Questionable Practices in Machine Learning.

Leech, G. (2024). Questionable Practices in Machine Learning.

Type

Preprint

Intellectual base

Grey literature

Year

2024

Link

https://arxiv.org/abs/2407.12220

Cited by

1 citation across 1 artifact.

Each citation links to the sentence it supports in the citing article.

Domain-specific

• Curse Of Knowledge
  • From software into ML evaluation: held-out blind reviewers and pre-registration of test items.

    This sourceCatalogues test-set leakage and contamination in ML evaluation and the held-out/blind discipline that guards against it — the structural corrective of routing evaluation through items the designer cannot have already seen.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:677fc6e20ef2 · see in the full table