TrackSmart AI: Cumulative Performance Report - NYRA & Regional Tracks

Reporting Period: December 26, 2025 – May 25, 2026

Track: Belmont at the Big A (BAQ) / Finger Lakes (FL) / Aqueduct (AQU) / Laurel Park (LRL) / Santa Anita Park (SA)

1. Executive Summary: May 25 Update

• Volume Expansion: The tracking dataset has grown to 764 total races with the addition of 75 races run across Belmont at the Big A, Finger Lakes, and the newly integrated Santa Anita Park from May 18 through May
• Strike Rate Resilience: The cumulative Top 4 Strike Rate held impressively steady at 78.5% (600 for 764). The model secured a flawless 100% accuracy card at Finger Lakes (May 25) and hit 90% cards at both Belmont at the Big A (May 23) and Santa Anita Park (May 25), effectively neutralizing the variance seen on highly chaotic mid-week slates.
• Value Normalization: The Average Payout for AI hits climbed to ~$7.72 (up from ~$7.62). Specialized off-track condition alerts, extreme mud upgrades, and dynamic scratch re-rankings helped the algorithm isolate massive value overlays this week, including Rock the Weekend ($23.68) at BAQ, Mia Nipotina ($23.66) at FL, and Novinophobia ($21.40) at SA.
• System Integrity and Updates: Execution of the dynamic scratch adjustment protocol was critical this week. The system flawlessly promoted lower-ranked alternates into the top tiers across multiple days filled with heavy surface changes and off-the-turf scratches, preserving the hit rate and capturing longshot beneficiaries that would have otherwise fallen out of exotic structures.

2. Daily Performance Breakdown

(Note: Prior totals reflect cumulative data up to May 17. Daily breakdowns from previous reports have been condensed into the Prev. Totals row. Live scratch protocols dynamically shifted runners up in rankings across multiple races this week, securing numerous top-tier hits.)

3. Winner Distribution by Rank (Cumulative)

4. Cumulative Statistics Summary

5. Aggregate Observations: May 18 - May 25 Insights

• Dynamic Scratch Adjustments Proved Essential: With widespread weather volatility heavily impacting cards (especially on May 23-25), the user rule to slide "Field Summary" horses into vacated spots preserved hit rates and caught massive This mechanical promotion directly resulted in top-tier payouts from runners like Fairy Godmother ($12.96), Trading Strategy ($7.86), and All Busted Up ($5.56).
• Off-Track & Pace Bias Success: The AI properly anticipated that off-track conditions would aggressively inflate the value of inside early speed on sloppy dirt, sniffing out heavy modifiers to find winners like Gresham's Law ($23.32) and Ashcroft Lane ($15.26). It also accurately flagged "Bet of the Day" off-track upgrades, specifically isolating Rock the Weekend for a $23.68 win via the "+6 Proven Mudder" angle.
• Vulnerabilities in Baseline Profiling: Deep dives into claiming ranks revealed that severe baseline penalties applied to basement-level claimers ($5k maidens) and horses returning from 180+ day "reset" layoffs are occasionally too harsh, blinding the AI to dramatic form reversals like Dignified Response (28-1) and Seventh Race The form-collapse penalty algorithms need slight softening for low-level maidens.
• Lone Speed on Turf Failsafes: While the AI correctly predicted destructive "Contested/Fast" meltdowns perfectly (nailing Mia Nipotina for $23.66), the model remains vulnerable to unpressured lone speed in turf High-profile trainers stretching early-speed runners out on yielding turf (e.g., Versailles Road at 32-1) require a dynamic pace-remapping feature to respect uncontested front-runners.

TrackSmart AI: Cumulative Performance Report - NYRA & Regional Tracks

Reporting Period: December 26, 2025 – May 31, 2026

Track: Belmont at the Big A (BAQ) / Finger Lakes (FL) / Aqueduct (AQU) / Laurel Park (LRL) / Santa Anita Park (SA) / Penn National (PEN) / Saratoga Harness (SARH) / Woodbine (WO)

1. Executive Summary: May 31 Update

• Volume Expansion: The tracking dataset has grown to 840 total races with the addition of 76 races run across Finger Lakes, Penn National, Santa Anita Park, Saratoga Harness, and Woodbine from May 27 through May
• Strike Rate Resilience: The cumulative Top 4 Strike Rate held impressively steady at 78.6% (660 for 840). The model secured another flawless 100% accuracy card at Finger Lakes (May 27) and hit dominant ~90% cards at both Santa Anita Park and Saratoga Harness on May 31, successfully translating its logic across dirt, turf, synthetic, and harness racing.
• Value Normalization: The Average Payout for AI hits stabilized to ~$7.59 (down slightly from ~$7.72). While payouts were depressed in the middle of several chalky cards where logical favorites delivered, excellent value retention was achieved by capitalizing on pace meltdowns to catch overlays like Sinclairity ($11.90) at WO, Quantum Innergy ($10.80) at SA, and Dressed To Kill ($6.60) at
• System Integrity and Updates: Execution of the dynamic scratch adjustment protocol was highly lucrative this week. The system flawlessly promoted Alternate (4th) selections into the primary Top 3 tiers across multiple slates, securing outright wins from horses like Sunset Storm, Miso Phansy, and Strawberry Treat that would have otherwise fallen off the board.

2. Daily Performance Breakdown

(Note: Prior totals reflect cumulative data up to May 25. Daily breakdowns from previous reports have been condensed into the Prev. Totals row. Live scratch protocols dynamically shifted runners up in rankings across multiple races this week, securing numerous top-tier hits. Finger Lakes May 27 includes a Dead Heat adjustment.)

3. Winner Distribution by Rank (Cumulative)

4. Cumulative Statistics Summary

5. Aggregate Observations: May 27 - May 31 Insights

• The Power of the Alternate (Scratch Protection): The automated scratch adjustment rule proved massively valuable this As massive favorites or top selections scratched out, the AI vaulted algorithmic alternates into the Top 3 slots. This mechanical promotion directly salvaged multi-race exotics by catching winners like Dressed To Kill ($6.60), Strawberry Treat ($6.80), Sunset Storm ($3.40), and Miso Phansy ($4.80).
• Track Bias & Geometry Capitalization: The model was incredibly dialed in on specific track geometries this At Saratoga Harness, the AI heavily rewarded inside draws and pocket trips ("The Golden Chair"), accurately predicting wire-to-wire runs. At Woodbine, the system successfully weaponized the all-weather synthetic bias, locking onto horses holding a raw algorithmic speed advantage from inside posts.
• Pace Meltdowns and Duel Projections: The flow algorithms performed exceptionally well when reading dirt and synthetic sprints. The system perfectly diagnosed contested early fractions and destructive early duels, successfully cashing on off-the-pace stalkers and sweepers like Sinclairity ($11.90) at Woodbine and various late-kick beneficiaries at Santa Anita.
• Turf Route Blind Spots: While the model hit high-priced turf winners like Bandiagara (GB) for $14.40 at Penn National, 1-mile turf routes remain a notable The AI struggled by aggressively favoring deep closers with high stamina ratings on firm turf that ultimately held early and tactical speed far better than historical pars suggested. Re-evaluation of the "turf route penalty" algorithm is needed so inside speed and outside-stalking profiles are not automatically downgraded for distance.

TrackSmart AI: Cumulative Performance Report - NYRA & Regional Tracks

Reporting Period: December 26, 2025 – June 7, 2026

Track: Belmont at the Big A (BAQ) / Finger Lakes (FL) / Aqueduct (AQU) / Laurel Park (LRL) / Santa Anita Park (SA) / Penn National (PEN) / Saratoga Harness (SARH) / Woodbine (WO) / Saratoga (SAR)

1. Executive Summary: June 7 Update

• Volume Expansion: The tracking dataset has grown to 924 total races with the addition of 84 races run across Finger Lakes and Saratoga from June 1 through June
• Strike Rate Resilience: The cumulative Top 4 Strike Rate maintained a strong level at 77.33% (714 for 924). The model secured another flawless 100% accuracy card at Finger Lakes on June 3 (8 for 8), and hit an impressive 87.5% at Finger Lakes on June 1. Saratoga proved slightly more challenging with larger fields and unpredictable turf dynamics, but the model consistently placed the winner in the top 4 over 50% of the time, peaking at 72.7% on multiple cards.
• Value Normalization: The Average Payout for AI hits rose to ~$7.73 (up from ~$7.59). Excellent value retention and massive overlay identification were achieved this week, capturing astronomical payouts like Pillar of Beauty ($56.86) and Buttah ($60.66) as deeper selections, as well as catching My Gun's Loaded ($38.02) and Bonus Move ($30.42) at Saratoga.
• System Integrity and Updates: The automated scratch adjustment protocol was absolutely essential this week. Moving up Alternate selections into the active Top 3 directly salvaged massive wins and multi-race exotics, securing outright wins from horses like Colten Goes ($7.88), Bonus Move ($30.42), New York Scrappy ($22.90), and King Farro ($9.28).

2. Daily Performance Breakdown

(Note: Prior totals reflect cumulative data up to May 31. Daily breakdowns from previous reports have been condensed into the Prev. Totals row. Live scratch protocols dynamically shifted runners up in rankings across multiple races this week, securing numerous top-tier hits.)

3. Winner Distribution by Rank (Cumulative)

4. Cumulative Statistics Summary

5. Aggregate Observations: June 1 - June 7 Insights

• The Power of the Alternate (Scratch Protection): The automated scratch adjustment rule proved indispensable this By promoting algorithmic alternates into the Top 3/4 slots when primary selections scratched, the system dynamically caught high-priced winners like Bonus Move ($30.42), New York Scrappy ($22.90), Colten Goes ($7.88), and King Farro ($9.28) that would have otherwise fallen out of exotic structures.
• Pace Meltdown Projections & Turf Dynamics: The AI excelled at anticipating pace meltdowns and correctly mapping out "Turf LP Dominator" trips (e.g., Right to Vote, Mo Complex). However, on specific turf routes at Saratoga, early speed held remarkably well, causing the model to over-penalize early speed and wide Adjusting turf friction algorithms and capping extreme draw penalties for top Prime Power horses is recommended to clean up slight misses.
• Identifying Massive Value & Chaos: Despite larger field complexities at Saratoga, the AI proved its ability to locate massive Finding Pillar of Beauty ($56.86) and Buttah ($60.66) as deeper alternate selections emphasizes the potency of the model's depth chart when chaotic fractions collapse the front end.
• Lone Speed Vulnerability and Break Dependency: The model occasionally struggled in sprints when heavily projected "Lone Speed" runaways missed the break or were scratched, completely fracturing the race Implementing dynamic recalculation of pace flow scenarios upon heavy favorite scratches, or incorporating a "break-dependency risk" penalty for one-dimensional speed horses, will strengthen secondary selection viability.

TrackSmart AI: Cumulative Performance Report - NYRA & Regional Tracks

Reporting Period: December 26, 2025 – June 14, 2026

Track: Belmont at the Big A (BAQ) / Finger Lakes (FL) / Aqueduct (AQU) / Laurel Park (LRL) / Santa Anita Park (SA) / Penn National (PEN) / Saratoga Harness (SARH) / Woodbine (WO) / Saratoga (SAR)

1. Executive Summary: June 14 Update

• Volume Expansion: The tracking dataset has grown to 986 total races with the addition of 62 races run across Finger Lakes and Belmont at the Big A from June 8 through June
• Strike Rate Resilience: The cumulative Top 4 Strike Rate increased slightly to 77.6% (765 for 986). The AI model turned in a spectacular week, highlighted by a flawless 100% accuracy card at Belmont at the Big A on June 11 (8 for 8), a 90% hit rate on June 12, and an 88.9% hit rate on June 14. Finger Lakes also provided consistent yields with an 87.5% hit rate on June 9.
• Value Normalization: The Average Payout for AI hits remained incredibly steady at ~$7.70 (down minimally from

~$7.73). Massive overlay identification anchored the week, catching astronomical payouts like Successful Agenda ($40.92) on the June 11 card as a 3rd selection, as well as multiple mid-priced winners hitting precisely as top choices.

• System Integrity and Updates: The automated scratch adjustment protocol continued to operate Moving up Alternate selections cleanly absorbed heavy scratch volume on the June 11 and June 14 Belmont cards, actively securing top-tier hits and salvaging multi-race exotics.

2. Daily Performance Breakdown

(Note: Prior totals reflect cumulative data up to June 7. Daily breakdowns from previous reports have been condensed into the Prev. Totals row. Live scratch protocols dynamically shifted runners up in rankings across multiple races this week, securing numerous top-tier hits.)

3. Winner Distribution by Rank (Cumulative)

4. Cumulative Statistics Summary

5. Aggregate Observations: June 8 - June 14 Insights

• Incredible Accuracy & Flawless Sweeps: The AI Engine was incredibly dialed in early/mid-week. It turned in an absolute flawless 8-for-8 performance on June 11 at BAQ (with 6 of those being 1st choices) and successfully isolated 9 of 10 winners on June 12.
• Track Bias Shifts & Late Pace Dominance: The model expertly mapped race environments. It correctly flagged a dominant 100% wire/rail bias at Finger Lakes on June 9 and utilized its "Late Pace (TSLP)" algorithms to isolate late-kick dynamics on the BAQ turf, finding perfectly setup closers.
• Catching Bombs via Deep Alternates: The model's third selections proved extremely potent for identifying hidden value. The absolute highlight of the week was finding Successful Agenda ($40.92) based on an "elite trainer intent" upgrade, completely diagnosing a turnaround effort.
• Chaos Immunity & Vulnerabilities: While the machine comfortably locked onto logical short/mid-priced winners, it proved vulnerable to extreme un-modeled Complete meltdowns and massive form reversals by horses like Mission Improbable ($58.28), Blue Pill ($44.16), and Retail Man ($51.36) bypassed the standard TS Speed baselines and TSLP algorithms.
• Scratch Protection Mechanics: Automated adjustment rules proved indispensable again. By efficiently promoting algorithmic alternates into the Top 3/4 slots, the structure cleanly absorbed heavy scratches (specifically on June 11 and 14), keeping horizontal and vertical tickets alive without losing structural integrity.