Pith. sign in

REVIEW 2 cited by

deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks

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 2204.06815 v1 pith:VJFQFRLY submitted 2022-04-14 cs.LG

Dennis Ulmer , Christian Hardmeier , Jes Frellsen This is my paper · ORCID
classification cs.LG
keywords researchsignificancestatisticallearningtestingastraybaselinecomputational
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature. Nevertheless, statistical significance testing (SST) is still not widely used. This endangers true progress, as seeming improvements over a baseline might be statistical flukes, leading follow-up research astray while wasting human and computational resources. Here, we provide an easy-to-use package containing different significance tests and utility functions specifically tailored towards research needs and usability.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Enriching Social Science Research via Survey Item Linking

    cs.DL 2024-12 conditional novelty 6.0 of 10

    A new bilingual benchmark (SILD) and a two-stage pipeline make survey item linking feasible, reaching document-level recall above 50% at k=10, with mention detection as the main bottleneck.

  2. Modelling Adjectival Modification Effects on Semantic Plausibility

    cs.CL 2025-07 conditional novelty 4.0 of 10

    Sentence transformers underperform standard classifiers on the ADEPT adjectival-plausibility benchmark, and unbalanced evaluation inflates apparent accuracy.

Pith tools