What the F-measure doesn't measure: Features, Flaws, Fallacies and Fixes

David M. W. Powers

What the F-measure doesn't measure: Features, Flaws, Fallacies and Fixes

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1503.06410 v2 pith:UNYGDNND submitted 2015-03-22 cs.IR cs.CLcs.LGcs.NEstat.COstat.ML

David M. W. Powers This is my paper · ORCID

classification cs.IRcs.CLcs.LGcs.NEstat.COstat.ML

keywords f-measurealternativesassumptionsbettercommonlycontextsdoesnf-score

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

The F-measure or F-score is one of the most commonly used single number measures in Information Retrieval, Natural Language Processing and Machine Learning, but it is based on a mistake, and the flawed assumptions render it unsuitable for use in most contexts! Fortunately, there are better alternatives.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Multi-Scale Deep Learning for Colon Histopathology: A Hybrid Graph-Transformer Approach
cs.CV 2025-09 reject novelty 2.0 of 10

A hybrid CNN-transformer-graph network is reported to reach 96% accuracy on LC25000, but the paper lacks architectural detail, code, and a described data split.

Pith tools