Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.

Predicting retracted research: a dataset and machine learning approaches

Open access
Fletcher, Aaron H. A., Stevenson, Mark · 2025 · Research Integrity and Peer Review

Abstract

Background: Retractions undermine the scientific record’s reliability and can lead to the continued propagation of flawed research. This study aimed to (1) create a dataset aggregating retraction information with bibliographic metadata, (2) train and evaluate various machine learning approaches to predict article retractions, and (3) assess each feature’s contribution to feature-based classifier performance using ablation studies. Methods: An open-access dataset was developed by combining information from the Retraction Watch database and the OpenAlex API. Using a case-controlled design, retracted research articles were paired with non-retracted articles published in the same period. Traditional feature-based classifiers and models leveraging contextual language representations were then trained and evaluated. Model performance was assessed using accuracy, precision, recall, and the F1-score. Results: The Llama 3.2 base model achieved the highest overall accuracy. The Random Forest classifier achieved a precision of 0.687 for identifying non-retracted articles, while the Llama 3.2 base model reached a precision of 0.683 for identifying retracted articles. Traditional feature-based classifiers generally outperformed most contextual language models, except for the Llama 3.2 base model, which showed competitive performance across several metrics. Conclusions: Although no single model excelled across all metrics, our findings indicate that machine learning techniques can effectively support the identification of retracted research. These results provide a foundation for developing automated tools to assist publishers and reviewers in detecting potentially problematic publications. Further research should focus on refining these models and investigating additional features to improve predictive performance. Trial registration: Not applicable.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s41073-025-00168-w

Cites

32 of 32 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Input format for encoder-based models
Fig. 1 Input format for encoder-based modelsCC BY · PubMed Central
Fig. 2 Input format for decoder-based models
Fig. 2 Input format for decoder-based modelsCC BY · PubMed Central
Fig. 3 Prompt template used for structuring input data during model fine-tuning
Fig. 3 Prompt template used for structuring input data during model fine-tuningCC BY · PubMed Central
Fig. 4 Publication year distribution for retracted and non-retracted works
Fig. 4 Publication year distribution for retracted and non-retracted worksCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

1 retracted

Show all 32 references

Research works printed but not linked: 1

  1. Bai Y, Kadavath S, Kundu S, Askell A, Kernion J, Jones A, et al. Constitutional AI: Harmlessness from AI Feedback. 2022. https://arxiv.org/abs/2212.08073. Accessed 23 Jan 2025. · arXiv

Cited by

See all 9

Metadata

Authors
Fletcher, A. H. A., & Stevenson, M.
Affiliations
University of Sheffield (GB)
Corresponding author
Fletcher, Aaron H. A.
Venue
Research Integrity and Peer Review
Published
2025-06-11
Volume
10
Issue
1
Pages
9-9
ISSN
2058-8615 (ISSN-L)
OpenAlex
W4411162931
Cited by
9
References
32
Citations by year
2026: 7 · 2025: 2
FWCI
9.31
Type
journal article
Language
en
Open access
Licence
Locations
  • Research Integrity and Peer Review (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
UK Research and Innovation (EP/S023062/1)
Topics
  • Social Sciences › Education › Academic integrity and plagiarism
  • Social Sciences › Library and Information Sciences › scientometrics and bibliometrics research
  • Social Sciences › Library and Information Sciences › Academic Publishing and Open Access
Keywords
retraction, Retraction Watch, bibliographic metadata, Llama 3.2, contextual language models, feature-based classifiers, random forest, scientific integrity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Predicting retracted research: a dataset and machine learning approaches. https://app.cochat.ai/papers/10.1186/s41073-025-00168-w
The paper
Fletcher, A. H. A., & Stevenson, M. (2025). Predicting retracted research: a dataset and machine learning approaches. Research Integrity and Peer Review. https://doi.org/10.1186/s41073-025-00168-w

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.