REFORMS: Consensus-based Recommendations for Machine-learning-based Science
Open accessThe DOI matches its Crossref record; 74 of the 74 references it cites were found in a registry or an index.
Abstract
Machine learning (ML) methods are proliferating in scientific research. However, the adoption of these methods has been accompanied by failures of validity, reproducibility, and generalizability. These failures can hinder scientific progress, lead to false consensus around invalid claims, and undermine the credibility of ML-based science. ML methods are often applied and fail in similar ways across disciplines. Motivated by this observation, our goal is to provide clear recommendations for conducting and reporting ML-based science. Drawing from an extensive review of past literature, we present the REFORMS checklist (recommendations for machine-learning-based science). It consists of 32 questions and a paired set of guidelines. REFORMS was developed on the basis of a consensus of 19 researchers across computer science, data science, mathematics, social sciences, and biomedical sciences. REFORMS can serve as a resource for researchers when designing and implementing a study, for referees when reviewing papers, and for journals when enforcing standards for transparency and reproducibility.
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.
Integrity signals
Registry
Cites
Statistics
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.
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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“For example, there is an active debate on how or if interpretability or explainability should be implemented in the context of different applications [see e.g., ( 141 )].”
Vandenbroucke, J. P., von Elm, E., Altman, D. G., Gøtzsche, P. C., Mulrow, C. D., Pocock, S. J., Poole, C., Schlesselman, J. J., Egger, M., & Initiative, F. T. S. (2007) · PLoS Medicine · doi:10.1371/journal.pmed.0040297 · Cited by 8,613
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788 · cited 1×
“Not using a held-out test set is a textbook error in ML ( 158 ).”
Collins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. M. (2015) · BMJ · doi:10.1136/bmj.g7594 · Cited by 4,388
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340 · cited 3×
“Breiman’s proposition was that more scientific research should use algorithmic modeling ( 12 ).”
Cross‐validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure
Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera‐Arroita, G., Hauenstein, S., Lahoz‐Monfort, J. J., Schröder, B., Thuiller, W., et al. (2017) · Ecography · doi:10.1111/ecog.02881 · Cited by 3,689
STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies
Bossuyt, P. M., Reitsma, J. B., Bruns, D. E., Gatsonis, C. A., Glasziou, P. P., Irwig, L., Lijmer, J. G., Moher, D., Rennie, D., de Vet, H. C. W., et al. (2015) · BMJ · doi:10.1136/bmj.h5527 · Cited by 3,660
AUC: A misleading measure of the performance of predictive distribution models
Lobo, J. M., Jiménez‐Valverde, A., & Real, R. (2008) · Global Ecology and Biogeography · doi:10.1111/j.1466-8238.2007.00358.x · Cited by 3,499
Scientists rise up against statistical significance
Amrhein, V., Greenland, S., & McShane, B. (2019) · Nature · doi:10.1038/d41586-019-00857-9 · Cited by 2,983 · cited 1×
“As a result, reporting uncertainty is better than performing statistical tests alone ( 178 ).”
Cited by
Fleurence, R. L., Bian, J., Wang, X., Xu, H., Dawoud, D., Higashi, M., & Chhatwal, J. (2025) · Value in Health · doi:10.1016/j.jval.2024.10.3846 · Cited by 54
Why an overreliance on AI-driven modelling is bad for science
Narayanan, A., & Kapoor, S. (2025) · Nature · doi:10.1038/d41586-025-01067-2 · Cited by 21
Self-citationThe reanimation of pseudoscience in machine learning and its ethical repercussions
Andrews, M., Smart, A., & Birhane, A. (2024) · Patterns · doi:10.1016/j.patter.2024.101027 · Cited by 18
Vrba, J., Steinbach, J., Jirsa, T., Verde, L., De Fazio, R., Zeng, Y., Ichiji, K., Hájek, L., Sedláková, Z., Urbániová, Z., et al. (2025) · Journal of Voice · doi:10.1016/j.jvoice.2025.03.028 · Cited by 6
“Especially regarding reproducibility, to our best knowledge, this is the first paper on voice pathology detection combining SVD and ML methods, that is fully re-producible and conforms to the REFORMS practices [55].”
Metadata
- Authors
- Kapoor, S., Cantrell, E. M., Peng, K., Pham, T. H., Bail, C. A., Gundersen, O. E., Hofman, J. M., Hullman, J., Lones, M. A., Malik, M. M., Nanayakkara, P., Poldrack, R. A., Raji, I. D., Roberts, M., Salganik, M. J., Serra-Garcia, M., Stewart, B. M., Vandewiele, G., & Narayanan, A.
- Venue
- Science Advances
- Published
- 2024-05-03
- Volume
- 10
- Issue
- 18
- Pages
- eadk3452-eadk3452
- ISSN
- 2375-2548 (ISSN-L)
- OpenAlex
- W4396541948
- Cited by
- 129
- References
- 74
- FWCI
- 49.19
- Type
- journal article
- Language
- en
- Open access
- gold
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: REFORMS: Consensus-based Recommendations for Machine-learning-based Science. https://app.cochat.ai/papers/10.1126/sciadv.adk3452
- The paper
- Kapoor, S., Cantrell, E. M., Peng, K., Pham, T. H., Bail, C. A., Gundersen, O. E., Hofman, J. M., Hullman, J., Lones, M. A., Malik, M. M., Nanayakkara, P., Poldrack, R. A., Raji, I. D., Roberts, M., Salganik, M. J., Serra-Garcia, M., Stewart, B. M., Vandewiele, G., & Narayanan, A. (2024). REFORMS: Consensus-based Recommendations for Machine-learning-based Science. Science Advances. https://doi.org/10.1126/sciadv.adk3452
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.