vs 18%) | 0/14 (0% vs 16%) |
| 6+ field goals | 8/96 (8% vs 9%) | 3/34 (9% vs 9%) | 1/14 (7% vs 7%) |
| Blowout (17+ margin) | 19/96 (20% vs 24%) | 1/7 (14% vs 24%) | 1/2 (50% vs 18%) |
| One-score game | 46/96 (48% vs 44%) | 7/19 (37% vs 54%) | 3/8 (38% vs 38%) |
Score-distribution model. We turned each closing line into tail probabilities (30 or fewer points, 60+, underdog by 7+, blowout, one-score) from how far real games landed from their lines, then let a model widen or narrow that spread game by game from the team stats. Its predicted volatility did not track how wild games actually were (correlation about zero in every split), and games it called "fatter-tailed" were not.
Line movement. Opening lines exist only for 2016–21 here, so movement rules could be explored but never checked on later seasons; none are used.
Over / under combinations of our chips, the book total and the stat trends, tested on every regular-season game 2016–24 with 2025 held out, using our walk-forward pregame number (no lookahead) and the closing line. A combo gets a card chip only if it clears the same bar as the Stat Trends: 60+ games, 6+ points above similar lines with the 90% lower bound above them, the 2025 holdout above its base, and no more than 2 losing seasons.
| Combo | 2016–24 | Similar lines | 2025 | 2026 | Result |
|---|---|---|---|---|---|
| (a) 🔥 Over Combo: Sweet Spotedge +2.0 to +3.5 + no under tail lean → over the closing total | 38-45 (46%) | 50% | 6-12 (33% vs 51%) | 3-10 | Did not survivenot significant (one-sided p=0.79) |
| (b) 🔥 Over Combo: High Book, No Trendno Super Trend + book total 48+ → over the closing total | 202-246-5 (45%) | 48% | 20-17 (54% vs 52%) | 6-3 | Did not survivenot significant (one-sided p=0.92) |
| (c) 🔥 Over Combo: Clean ShootoutShootout chip (our total 50+) + no Super Trend → over the closing total | 77-106-2 (42%) | 48% | 10-9 (53% vs 51%) | 4-1 | Did not survivenot significant (one-sided p=0.96) |
| (d) 🧊 Under Combo: Trend Shootouta Super Trend + Shootout chip (our total 50+) → under the closing total | 39-53-2 (42%) | 51% | 6-7 (46% vs 49%) | 1-4 | Did not survivetoo small (train n=92, 2025 n=13) |
| (e) 🧊 Under Combo: Thin Edgeour total above the book by less than 2.0 → under the closing total | 597-545-9 (52%) | 51% | 71-78 (48% vs 48%) | 15-17 | Did not survivenot significant (one-sided p=0.27) |
| (f) edge above +4.0edge above +4.0 → under the closing total | 0-0 (–) | – | 1-1 (50% vs 45%) | – | Did not survivetoo small (train n=0, 2025 n=2) |
| (f2) edge above +4.0 with a book total of 42 or loweredge above +4.0 + book total 42 or lower → under the closing total | 0-0 (–) | – | 1-1 (50% vs 45%) | – | Did not survivetoo small (train n=0, 2025 n=2) |
| (g) book total 38.5 or lowerbook total 38.5 or lower → under the closing total | 83-76-1 (52%) | 50% | 13-11 (54% vs 49%) | 3-1 | Did not survivenot significant (one-sided p=0.36) |
| (fg) 🧊 Under Combo: Low Total Trapedge above +4.0 and book total 42 or lower — or — book total 38.5 or lower → under the closing total | 83-76-1 (52%) | 50% | 14-11 (56% vs 49%) | 3-1 | Did not survivenot significant (one-sided p=0.36) |
| (h) 🧊 Under Combo: Weather Overrideunder tail lean (rain/snow, or wind 10+ open air) + Model leans over chip → under the closing total | 2-7 (22%) | 46% | 0-2 (0% vs 42%) | – | Did not survivetoo small (train n=9, 2025 n=2) |
| (i) 🧊 Under Combo: No Ground GameSuper Trend "Neither side runs much or well" → under the closing total | 91-110 (45%) | 51% | 3-12 (20% vs 46%) | 2-1 | Did not survivenot significant (one-sided p=0.96) |
| (j) 🔥 Over Combo: High-Total ShootoutShootout chip (our total 50+) + our total 49+ + book total 49+ + home spread -7.5 to +7 (no favorite bigger than 7.5) → over the closing total | 113-114-3 (50%) | 49% | 12-11 (52% vs 50%) | 6-0 | Did not survivenot significant (one-sided p=0.49) |
| (fh) Favorite holds chipFavorite holds chip → favorite covers | 725-776-43 (48%) | 49% | 86-96 (47% vs 49%) | 16-19-5 | Did not survivenot significant (one-sided p=0.66) |
| (fh_over) Favorite holds and Model leans overFavorite holds chip + Model leans over chip → favorite covers | 6-9 (40%) | 49% | 0-2 (0% vs 55%) | – | Did not survivetoo small (train n=15, 2025 n=2) |
| (k) 🐶 Underdog Combo: Holds + OverFavorite holds chip + Model leans over chip → underdog covers | 9-6 (60%) | 51% | 2-0 (100% vs 45%) | – | Did not survivetoo small (train n=15, 2025 n=2) |
| (fh_fade) Favorite holdsFavorite holds chip → underdog covers | 776-725-43 (52%) | 51% | 96-86 (53% vs 51%) | 19-16-5 | Did not survivenot significant (one-sided p=0.36) |
Favorite holds: We expect the favorite to win outright: it did 71% of the time in 2016–24 (all favorites 67%). Not a spread pick: these favorites covered 48%, the same as similar lines (49%).
Records are W-L-P (pushes counted apart). Records only, not advice · 21+. Study 2026-10-11.
Every one- and two-part combination (three-part ones were tested too) of the board's pregame building blocks (both teams' league-rank thirds frozen before kickoff and the offense-vs-defense edges between them, line / total / implied-total buckets, our walk-forward number vs the line, venue, division game, rest, roof, recorded kickoff weather, season stage, each team's last result and cover) is searched on 2016–2021 (1548 regular-season games with a closing line) for six outcomes (favorite / underdog wins and covers, over, under). A condition is kept only if it hit 75%+ on at least the sample bar (0–50 games, set per outcome and tier where shuffled results produce fewer than one by chance), the record is under 1% likely from the line alone (big favorites winning doesn't count), and it then held up on 2022–2025 (1087 games it never saw). 2026 (107 games so far) is the untouched test record.
Luck check: the whole pipeline on 10 shuffles of the results (moved only between games with similar spreads) keeps 0 conditions per shuffle by chance. Real run (2026-10-27): 0 survivors. Walk-forward (each season searched only on the seasons before it): 0-0 on 0 flagged games across 7 seasons. Player conditions use the same guards on 2021–2023 player games, validated on 2024–2025 and tested on 2026: 0 kept, 0.1 per shuffle by chance. Re-run by the weekly refresh. Records only, not advice.
No game condition survived the multi-season guards. The board's 🔥 chip stays at 0 until one does: most strong spots found on old seasons fall back to a coin flip on later ones.
Each badge type's record on games the model never saw, next to how often a typical player landed on that side of his own season average.
| Badge | 2025 | 2026 | 2025–26 | Typical | 2021–23 / 2024 | Status |
|---|---|---|---|---|---|---|
| 🎯 High passing yards | 20-12 (63%) · 3 void | 7-4 (64%) | 27-16 (63%) · 3 void | 52% | 33-27 (55%) · 4 void / 13-8 (62%) · 1 void | On cards |
| 🧊 Low passing yards | 121-108 (53%) · 16 void | 14-7 (67%) | 135-115 (54%) · 16 void | 48% | 447-283 (61%) · 54 void / 123-124 (50%) · 13 void | Dropped |
| 🏃 High rushing yards | 22-12 (65%) · 3 void | 5-4 (56%) | 27-16 (63%) · 3 void | 42% | 82-52 (61%) · 1 void / 15-12 (56%) | On cards |
| 🧱 Low rushing yards | 63-34 (65%) · 9 void | 6-3 (67%) · 2 void | 69-37 (65%) · 11 void | 58% | 218-80 (73%) · 50 void / 92-31 (75%) · 12 void | On cards |
| 🙌 High receiving yards | 1-0 (100%) | 2-0 (100%) | 3-0 (100%) | 40% | 1-2 (33%) / 2-2 (50%) | Dropped |
| 🔒 Low receiving yards | 176-82 (68%) · 38 void | 44-20 (69%) · 9 void | 220-102 (68%) · 47 void | 60% | 565-242 (70%) · 93 void / 215-102 (68%) · 28 void | On cards |
| 🧲 High receptions | 0-0 (–) | 0-0 (–) | 0-0 (–) | 40% | 0-0 (–) / 0-0 (–) | Dropped |
| 🪫 Low receptions | 177-84 (68%) · 15 void | 86-44 (66%) · 6 void | 263-128 (67%) · 21 void | 60% | 481-233 (67%) · 44 void / 159-91 (64%) · 8 void | On cards |
| 📈 Receptions leader | 42-45 (48%) · 2 void | 7-14 (33%) | 49-59 (45%) · 2 void | 18% | 125-147 (46%) · 7 void / 42-42 (50%) · 1 void | Dropped |
| 🏈 TD threat | 35-45 (44%) · 2 void | 15-11 (58%) | 50-56 (47%) · 2 void | 33% | 115-115 (50%) · 8 void / 58-43 (57%) · 2 void | Dropped |
Fitted on 2021, 2022, 2023, thresholds set on 2024, tested on 2025 and 2026 (never used for fitting). "Typical" = how often any eligible player landed on that side of his own season average. A badge type shows on cards only at 55%+ on 30+ test badges and above the typical rate. Void = the player didn't play. Records only, not advice.