Evidence map›Paper›PMID 37720327›Full record

ArticlePatterns (New York, N.Y.)2023

Leakage and the reproducibility crisis in machine-learning-based science.

Sayash Kapoor, Arvind Narayanan

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in Patterns (New York, N.Y.), 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 303 papers, 4 of them syntheses that pooled it.

0numbers the graph read from it
0cells of the map it votes in
303citing papers in PubMed, 4 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

303 citing papers in PubMed, 4 syntheses or guidelines pooled it.

  1. Pooled it
  2. Pooled it
  3. Pooled it
  4. Pooled it
  5. Article
  6. Article
  7. Review
  8. Review
  9. Review
  10. Review
  11. Article
  12. Article
  13. Article
  14. Review
  15. Article
  16. Article
  17. Review
  18. Article
  19. Article
  20. Article

243 more citing papers are in PubMed but not listed here.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

2 authors.

Sayash KapoorDepartment of Computer Science and Center for Information Technology Policy, Princeton University, Princeton, NJ 08540, USA.
Arvind NarayananDepartment of Computer Science and Center for Information Technology Policy, Princeton University, Princeton, NJ 08540, USA.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

Machine-learning (ML) methods have gained prominence in the quantitative sciences. However, there are many known methodological pitfalls, including data leakage, in ML-based science. We systematically investigate reproducibility issues in ML-based science. Through a survey of literature in fields that have adopted ML methods, we find 17 fields where leakage has been found, collectively affecting 294 papers and, in some cases, leading to wildly overoptimistic conclusions. Based on our survey, we introduce a detailed taxonomy of eight types of leakage, ranging from textbook errors to open research problems. We propose that researchers test for each type of leakage by filling out model info sheets, which we introduce. Finally, we conduct a reproducibility study of civil war prediction, where complex ML models are believed to vastly outperform traditional statistical models such as logistic regression (LR). When the errors are corrected, complex ML models do not perform substantively better than decades-old LR models.

Indexed as

leakagemachine learningreproducibility

Identifiers

PMID37720327
PMCPMC10499856

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.