Cycling race predictor · one-day race

Gran Piemonte settled

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.

Raced 8 October 2026 1 reading 168 riders priced models retrained 72bc1bd857 market snapshot no capture

The fork

1 reading of the same road

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.

Own history

Gran Piemonte on its own recent editions
sprint0.01
mountain0.14
hilly0.03
rolling0.55
break0.27
TT0.00
References: Gran Piemonte (2025); Gran Piemonte (2024); Gran Piemonte (2023); Gran Piemonte (2022); Gran Piemonte (2021)
The race read on its own recent history: the profile is the average of this race's last 5 editions, so the terrain and the kind of rider it selects come from the race itself rather than from an archetype.
Top 5 (blend): del Toro Isaac 37.6%; Grégoire Romain 9.2%; Silva Thomas 7.0%; Pedersen Mads 6.3%; Johannessen Tobias Halland 3.8%

The board

Win probabilities across the heads

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 own history 124% — 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.

RiderTeamBlendCascadeLambdaRankMarket oddsMarket devigMax edge
del Toro IsaacUAE Team Emirates-XRG37.6%38.7%29.9%n/a––
Grégoire RomainGroupama-FDJ United9.2%10.8%7.0%n/a––
Silva ThomasXDS Astana Team7.0%2.9%6.6%n/a––
Pedersen MadsLidl-Trek6.3%15.2%2.8%n/a––
Johannessen Tobias HallandUno-X Mobility3.8%1.7%3.6%n/a––
Godon DorianNetcompany INEOS3.8%6.3%2.4%n/a––
Pithie LaurenceRed Bull-BORA-hansgrohe3.7%4.0%2.9%n/a––
Hirschi MarcTudor Pro Cycling Team3.6%2.2%3.3%n/a––
McNulty BrandonUAE Team Emirates-XRG3.6%3.8%2.8%n/a––
Cosnefroy BenoîtUAE Team Emirates-XRG2.8%2.9%2.3%n/a––
Zambanini EdoardoBahrain Victorious2.4%0.8%2.3%n/a––
Matthews MichaelTeam Jayco-AlUla2.3%4.4%1.4%n/a––
Strong CorbinNSN Cycling Team2.2%1.9%1.9%n/a––
Vendrame AndreaTeam Jayco-AlUla1.9%2.2%1.4%n/a––
Narvaez JhonnatanUAE Team Emirates-XRG1.7%1.2%1.6%n/a––
Morgado AntónioUAE Team Emirates-XRG1.7%2.8%1.1%n/a––
Oldani StefanoCaja Rural-Seguros RGA1.7%1.3%1.5%n/a––
Schmid MauroTeam Jayco-AlUla1.6%2.9%1.0%n/a––
Tesfazion NatnaelMovistar Team1.5%0.5%1.5%n/a––
Honore MikkelEF Education-EasyPost1.0%0.9%0.9%n/a––
Gran Piemonte on its own recent editions — top 30, all heads
#RiderBlendCascade LambdaRankPodiumTop 15 Market odds
1del Toro Isaac37.6%38.7%29.9%54.7%77.4%n/a
2Grégoire Romain9.2%10.8%7.0%25.0%53.2%n/a
3Silva Thomas7.0%2.9%6.6%13.1%39.3%n/a
4Pedersen Mads6.3%15.2%2.8%25.3%46.6%n/a
5Johannessen Tobias Halland3.8%1.7%3.6%6.0%29.3%n/a
6Godon Dorian3.8%6.3%2.4%15.0%42.4%n/a
7Pithie Laurence3.7%4.0%2.9%13.1%36.8%n/a
8Hirschi Marc3.6%2.2%3.3%7.0%34.2%n/a
9McNulty Brandon3.6%3.8%2.8%9.2%28.3%n/a
10Cosnefroy Benoît2.8%2.9%2.3%10.7%38.5%n/a
11Zambanini Edoardo2.4%0.8%2.3%4.5%33.4%n/a
12Matthews Michael2.3%4.4%1.4%9.4%35.7%n/a
13Strong Corbin2.2%1.9%1.9%9.0%37.6%n/a
14Vendrame Andrea1.9%2.2%1.4%7.5%38.0%n/a
15Narvaez Jhonnatan1.7%1.2%1.6%3.4%21.0%n/a
16Morgado António1.7%2.8%1.1%9.8%31.4%n/a
17Oldani Stefano1.7%1.3%1.5%4.2%32.7%n/a
18Schmid Mauro1.6%2.9%1.0%8.7%26.9%n/a
19Tesfazion Natnael1.5%0.5%1.5%2.4%25.3%n/a
20Honore Mikkel1.0%0.9%0.9%4.6%19.4%n/a
21Trentin Matteo0.9%2.1%0.5%3.4%23.3%n/a
22Miquel Delgado Pau0.9%0.5%0.8%2.7%22.4%n/a
23Costiou Ewen0.9%0.4%0.8%2.6%17.1%n/a
24Belletta Dario0.9%0.4%0.8%2.2%19.0%n/a
25Nerurkar Lukas0.8%0.8%0.6%2.4%19.3%n/a
26Teuns Dylan0.7%0.3%0.7%1.4%13.9%n/a
27Laurance Axel0.7%0.3%0.6%2.6%19.2%n/a
28Fisher-Black Finn0.6%0.8%0.5%2.2%14.1%n/a
29Turconi Filippo0.6%0.3%0.6%0.8%11.1%n/a
30Maisonobe Sam0.6%0.3%0.6%2.4%10.7%n/a

After the race

Result — won by Godon Dorian

PosRiderTeamOwn history win p
1Godon DorianNETCOMPANY INEOS3.8%
2Charmig AnthonUNO-X MOBILITY–
3Bettiol AlbertoXDS ASTANA TEAM0.2%
4Nerurkar LukasEF EDUCATION - EASYPOST0.8%
5Hermans QuintenPINARELLO-Q36.5 PRO CYCLING TEAM–
6WRIGHT Alfred BrockwellPINARELLO-Q36.5 PRO CYCLING TEAM–
7Eulalio AfonsoBAHRAIN VICTORIOUS–
8Matthews MichaelTEAM JAYCO ALULA2.3%
9Narvaez JhonnatanUAE TEAM EMIRATES XRG1.7%
10Marti PauNSN CYCLING TEAM0.2%

1 rider in the top 15 is shown under a provisional identity pending reconciliation: WRIGHT Alfred Brockwell.

Scoring — probability given to the actual winner

ReadingBlendCascade LambdaRankMarket devig
Own history3.76%6.32%2.38%–

Result rows are joined to the boards by FirstCycling rider id through the riders table. 0 row(s) needed the normalised-name fallback; 2 finisher(s) could not be matched at all.