Preprint reviews are being posted at an increasing rate (Fig 1). Multiple preprint review services (Box 2) whose outputs meet the above definition (including Review Commons, Peer Community In, PeerRef, PREreview, Qeios, and Rapid Reviews\Infectious Diseases) were represented at the workshop. They illustrate the diversity of approaches—from spontaneous posting of reviews by individuals to community-driven review platforms—that can be used to satisfy the above criteria.

Prior to widespread adoption of preprinting in biology, some publishers had already implemented workflows that in many respects resemble preprint review. For example, Copernicus’s discussion journals encouraged community comments on manuscripts under peer review, and F1000 developed a model in which manuscripts are published first and then undergo open peer review (reviewers in the F1000 model assign report statuses that contribute to a threshold for passing peer review). As posting of preprints has become more common over the past decade, many journals have adopted policies that support preprinting and the publication of peer-review reports. Furthermore, new preprint review initiatives that decouple peer review from journals have emerged, including platforms such as PREreview and Peer Community In. More recently, eLife has introduced a new editorial model in which Reviewed Preprints are the primary output [21]. Review Commons has successfully implemented journal-agnostic preprint peer review in partnership with a growing consortium of journals. Furthermore, in 2022, preprints with reviews were recognized as satisfying the “peer-reviewed publication” eligibility criterion for EMBO Postdoctoral Fellowships [22], 9 funders committed to recognizing reviewed preprints in assessments [23], and cOAlition S stated that, for many of its funders, a paper that has “been subject to a journal-independent standard peer review process with an implicit or explicit validation” will be considered equivalent to a journal-reviewed article [24].

At the workshop, our discussions focused on the peer review itself, rather than on any decision or “validation” that follows from it. While some preprint review projects such as Review Commons deliberately avoid making editorial decisions (leaving this to the journal to which the reviews may be transferred), others provide endorsements or other shorthand signifiers of rigor and impact. Peer Community In, for example, only publishes reviews of articles that have been “endorsed” by their recommender (i.e., by the person coordinating the peer review for the preprint). Other services do not provide an accept/reject decision: Rapid Reviews\Infectious Diseases assigns scores to papers, and eLife’s new model deliberately moves away from accept/reject decisions, instead using a controlled vocabulary to express editorial judgments about the strength of the evidence and the significance of the findings in a summary statement published alongside the reviews. These varied approaches may yield different benefits for authors and readers. In cases where an explicit recommendation is not made, reviewers may feel liberated to focus on providing feedback for the author. By contrast, preprint review models that create a recommendation compress reviewers’ opinions into a concise and digestible message that can help readers sift through the scientific literature.

When peer reviews of preprints are made publicly available, readers are able to see the reports alongside the article, evaluate the claims, and join the conversation. Interactions between authors, reviewers, and readers stimulated by public posting of reviews may surface perspectives from a larger and more diverse sample of the community, increasing the robustness of the assessment and providing further context. This can enable a wider audience, including non-specialists, to benefit from these insights and gain an understanding of how experts perceive the strengths and weaknesses of an article. Preprint review can also give readers more rapid access to peer-reviewed information because, unlike journal publication, reviews can be made available immediately rather than after multiple cycles of review and revisions (e.g., preprint reviews are posted a median of 46 days after the article [25], in contrast to an observed 199-day delay between preprinting and journal publication [26], or the 163 days from submission to journal publication seen elsewhere [27]).

Preprint review offers important benefits to trainees, who can learn good practices from reading public reviews. In addition, while early career researchers in certain disciplines may seldom be invited to peer review by journal editors, they can freely participate in many forms of preprint feedback and review, offering valuable perspectives; early career reviewers may be more attentive and have hands-on experience with new techniques that may be less familiar to senior reviewers. Some preprint review platforms (such as PREreview) offer structured templates that can help guide new reviewers [28]. Preprint review is already being incorporated into undergraduate and graduate courses on scientific publishing [29–31]. Furthermore, by focusing journal clubs on preprints rather than journal publications, participants can move beyond simply discussing a paper that is unlikely to change to producing reviews that will help authors and readers.

Preprint review can also benefit journals. For example, journals can use preprint reviews (as well as informal comments on preprints) to identify papers to invite for submission. In some cases, they may choose to reuse the reviews to expedite their own peer-review process, reducing the burden on the reviewer pool, and—when reviews are signed—providing useful leads to identify qualified peer reviewers for other papers.

In addition to these benefits, we believe that preprint review can promote a cultural shift in peer review. Reviewers can focus on the research as it stands, without having to comment on its fit for a particular journal. Open dialog may encourage reviewers to be more collegial and constructive. Authors could use the opportunity offered by preprint review to publicly respond to questions and concerns, thereby ensuring that their responses can be read by all. Finally, by making the comments of reviewers an integral element of scholarly discourse, peer review will increasingly be seen as a scholarly contribution in its own right.

Despite the benefits noted above, preprint review is not without potential challenges. Participants raised a variety of concerns at the workshop, and we discussed how each can be addressed with thoughtful implementation of services and policies.

Preprint review services must address bias and non-collegial input, which can be serious problems in peer review [32]. In the most informal preprint feedback models, anyone may comment on a paper, and anonymous and pseudonymous feedback is permitted; thus, it becomes even more important to address the question of competing interests through transparent declarations or editorial oversight if these comments are to be treated as preprint reviews. Likewise, services that have editors or coordinators can promote constructive dialog through moderation of comments. Transparent disclosures about the nature of this moderation will help ensure readers use feedback appropriately. But for more open models that aim to minimize the impact of bad actors through community consensus, we need to nurture a culture in which norms of collegiality are established through training and community regulation [33].

Although the practice of posting preprints has been growing, only a minority of biomedical papers are posted as preprints (we estimate less than 10% [34]). Concerns about preprints differ across countries [35], with worries about scooping being more prominent among researchers in China than in the USA and Europe. Furthermore, perceived benefits of preprints vary, with one study finding that respondents in the Global South were more likely to strongly agree with benefits related to preprint visibility than those in the Global North [36]. Currently, preprint adoption varies across disciplines and geographies [37], with the highest rates of preprinting found in the USA and UK. Thus, not all communities may be ready to embrace preprint reviewing yet, and disciplinary and/or geographical differences in participation may also arise in the context of preprint review. While we should be mindful of supporting adoption in a manner that fosters inclusive participation, this should not deter progress on preprint review among those who are ready. At the same time, policies or guidance for preprint review must avoid undermining the value of the preprints themselves. Many funders and institutions recognize preprints cited in CVs and job or grant applications as research outputs alongside journal articles [38]. Recognition for preprint review must build on recognition for preprints. Preprint review can support and enrich evaluation of these articles, but the presence of such reviews does not itself signal the quality of the work.

Not all preprint authors will feel comfortable actively soliciting reviews of their papers. Those who submit to review services are both willing to risk participation in nontraditional publication models and are comfortable with public critique of their work. Moreover, reviewers and editors may be more willing to perform preprint review for authors within their existing networks, potentially reinforcing Matthew effects (i.e., benefits accrue to those who are already privileged) [39]. On the other hand, preprints lower barriers to sharing: many preprints are never published in a journal, and this fraction varies from approximately 20% of preprints from researchers in high-income countries to approximately 40% of preprints from researchers in low-income countries, and is correlated with funding disclosures [26]. This suggests that preprints enable the release of scientific outputs that would not otherwise be shared. Free or low-cost reviewing approaches built on top of preprints can make peer review more accessible to authors who lack funding or stable research environments.

If the fraction of biomedical papers posted as preprints is currently small, the fraction of preprints that have reviews is even smaller, and it is not equitably distributed. Less than 2% of preprints have accompanying reviews [20]. Preprint review services would need to scale massively to provide reviews for all the preprints that are currently posted. Platforms that organize preprint review as a service should be easy to use and able to scale so that any researcher can request or contribute to preprint review. Journal editors often report challenges in finding reviewers for manuscripts, so it will be important for preprint review services to expand their pools of potential reviewers to enable them to respond to growing demand. Participating in preprint review, and thereby developing a portfolio of public reviews, may be particularly attractive for early career researchers, who are often underrepresented in journal peer review. This should provide an opportunity for both preprint review services and journals to not only expand their pool of active reviewers but to also include a more diverse group of researchers in the peer-review process. Institutions that recognize preprint review should support preprint review services financially and encourage researchers to participate in organized preprint review. It is also essential that preprint reviews be visible and citable; we have proposed a citation format elsewhere [40].

Despite the rarity of preprint reviews, it is possible for authors to receive an overwhelming amount of feedback on their papers through social media or other channels, forcing them to prioritize responses to only those that are most useful or offered in good faith. An inundation of comments or reviews would also be difficult for readers to digest. Thus, tools to help manage information overload (such as searching, indexing, and summarization) will eventually be useful to help both authors and readers identify the reviews most relevant to them.

While services and frameworks such as DocMaps and COAR Notify are emerging, many indexing tools do not adequately connect the distributed network of reviews to preprints [41], which can make it difficult for researchers and other stakeholders to discover preprint reviews. A positive example is Europe PMC, which currently ingests DocMaps metadata from Sciety and Review Commons to facilitate accessibility and visibility of preprint reviews; users can filter their search of preprints to those with reviews. Europe PMC will be working on ingesting Crossref preprint review DOI metadata next. Sciety is an example of a platform that is dedicated to aggregating preprint review and feedback activity in one place, making it easier for researchers to read reviews and discover related reviewed preprints. Users can organize, comment on, and highlight preprints of interest, raising visibility and aiding the discovery of the research. We urge other databases to implement similar measures. Furthermore, we emphasize that preservation strategies are required to ensure that reviews remain accessible in the future.

We also encourage preprint servers to import or aggregate links to external preprint reviews, as is currently done by bioRxiv. In the absence of such integrations, readers may be inclined to post reviews via the commenting system of the preprint server. Such systems do not currently issue DOIs or any other form of persistent identifier. Ideally commenters posting reviews should also provide an authenticated ORCID, but this may create a barrier to entry, so tension between best practices for long-term discoverability and adoption exists. There is also the question of whether all comments warrant such a formal logging within the scientific record, and if this is not the case, how to distinguish between reviews and informal feedback.

We believe that all of the above challenges are surmountable, and that we now have the tools and community support needed to embrace preprint review. We recommend the following actions for stakeholders interested in participating in and promoting preprint review (Box 3).

Our recommendations encourage all researchers and readers to participate in preprint review, whether by requesting, partaking, funding, or considering it. Journals can contribute to creating an environment that supports preprint review by creating policies that welcome it and promote its reuse. Institutions and funders can incentivize preprint review by recognizing it as a form of scholarship in grant applications, reporting, hiring, graduation, and tenure and promotion policies. Furthermore, preprint review services, preprint servers, and indexing and search tools will have an important role in facilitating these actions by making preprint reviews more discoverable.