Jev as a recommender · live replay of saved test predictions

Jev Decision Desk

One request = one MovieLens user's last 20 ratings (the state) and 20 candidate movies (one Choice question). The model returns a calibrated probability for every candidate in a single forward pass. Pick a scenario and a model, then step through real test users.

Whole test set · click a model to inspect it

The state

    The decision

    20 candidates · ranked by

      What the same decision costs

      Why isolated is cheaper

      Jev pointwise feeds state + candidate as K separate sequences. Isolated packs them into one: each candidate (c1–c3) sees the state (s) and itself, never another candidate, and its position ids restart after the state. The logits are the same function, but the state is read once.