AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

What Is the Optimal Ranking Score Between Precision and Recall? We Can Always Find It and It Is Rarely F1

Sébastien Piérard, Adrien Deliège, Marc Van Droogenbroeck

CVPR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking models from comparisons

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use F1 instead of the optimal beta for ranking on fixed-prior distributionsF1 ranking · Uniform distribution, fixed class priorsdegree of optimality O: O in [50%, 100%], optimal only for pi+ ~ 0.381Hurt
use F1 on uniform distribution over all performancesF1 ranking · Uniform distribution over all performancesdegree of optimality O: O = 100% (optimal)No clear effect
use SIVF instead of F1 for rankingSIVF ranking · CDnet 2014 (53 real sets)mean degree of optimality O: 78.44% -> 56.71%Hurt
use heuristic beta^2 = E[PFP]/E[PFN] instead of F1F-beta ranking · CDnet 2014 (53 real sets)mean degree of optimality O: 78.44% -> 89.53%Improved
use closed-form median-based optimal beta instead of fixed F1F-beta ranking · CDnet 2014 (53 real sets)degree of optimality O: 78% (F1) -> 100%Improved
use F2 as in CADA-RRE challenge to emphasize recallCADA-RRE ranking · CADA-RRE (16 performances)rank mimicry: beta=2 vs beta=0.914 for 4x recall weighting by ranksHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy