iiinova — where your digital self keeps evolving

Reposted by Frederik Aust

Society for the Improvement of Psychological Science (SIPS) @improvingpsych.org · 25/09/2026

Support open-access research in psychological science – join the PsyArXiv Moderation team! 🧑‍🏫Moderator training is provided 🕰️Commitment: ~2 hours a month 📝Checking submissions for relevance, scope, and appropriate metadata 🌐Moderation work can be done asynchronously buff.ly/6TlgL7Q

buff.ly

It is amazing that you are considering becoming a moderator. Moderation is a small job when there are plenty of moderators, which is why we are always on the lookout for people to join the team. We…

055

Reposted by Frederik Aust

Institute for Replication @i4replication.bsky.social · 25/09/2026

Over the past two years, I4R partnered with Psychological Science (@psychscience.bsky.social) on a large reproducibility project. 67 independent teams reproduced 64 articles published in 2024–2025, about 44% of eligible papers. Paper: www.econstor.eu/bitstream/10... Here's what we learned 🧵

18855

Reposted by Frederik Aust

Emil Hvitfeldt @emilhvitfeldt.bsky.social · 23/09/2026

I think I have cracked one of the final things that kept people in keynote over quarto revealjs slides. Introducing ✨️ quarto-revealjs-magic-move ✨️ emilhvitfeldt.com/post/quarto-... #quarto #slidecrafting

25510

Reposted by Frederik Aust

Zurich Cognition Lab @cognition-zurich.bsky.social · 23/09/2026

Open Postdoc (80%) in our Lab @uzh-ch.bsky.social (PI: Klaus Oberauer) Topics are: Working memory, long-term memory, attention; experiments, individual differences, computational modeling. Start Dec 2026 to Feb 2027, until June 2030. Apply by Oct 15; Questions to: k.oberauer@psychologie.uzh.ch

12020

Reposted by Frederik Aust

Micah G. Allen @micahgallen.com · 22/09/2026

So… we just found out that GPT sol can complete a complex online behavioral/cognitive study producing nearly indistinguishable behavior and subjective reports… right as we are about to launch. Is this doomsday for online cognitive testing?

3212568

Reposted by Frederik Aust

Josh de Leeuw @joshdeleeuw.bsky.social · 21/09/2026

DataPipe (pipe.jspsych.org) is ready for its post-OSF life. You can use it as before to save data from online experiments, but now the data can be sent to Zenodo, Google Drive, or a Dataverse instance. Existing OSF connections work until 11/16 I took this opportunity to do some major updates...

pipe.jspsych.org

DataPipe

13217

Reposted by Frederik Aust

Benedek Kurdi @benedek.bsky.social · 17/09/2026

🚀 Project Implicit’s critical work continues! Our website remains fully operational 24/7, collecting data and launching new studies. We are finalizing a new organizational structure to carry our research and educational mission forward. Thank you to our global community. ➡️ implicit.harvard.edu

September 17, 2026
Project Implicit Continues its Critical Work
We are more excited than ever to not only continue but to expand the scientific collabora-tion at the heart of Project Implicit. With the non-profit that served as our operational home for two decades shutting down, a new organizational structure is being finalized to carry our research and educational mission forward.
In the meantime, the Project Implicit website (http://implicit.harvard.edu/) remains fully operational and continues to collect data 24/7. New studies, programs, and educational ef-forts are actively underway. We expect public data to remain available in perpetuity, and new data from 2026 will be released in January of next year.
We express our deep gratitude to everyone who has helped create, sustain, and grow Pro-ject Implicit. This includes the founders, members of the Board of Directors and the Scien-tific Advisory Board, staff members of the non-profit, international collaborators, and the students across dozens of labs tending to tasks big and small. We are also thankful to our generous donors who have answered our calls and supported our mission, and especially the millions of annual visitors who continue to honor us with their curiosity, time, and data.
We look forward to providing more details in the weeks ahead.
Jordan Axt, McGill University
Yoav Bar-Anan, Tel-Aviv University
Benedek Kurdi, University of Illinois
Calvin Lai, Rutgers University
Ryan Lei, Haverford College
Curtis Phills, University of Oregon
Kate Ratliff, University of Waterloo
Colin Tucker Smith, Wilfrid Laurier University
Jennifer Steele, York University
Heidi Vuletich, University of Denver

02215

Reposted by Frederik Aust

Peter Ellis @freerangestats.info · 16/09/2026

Inspired by a @f2harrell.bsky.social comment, I did some #rstats simulations about how big a sample needs to be for the central limit theorem to kick in and the sample mean be normally distributed for inference purposes. Yes, with skewed data the answer is "lots". freerangestats.info/blog/2026/09...

Scatter plot with 8 facets, each showing a different distribution, and the actual coverage of a 95% confidence interval for the mean at different sample sizes. Most values are well below 95%.

33315

Reposted by Frederik Aust

ArXiv Paperboy (Stat.ME+Econ.EM) @paperposterbot.bsky.social · 16/09/2026

arXiv📈🤖 Dangers of Bayesian analyses and how to address them By Greenland, Oke

In light of the US FDA announcement supporting the use of Bayesian methods in clinical trials, we present a nontechnical review of problems with Bayesian analyses and methods to address them. Our focus is on the well-known sensitivities of Bayesian results to biases embedded in their prior distributions. This vulnerability calls for special safety features, including detailed justification of informative priors based on empirical-research literature rather than on singular expert opinions. Crucially, the information contributed by priors should be realistic in light of actual background data rather than merely judged so by available experts. We illustrate our recommendations with using a textbook clinical-trial example which covered these points.
We then use the example describe basic diagnostic procedures and safety recommendations for Bayesian analyses and their presentation. These include reference analyses which exclude informative priors, and justification for informative priors based on empirical-research literature rather than on philosophical arguments. We also critique some common priors that violate our realism requirements. One strategy to aid judgments about priors is to translate them into data to be added to the study data. The source of these prior data should be examined with the same critical attitude as the source of study data. We illustrate some simple summary methods for comparing prior and data information, including prior predictions of data, variance ratios, and their translation to effective sample sizes (ESS). Finally, we argue that Bayesian analyses should be treated as extensions or supplements to conventional analyses, rather than replace them, for that treatment puts prior construction and justification at the fore of the transition from frequentist to Bayesian analyses in teaching and practice.

041

Reposted by Frederik Aust

Greg Wester @gwestr.me · 16/09/2026

LOL

3488146

Reposted by Frederik Aust

Vishnu Sreekumar @vishnusreekumar.bsky.social · 05/08/2026

📢 ***Call for papers at Psychological Science (APS)*** Dr Roni Porat and I are editing a special issue, "From Lab to Life: Psychological Science in the Real World.” Please see the detailed call here (www.psychologicalscience.org/publications...) and send us your best work!

41923

Reposted by Frederik Aust

Brian Nosek @briannosek.bsky.social · 14/09/2026

I am sad to share that Project Implicit, my first non-profit and foundation of my career, is closing. The IAT website will continue, managed by the next generation of leaders in implicit bias research. Here's the statement I posted to LinkedIn. It didn't vibe right as a bsky thread.

55425

Reposted by Frederik Aust

Terence Tao @teorth.bsky.social · 11/09/2026

A group of 25 Fields Medalists, including myself, have made a joint declaration on Math and AI: mathandai.org . We welcome additional signatories. See also this article in the Economist announcing the declaration: www.economist.com/science-and-...

mathandai.org

Declaration — Math and AI

Read the declaration and add your name.

422052926

Reposted by Frederik Aust

Ruben C. Arslan @ruben.the100.ci · 11/09/2026

An interesting thing is happening to me at the moment. I have a standing bug bounty policy for my first authored scientific work. That means, I've committed to pay people who report bugs in my code, up to 750€ for severe errors. Since GPT-6 Astra came out, I'm now getting several bug reports daily.

39233

Reposted by Frederik Aust

Lindsey Powell @lindseypowell.bsky.social · 09/09/2026

UCSD Psychology is hiring!! We’re seeking a new assistant professor colleague who studies high-level human cognition, broadly construed. Please share and/or apply! apol-recruit.ucsd.edu/JPF04646

apol-recruit.ucsd.edu

Assistant Professor in High-level Human Cognition

University of California, San Diego is hiring. Apply now!

09680

Reposted by Frederik Aust

Alex Holcombe @alexh.bsky.social · 03/09/2026

Great news! Some of us have been waiting a long time for major funders to not just shovel $ into the maws of the big publishers, and instead support the long tail of scholar-controlled journals that are run on a shoestring

05816

Reposted by Frederik Aust

aaron bornstein @aaronbornstein.bsky.social · 03/09/2026

UC Irvine Cognitive Sciences is hiring! Focus on social cognition, broadly construed. Come be my colleague :) I am not on the search committee but happy to talk about the campus, environment, careers, etc any time. recruit.ap.uci.edu/JPF10411

recruit.ap.uci.edu

Assistant Professor - Cognitive Sciences

University of California, Irvine is hiring. Apply now!

15863

Reposted by Frederik Aust

American Statistical Association History of Statistics @hos-asa.bsky.social · 02/09/2026

Frank Wilcoxon b #OTD 1892 (d 18 Nov 1965) ASA Fellow 1955. Best known for his nonparametric rank-sum and signed-rank tests. An enthusiastic cyclist, in his 70s he shifted to a Honda motorcycle to get to work at Florida State University campus

011

Reposted by Frederik Aust

simine vazire @simine.com · 28/08/2026

Psych Science (the journal) is broader than you might think! Do you do descriptive research? Or research w/ underrepresented populations or cultural frameworks? Or research on AI/LLMs for psych? Or research testing lab findings in the real world? We have a special issue for that!

14931

Reposted by Frederik Aust

simine vazire @simine.com · 02/09/2026

Psych Science has retracted Ariely & Wertenbroch (2002). The second author requested the retraction. Both authors agreed to it. journals.sagepub.com/doi/full/10.... So grateful to @datacolada.bsky.social for these blog posts and the work behind them: datacolada.org/138 and datacolada.org/139 1/2

journals.sagepub.com

Sage Journals: Discover world-class research

Subscription and open access journals from Sage, the world's leading independent academic publisher.

426794

Reposted by Frederik Aust

Data Colada @datacolada.bsky.social · 02/09/2026

Colada[139] Artificial Deadlines Part 2 Evidence of fraud in the 25 year old gradesheet behind the key finding in an influential paper on deadlines and procrastination. datacolada.org/139

816857

Reposted by Frederik Aust

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 02/09/2026

I personally think anti-monopoly action is needed against the big publishers. I mean, academic publishing markets are not efficient! We have laws about this stuff already. But somehow I doubt any country is even thinking about it?

14211

Reposted by Frederik Aust

Sam Gershman @gershbrain.bsky.social · 01/09/2026

If this makes you mad, submit your cognitive science research to @openmindjournal.bsky.social No APCs, no subscription fees. It's funded by university libraries, at low cost.

18934

Reposted by Frederik Aust

Matt Makel @mattmakel.bsky.social · 31/08/2026

I made a mistake. And because of that mistake, I no longer have confidence that results that I reported in several research papers are an accurate reflection of replication rates. 1/

19430

Reposted by Frederik Aust

Tom Hardwicke @tomhardwicke.bsky.social · 27/08/2026

3. From Lab to Life: Psychological Science in the Real World www.psychologicalscience.org/publications... 4. Centering Underrepresented Populations and Cultural Frameworks in Psychological Science: African and Global Perspectives www.psychologicalscience.org/publications...

0129

Reposted by Frederik Aust

Tom Hardwicke @tomhardwicke.bsky.social · 27/08/2026

Send your best work to Psychological Science! Four special issue calls: 1. Descriptive Research in Psychological Science www.psychologicalscience.org/publications... 2. Advancing Psychological Science Using Large Language Models www.psychologicalscience.org/publications...

12316

Reposted by Frederik Aust

Yihui Xie @yihui.org · 21/08/2026

Please help support Tomáš’s widow and young son. I was worried about them when I heard the sad news back in April, and I really appreciate that the R Foundation has set up this fund to help the family.

043

Frederik Aust @frederikaust.com · 20/08/2026

For a one-sided tests, BF01 is unbounded, afaik. So, if the effect can only go one way, it is possible to get much stronger evidence for absence.

110

Frederik Aust @frederikaust.com · 20/08/2026

Calculation of max(BF01) for the default JZS t-test requires numerical integeration (no closed form), but you can conveniently calculate it using {BayesFactor}, e.g.: > as.vector(1/BayesFactor::meta.ttestBF(t = 0, n1 = 100, rscale=sqrt(2)/2)) Null, d=0 9.033045

120

Frederik Aust @frederikaust.com · 19/08/2026

I don‘t know the upper bound for the default t-test from the top of my head, but for example in a z-test with unit-information prior the upper bound is well approximated by the square root of the effective sample size (number of pairs), max(JAB01) = sqrt(neff). arxiv.org/abs/2607.12132

arxiv.org

Extracting Bayesian Evidence from Frequentist p-Values

The $p$-value and the Bayes factor are measures of evidence that are often considered to be philosophically and mathematically incompatible: The $p$-value quantifies conflict between data and $H_0$ ("...

120

Frederik Aust @frederikaust.com · 19/08/2026

In two-sided tests with prior scale, variance, and N fixed, BF01 has an upper bound. For stronger evidence of absence you need to increase N. If you can make due with smaller BF01 than BF10 (maybe due to prior belief), you can ofc use asymmetric stopping criteria. Needless to say: Best preregister.

110

Reposted by Frederik Aust

Society for the Improvement of Psychological Science (SIPS) @improvingpsych.org · 15/08/2026

🥳Today, PsyArXiv – the community preprint server for psychology – turns 10! 🥳 Thank you to everyone who contributed to the server's growth, including volunteers who work behind the scenes to keep it running, preprint authors, and readers!

06917

Reposted by Frederik Aust

PsyArXivBot @psyarxivbot.bsky.social · 14/08/2026

A Poisson Count Race as a Generative Bridge Between Logit and Probit Choice: osf.io/r36vs

021

Frederik Aust @frederikaust.com · 14/08/2026

Strong responses here, worth a read: vincentholst.github.io/the_curious_...

021

Reposted by Frederik Aust

Neuroskeptic @neuroskeptic.bsky.social · 14/08/2026

In mice, hibernation causes the loss of more than 50% of all hippocampal synapses. But after recovery, memories are preserved and most of the 'lost' synapses grow back! www.science.org/doi/10.1126/... "Somehow, the synapse returned."

science.org

Artificial hibernation reveals synaptic engram architecture associated with memory retention

Memories leave lasting physical changes at the synaptic level. Although stable, larger spines are thought to support memory, the high turnover of dendritic spines and the drifting of neuronal represen...

12511

Frederik Aust @frederikaust.com · 14/08/2026

My reading was that the effect is greatly attenuated compared to the originally reported effect, no?

110

Frederik Aust @frederikaust.com · 14/08/2026

Kronmal (1993): "It is shown that the use of ratios in regression analyses can lead to incorrect or misleading inferences. A recommendation is made that the use of ratios in regression analyses be avoided." www.jstor.org/stable/2983064

jstor.org

Client Challenge

0110

Reposted by Frederik Aust

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 13/08/2026

These ratio outcome variables are a plague in the sciences. If your analysis treats 1/2 and 10/20 as the same evidence, then you have discarded uncertainty in the outcome. Model what you measure, not what you construct. Use the denominator as an exposure instead.

612237

Frederik Aust @frederikaust.com · 14/08/2026

For context, I should also link to the critique.

100

Frederik Aust @frederikaust.com · 14/08/2026

@vincentholst.bsky.social probably won't get a chance to formally reply to this. I wonder what you make of the rebuttal arguments.

200

Frederik Aust @frederikaust.com · 14/08/2026

Here is the author's reply to the critique of the decine in disruptiveness paper. Zero-reference works appear to play an important role. Maybe I have never read a truly disruptive paper, but I don't think I have ever seen a zero-reference paper in psychology. www.nature.com/articles/s41...

240

Reposted by Frederik Aust

vincentholst.bsky.social @vincentholst.bsky.social · 13/08/2026

Instead of a decline in the disruptiveness of scientific and technological knowledge, the data mainly show an increasing metadata quality over time: relatively fewer papers with zero references due to database errors. 7/8

The decline in disruption (including zero reference papers, left panel) mirrors the relative decrease of zero reference papers which were wrongly counted as being maximally disruptive (right panel).

14013

Reposted by Frederik Aust

vincentholst.bsky.social @vincentholst.bsky.social · 13/08/2026

In 2023, @nature.com published 'Papers and patents are becoming less disruptive over time', receiving world-wide media attention. Our Matters Arising, published after a 32 month delay (more on that soon), shows that the reported decline can largely be attributed to dataset artefacts. 🧵

The average CD_5 index per year for Web of Science. The original Park et al. decline (top curve) becomes essentially flat (bottom curve) when removing papers with CD_5=1. Those papers largely correspond to dataset artefacts.

9351173

Reposted by Frederik Aust

simine vazire @simine.com · 10/08/2026

Special issue at Psych Science on psychology research using LLMs Theoretical & methodological work welcome. Read the full call for important info about what we’re looking for! Submission deadline: 15 March 2027 (15 October 2026 for Registered Reports) www.psychologicalscience.org/publications...

psychologicalscience.org

Special Issue Call for Submissions: “Advancing Psychological Science Using Large Language Models”

Editors: Jamie Cummins and Ruben C. ArslanPsychological Science invites submissions for a special issue on psychological science involving large language models. We welcome theoretically and empirical...

03024

Reposted by Frederik Aust

simine vazire @simine.com · 10/08/2026

Special issue at Psych Science on psychological science in the real world! Send us your best work looking at whether effects from the lab (or from theories) hold up in ecologically valid settings. Submission deadline: 15 January 2027 www.psychologicalscience.org/publications...

psychologicalscience.org

Special Issue Call for Submissions: “From Lab to Life: Psychological Science in the Real World”

Editors: Roni Porat and Vishnu SreekumarPsychological Science invites submissions presenting innovative research that brings psychological science “into the wild,” whether to strengthen its ecological...

28158