Style is the dough; toppings are the identity on top of it. 3,698 of 4,993 recipes name at least one recognizable topping (38 canonical toppings after normalizing the free-text names). Below: what the internet actually puts on pizza, what makes each regional style itself, and which toppings travel together.
The canon
Share of topped recipes that include each topping. Garlic, basil, and mozzarella read more like infrastructure than choices.
onion
40%
garlic
36%
basil
25%
oregano
20%
bell pepper
17%
pepperoni
15%
mushroom
14%
sausage
12%
olives
12%
chicken
9%
chili flakes
8%
bacon
7%
spinach
7%
egg
7%
arugula
6%
ham
5%
potato
5%
ground beef
5%
zucchini
4%
prosciutto
4%
What makes a style itself
Signature toppings per regional style — the ones a style uses far more than the rest of the dataset does (“3×” = three times the global rate). The regional identities survive normalization: clams belong to New Haven, anchovies to sfincione, pesto to California.
Lift between the top toppings: red = the pair appears together more often than chance (classic combinations), grey ≈ independent, light = they avoid each other. Hover a cell for numbers.
Method: free-text topping names normalized to a controlled vocabulary (seasonings, oils, and dough ingredients excluded). Lift = how much more often X appears in a group than in the dataset overall; pairs with fewer than 5 shared recipes are left unscored.