Measured pairing · from 63,696 recipes

What goes with pumpkin?

Measured across 63,696 recipes, the 8 ingredients that co-occur with pumpkin most disproportionately are enokidake (×14.6 chance, n=20), nutmeg (×10.1 chance, n=351), cinnamon (×6.5 chance, n=498), ginger (×5.8 chance, n=355), soybean (×4.0 chance, n=61), clam (×4.0 chance, n=26), shiitake (×3.9 chance, n=30) and maple syrup (×3.8 chance, n=25). The score behind the ranking is positive pointwise mutual information — how many times more often a pair shares a recipe than random combination would predict — and n is the number of recipes containing both ingredients. Nothing is published below a floor of 20 recipes per pair and 100 per ingredient. Co-occurrence records what recipe authors actually do — it conflates deliciousness with popularity and tradition — so read it as ethnography, not judgment.

The measured partners — PPMI · ×chance · n

1. enokidake — PPMI 2.68 · ×14.6 chance · n=20 (enokidake itself appears in 106 recipes)
2. nutmeg — PPMI 2.32 · ×10.1 chance · n=351 (nutmeg itself appears in 2,686 recipes)
3. cinnamon — PPMI 1.88 · ×6.5 chance · n=498 (cinnamon itself appears in 5,918 recipes)
4. ginger — PPMI 1.75 · ×5.8 chance · n=355 (ginger itself appears in 4,775 recipes)
5. soybean — PPMI 1.38 · ×4.0 chance · n=61 (soybean itself appears in 1,192 recipes)
6. clam — PPMI 1.38 · ×4.0 chance · n=26 (clam itself appears in 509 recipes)
7. shiitake — PPMI 1.36 · ×3.9 chance · n=30 (shiitake itself appears in 596 recipes)
8. maple syrup — PPMI 1.34 · ×3.8 chance · n=25 (maple syrup itself appears in 507 recipes)

Cook the pairing

Dishes in Palate's live corpus that use pumpkin with one of its measured partners:

• Mole Poblano — with cinnamon
• Dhansak (Goat with Three Lentils, Pumpkin and Fenugreek) — with ginger
• Ghapama (Pumpkin Baked with Rice and Dried Fruit) — with cinnamon

How this was measured

pumpkin appears in 821 of the 63,696 recipes counted (5,296 parsed + 1,081 hand-curated + 57,319 from the dataset published with Ahn et al., 2011). PPMI = max(0, ln(count(A,B)·N / (count(A)·count(B)))), all counts over the same N; lift = e^PMI, which reads directly as "×chance." Staples (salt, sugar, flour, water) are excluded because sources under-record them, and pairs where one name contains the other are excluded as near-duplicates.

Read the numbers with their limits: the corpus is Western-skewed (90% of it is the largely North American and European recipe dataset published with Ahn et al.'s 2011 paper), so the absence of a pairing here proves nothing except who wrote the recipes down. PPMI favors the rare end even above the floor — a niche pair at n=22 can outrank a workhorse pair seen thousands of times, because common ingredients' huge counts divide the score down — so read PPMI and n together.

The full reference — 150 ingredients, top 8 partners each — lives at What actually goes with X.

Curious how these flavors fit your palate — take the short taste test →

Every number above is counted from recipes — pointwise mutual information over 63,696 of them — not chef interviews, model guesses, or reviews.