The cold read
The opening assessment uses the horses’ form and the known race conditions. It has not yet seen how this meeting is unfolding. Treat the morning card as a starting point.
THE SATURDAY EXPERIMENT / READING GUIDE
Make sense
of the cards.
Start with the four. Keep the uncertainty in view.
How the race day works
The first read is the starting point.
The model rules stay fixed for the meeting. New evidence from earlier races can change the calls for races still to come.
Refresh the next races
Once an earlier race is final, the day layer reassesses the remaining races using that result. Emerging jockey, stable and barrier patterns can change the percentages, order or membership of the four.
Check again after each earlier result and before your race jumps. A new assessment can also leave the picks unchanged. Interim results do not count.
The call is frozen
That race’s last issued selections stay on the record. Its eventual result can inform later races, but it cannot rewrite its own prediction.
For Race 7:Morning read R1 final R2 final … R6 final R7 jumps and freezes.
Look for the issue time and the latest earlier result used on the card. If the preceding result is still pending, the card has not absorbed it yet.
The running total
Base and day-adjusted,
across the full record.
Across the same 79 scored races, the base four held 54 winners. The day-adjusted four held 57.
The day layer added 5 winners to the four and removed 2. Winning leans: 22 base and 22 adjusted, from the same 79 races. These exploratory results span model versions and do not establish a reliable general advantage. The comparison uses each race’s saved base and adjusted forecasts, rather than an unchanged morning card.
See the changes and the limits of the evidence01 / Read the card
What you’re looking at.
Read each selection’s role
alongside its estimated chance.
2869
The box
Four horses, identified by their saddlecloth numbers. In this example: 2, 8, 6 and 9. Start with all four horses. Read their form, watch how the race might unfold and decide what deserves a closer look.
★THE LEAN
A preference, not a certainty
The lean is the model’s first-ranked selection. It has won 22 of the 79 scored races in this window. The other three matter.
◇THE UPSET
Fourth for a reason
The fourth-ranked horse occupies the upset slot. It remains part of the box, even when the model gives it a small chance of winning.
No. 8
The large number is the saddlecloth.
Use No. 8 to identify the horse. “Box rank 2 of 4” is the model’s preference and is shown underneath in smaller text.
The model’s estimated win chance.
It is not a price or a promise. Calibration is still being tested.
The four, in the wild
Here’s one we prepared earlier.
ONE REAL EXAMPLE17 OCT 2026
Randwick · R7
The Everest
Frozen at jump · 4:15 pm AEDT
See the four selections
- No.2JimmysstarBox rank 1 of 4 · The lean22.1%model win
- No.8JoliestarBox rank 2 of 4 · In the box11.7%model win
- No.6HeadwallBox rank 3 of 4 · In the box10.9%model win
- No.9TemptedBox rank 4 of 4 · The upset9.0%model win
No. 9 Tempted won. Box rank 4.The lean missed. Three of the first four home were in the box.
A past result to explain the card. Not a current recommendation.
02 / Read the confidence
How clear is the picture?
Race confidence describes the model’s view of the whole field. It is separate from any one horse’s percentage.
A clearer view
The model sees more separation between the runners. It can still be wrong.
2 / 4winners in box · lean won 1 of 4
Some separation
There is a reasonable view, with meaningful uncertainty. Read the whole box.
8 / 10winners in box · lean won 4 of 10
An open race
The model has little conviction about the order. Treat the four as a shortlist to explore.
15 / 22winners in box · lean won 2 of 22
Dated example, 3–17 October 2026: 36 races. These are small samples, not promised success rates. Bars are ordinal labels, not calibrated probabilities.
What about Back / Small / Pass and the horse labels?
Earlier cards pair Strong, Fair and Weak with Back, Small and Pass. These are the original published tier names, not instructions to stake money. The day layer can lower the tier but cannot raise it under the current rule.
High, Medium, Low and Speculative describe individual selections. They are model labels, not independently calibrated guarantees. Read them alongside the horse’s model percentage.
03 / Put it together
A quick race-day routine.
- 01
Choose the meeting and race.
Check the date, conditions and issue time. Refresh after each earlier final result; check which earlier race the card has absorbed.
- 02
Read the confidence, then the four.
A Weak race deserves a different reading from a Strong one. Don’t turn a lean into a certainty.
- 03
Compare the call with the result.
Open the base comparison to see what the day’s evidence changed. Once the race jumps, its last issued picks stay beside the result.
57/79
winners in the box
22/79
leans won
9 meetings, 26 September–31 October 2026. R1 excluded. A small, exploratory sample across model versions. This is coverage, not evidence of beating the market.