One day, one result: the production stack priced the whole field under 1 course reading, against the market's line where one was captured. A one-day race is its own best reference — the main reading is built from this race's own recent editions.
The fork
Course profile is an input the model cannot see from a map — it is set from reference races. The main reading averages this race's own last editions, so the terrain and the kind of rider it selects come from the race's own history; any alternate reading swaps in an archetype set to ask what a different day would do to the same field.
The board
Blend is the production price (cascade × LambdaRank, DNF-adjusted at the pricing layer); Cascade and LambdaRank are the two underlying heads shown for the main reading. The market columns are the devigged win line, present as the information benchmark the model is scored against.
Read "Max edge" as directional, not as a price. The blend is a set of per-rider marginals and does not sum to one book — across this field each reading totals hindsight 141% — while the devigged market column sums to exactly 100%. Putting the two side by side flatters the model, and Max edge is inflated by about that factor. Of our heads only the LambdaRank one is natively book-preserving.
| Rider | Team | Blend | Cascade | LambdaRank | Market odds | Market devig | Max edge |
|---|---|---|---|---|---|---|---|
| Kooij Olav | DECATHLON CMA CGM TEAM | 47.2% | 45.3% | 33.8% | n/a | – | – |
| Magnier Paul | Soudal Quick-Step | 45.0% | 47.6% | 31.1% | n/a | – | – |
| Lonardi Giovanni | Team Polti VisitMalta | 10.3% | 8.4% | 7.7% | n/a | – | – |
| Fretin Milan | Cofidis | 9.8% | 9.7% | 6.9% | n/a | – | – |
| Vernon Ethan | NSN Cycling Team | 4.4% | 3.5% | 3.3% | n/a | – | – |
| Wærenskjold Søren | Uno-X Mobility | 3.7% | 3.2% | 2.7% | n/a | – | – |
| Bittner Pavel | Team Picnic PostNL | 2.9% | 2.9% | 2.1% | n/a | – | – |
| Penhoët Paul | Groupama-FDJ United | 2.0% | 2.0% | 1.4% | n/a | – | – |
| Bol Cees | Decathlon CMA CGM Team | 1.7% | 1.2% | 1.3% | n/a | – | – |
| de Kleijn Arvid | Tudor Pro Cycling Team | 1.6% | 1.3% | 1.2% | n/a | – | – |
| Bennett Sam | Pinarello-Q36.5 Pro Cycling Team | 1.5% | 3.9% | 0.5% | n/a | – | – |
| Moschetti Matteo | Pinarello-Q36.5 Pro Cycling Team | 1.3% | 1.3% | 1.0% | n/a | – | – |
| Mozzato Luca | Tudor Pro Cycling Team | 1.2% | 0.8% | 0.9% | n/a | – | – |
| # | Rider | Blend | Cascade | LambdaRank | Podium | Top 15 | Market odds |
|---|---|---|---|---|---|---|---|
| 1 | Kooij Olav | 47.2% | 45.3% | 33.8% | 68.7% | 85.3% | n/a |
| 2 | Magnier Paul | 45.0% | 47.6% | 31.1% | 67.3% | 84.2% | n/a |
| 3 | Lonardi Giovanni | 10.3% | 8.4% | 7.7% | 29.2% | 71.8% | n/a |
| 4 | Fretin Milan | 9.8% | 9.7% | 6.9% | 25.4% | 68.7% | n/a |
| 5 | Vernon Ethan | 4.4% | 3.5% | 3.3% | 12.6% | 46.8% | n/a |
| 6 | Wærenskjold Søren | 3.7% | 3.2% | 2.7% | 11.5% | 52.2% | n/a |
| 7 | Bittner Pavel | 2.9% | 2.9% | 2.1% | 14.9% | 65.2% | n/a |
| 8 | Penhoët Paul | 2.0% | 2.0% | 1.4% | 10.2% | 56.9% | n/a |
| 9 | Bol Cees | 1.7% | 1.2% | 1.3% | 5.6% | 30.8% | n/a |
| 10 | de Kleijn Arvid | 1.6% | 1.3% | 1.2% | 6.2% | 34.4% | n/a |
| 11 | Bennett Sam | 1.5% | 3.9% | 0.5% | 7.8% | 35.2% | n/a |
| 12 | Moschetti Matteo | 1.3% | 1.3% | 1.0% | 7.4% | 46.8% | n/a |
| 13 | Mozzato Luca | 1.2% | 0.8% | 0.9% | 4.1% | 37.8% | n/a |
| 14 | Thijssen Gerben | 1.0% | 1.3% | 0.6% | 7.5% | 56.0% | n/a |
| 15 | Tesson Jason | 1.0% | 1.1% | 0.7% | 5.8% | 43.6% | n/a |
| 16 | Gudmestad Tord | 0.9% | 0.9% | 0.7% | 5.2% | 34.8% | n/a |
| 17 | Blikra Erlend | 0.7% | 0.9% | 0.4% | 5.7% | 34.5% | n/a |
| 18 | Grisel Matys | 0.7% | 0.9% | 0.4% | 5.4% | 43.1% | n/a |
| 19 | Aniolkowski Stanislaw | 0.4% | 0.5% | 0.2% | 6.1% | 39.8% | n/a |
| 20 | Taminiaux Lionel | 0.4% | 0.1% | 0.3% | 1.2% | 22.8% | n/a |
| 21 | Kockelmann Mathieu | 0.4% | 0.3% | 0.3% | 2.5% | 39.4% | n/a |
| 22 | Huens Axel | 0.2% | 0.2% | 0.2% | 1.4% | 23.9% | n/a |
| 23 | Belletta Dario | 0.2% | 0.2% | 0.2% | 1.4% | 35.9% | n/a |
| 24 | Stewart Jake | 0.2% | 0.3% | 0.1% | 2.3% | 22.3% | n/a |
| 25 | Müller Tobias | 0.2% | 0.1% | 0.1% | 1.9% | 29.9% | n/a |
| 26 | Peñalver Manuel | 0.2% | 0.1% | 0.1% | 1.2% | 25.0% | n/a |
| 27 | Serrano Javier | 0.1% | 0.1% | 0.1% | 1.5% | 34.2% | n/a |
| 28 | Degenkolb John | 0.1% | 0.2% | 0.1% | 0.7% | 17.0% | n/a |
| 29 | Milan Matteo | 0.1% | 0.1% | 0.1% | 1.4% | 25.3% | n/a |
| 30 | Heremans Joppe | 0.1% | 0.1% | 0.1% | 1.0% | 22.5% | n/a |
After the race
| Pos | Rider | Team | Hindsight (post-hoc) win p |
|---|---|---|---|
| 1 | de Kleijn Arvid | Tudor Pro Cycling Team | 1.6% |
| 2 | Müller Tobias | Unibet Rose Rockets | 0.2% |
| 3 | Vernon Ethan | NSN Cycling Team | 4.4% |
| 4 | Bittner Pavel | Team Picnic PostNL | 2.9% |
| 5 | Moschetti Matteo | Pinarello-Q36.5 Pro Cycling Team | 1.3% |
| 6 | Lonardi Giovanni | Team Polti VisitMalta | 10.3% |
| 7 | Konijn Alexander | Nice Métropole Côte d'Azur | 0.0% |
| 8 | Thijssen Gerben | Alpecin-Premier Tech | 1.0% |
| 9 | Ghys Robbe | Decathlon CMA CGM Team | 0.0% |
| 10 | Marsman Tim | Alpecin-Premier Tech | 0.0% |
| Reading | Blend | Cascade | LambdaRank | Market devig |
|---|---|---|---|---|
| Hindsight (post-hoc) | 1.56% | 1.33% | 1.16% | – |
Result rows are joined to the boards by FirstCycling rider id through the riders table. 0 row(s) needed the normalised-name fallback; 1 finisher(s) could not be matched at all.