Measured pairing · from 63,696 recipes

What goes with sake?

Measured across 63,696 recipes, the 8 ingredients that co-occur with sake most disproportionately are kelp (×41.6 chance, n=80), enokidake (×37.1 chance, n=42), wasabi (×18.7 chance, n=27), shiitake (×16.2 chance, n=103), chinese cabbage (×15.8 chance, n=29), squid (×15.7 chance, n=40), radish (×13.8 chance, n=82) and soy sauce (×12.5 chance, n=569). 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. kelp — PPMI 3.73 · ×41.6 chance · n=80 (kelp itself appears in 180 recipes)
  2. enokidake — PPMI 3.61 · ×37.1 chance · n=42 (enokidake itself appears in 106 recipes)
  3. wasabi — PPMI 2.93 · ×18.7 chance · n=27 (wasabi itself appears in 135 recipes)
  4. shiitake — PPMI 2.78 · ×16.2 chance · n=103 (shiitake itself appears in 596 recipes)
  5. chinese cabbage — PPMI 2.76 · ×15.8 chance · n=29 (chinese cabbage itself appears in 172 recipes)
  6. squid — PPMI 2.75 · ×15.7 chance · n=40 (squid itself appears in 238 recipes)
  7. radish — PPMI 2.63 · ×13.8 chance · n=82 (radish itself appears in 555 recipes)
  8. soy sauce — PPMI 2.52 · ×12.5 chance · n=569 (soy sauce itself appears in 4,263 recipes)

Cook the pairing

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

How this was measured

sake appears in 681 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.