Lightnews — Scholar-powered news

Reposted by Kou Murayama

Darren Dahly @statsepi.bsky.social · May 26

We've been asked what the most important thing we can do to improve research culture. My answer, the only answer, is to withdraw immediately from university rankings.

bsky.app/profile/stat...

Darren Dahly @statsepi.bsky.social · Dec 20

Restating a prediction I made on twitter that university rankings will be a thing of the past 10 years from now, and we'll look back on the university heads that first led us away from them with a great respect and appreciation....1/

2 11 44

Reposted by Kou Murayama

Julia M. Rohrer @dingdingpeng.the100.ci · May 26

Writing some paragraphs about odds ratio and, more generally, different scales in nonlinear models.

Any favorite articles on odds ratio?>

19 21 120

Kou Murayama @koumurayama.bsky.social · May 24

In Japan every morning you can know your fortune of the day according to your zodiac sign and blood type.

1 1

Reposted by Kou Murayama

Ulrike Luxburg @ulrikeluxburg.bsky.social · May 23

Our cluster Machine Learning for Science is up for 7 years more funding!

ML for Science @ml4science.bsky.social · May 22

We're super happy: Our Cluster of Excellence will continue to receive funding from the German Research Foundation @dfg.de ! Here’s to 7 more years of exciting research at the intersection of #machinelearning and science! Find out more: uni-tuebingen.de/en/research/... #ExcellenceStrategy

The members of the Cluster of Excellence "Machine Learning: New Perspectives for Science" raise their glasses and celebrate securing another funding period.

5 24

Kou Murayama @koumurayama.bsky.social · May 23

I need your input! Are there any good AI tools which can work on the reference section of a manuscript? i.e., you have a manuscript with an incomplete reference section and the tool can proactively find missing papers and information (e.g., page numbers). Like what journal production teams do.

1 1

Reposted by Kou Murayama

Manuel Bohn @elmanubohn.bsky.social · May 20

New preprint w/ @christophvoelter.bsky.social et al.

Individual differences in great ape cognition across time and domains: stability, structure, and predictability

48 apes 🦍, 10 tasks 🧠, 10 sessions📊, 1.5 y📅
✅ Stable individual traits
❌ No g-factor
🤝 Social ≠ non-social

🔗: osf.io/preprints/ps...

OSF

osf.io

11 26

Reposted by Kou Murayama

Sam Gershman @gershbrain.bsky.social · May 19

This highlights the point that comparisons between humans and machines are continually muddied by a lack of distinction between evolution and development, both of which contribute to learning in the broad sense.

4 4 27

Reposted by Kou Murayama

Charley Wu | hiring PhDs/Postdocs @thecharleywu.bsky.social · May 19

Since traveling to #cogsci2025 may be particularly difficult this year, we’re hosting a local workshop in Tübingen!
📅 July 24 | Talks & posters + catering supported by @ml4science.bsky.social
Open to *everyone*, even without an accepted paper/abstr.
👉 Register by July 1: forms.gle/v6VtEE6UqYw5...

Tübingen pre-CogSci workshop 2025

July 24th from 10:00 - 15:00, Ground floor seminar room, Maria-von-Linden Str. 6 For the cognitive science community here in Tübingen, the annual Cogsci conference (https://cognitivesciencesociety.or...

forms.gle

13 35

Reposted by Kou Murayama

Berna Devezer @devezer.bsky.social · May 15

You don't want to miss this preprint (soon to be posted) about the many sins and crimes of p-curve procedures. See a quick tl;dr below. They were prematurely introduced into the science reform literature without doing the foundational theoretical work needed for all statistical methods.

Richard D. Morey @richarddmorey.bsky.social · May 15

@clintin.bsky.social and I show in a new paper (for which we are about to submit a revision ) that 1) the p curve procedures are inappropriately sensitive, 2) inadmissible (i.e. have lower power than some other procedure for all alternatives), 2/

1 6 23

Reposted by Kou Murayama

Tobias Hauser @tobiasuhauser.bsky.social · May 14

#OCD is a understudied disorder, meaning that we know way too little about the underlying (brain) processes.
We have thus built the Brain Explorer app www.brainexplorer.net where everyone can easily contribute to understanding OCD.
#MentalHealthAwareness @tueneurocampus.bsky.social @ucl.ac.uk

Brain Explorer - Test your brain power

The brain explorer app for Apple and Android tests your brain functions and helps researchers to understand the brain. Explore your brain power and how brain functions are important for mental health.

www.brainexplorer.net

1 13 8

Reposted by Kou Murayama

Julia M. Rohrer @dingdingpeng.the100.ci · May 11

Thanks to everybody who chimed in!

I arrived at the conclusion that (1) there's a lot of interesting stuff about interactions and (2) the figure I was looking for does not exist.

So, I made it myself! Here's a simple illustration of how to control for confounding in interactions:>

69 280 1.1K

Reposted by Kou Murayama

Jay Patel @infotainment.bsky.social · May 11

Behavioral scientists: If you want to impress us, show us how to increase our end-of-semester Course Evaluation Survey responses.

#psych #nudge #behsci

3 1 4

Reposted by Kou Murayama

SRMA-SIG @srma-sig.bsky.social · May 9

Please join us next week Friday for our final seminar of the 2025 season! We are thrilled to be joined by Dr. Richard Riley (@richarddriley.bsky.social), a leading expert in individual participant data meta-analysis, to discuss the rationale, concepts, and pitfalls in conducting IPD syntheses.

AERA Systematic Review and Meta-Analysis SIG Online Seminar Series

Friday, May 16, 2025
8 am PDT / 9 am MDT / 10 am CDT / 11 am EDT / 15.00 UTC
**note the earlier time**

Individual Participant Data Meta-Analysis Projects: Rationale, Concepts and Pitfalls
Dr. Richard Riley, University of Birmingham

More details and registration at https://www.srmasig.org/seminar/upcoming-seminars/

1 12 13

Reposted by Kou Murayama

WesternU Research @westernuresearch.bsky.social · May 7

Join #WesternU as our next Canada Excellence Research Chair ( #CERC). The awards provide for international researchers to lead prestigious research programs at Western and contribute to Canada's excellence in research & innovation.

Application review begins June 4, 2025.

www.uwo.ca/research/cer...

1 10 10

Reposted by Kou Murayama

Virginia Gewin @virginiagewin.bsky.social · May 6

“There is far too much power in the hands of professors in the German system,” says @leising.bsky.social.

My latest @nature.com story digs into efforts to tackle the entrenched structural heirarchy that enables academic bullies.

Can Germany rein in its academic bullying problem?

Researchers and administrators are exploring ways to restructure a rigid hierarchy that can breed power abuses.

www.nature.com

4 87 170

Reposted by Kou Murayama

Charles Logan @charleswlogan.bsky.social · May 2

FYI: The Spencer Foundation, Kapor Foundation, The William T. Grant Foundation, and the Alfred P. Sloan Foundation have collaborated to offer $25K rapid response grants.

"This rapid response bridge funding opportunity is for scholars and teams whose grants have recently been cancelled by NSF."

Rapid Response Bridge Funding Program

In the face of recent abrupt shifts in federal funding for education research, including large-scale terminations of National Science Foundation (NSF) research grant awards, we have developed a rap...

www.spencer.org

6 550 760

Reposted by Kou Murayama

William Ngiam | 严祥全 @williamngiam.github.io · Apr 24

I created this reading list on theory in psychology a while back, so it probably needs an update! Would love any recommendations for papers to include – maybe I can turn this into a syllabus of sorts.

PDF of this reading list here: williamngiam.github.io/reading_list...

A reading list on theory in psychological science; it contains ten papers, a summary of those papers, keywords and a related resource. This is best viewed at https://williamngiam.github.io/reading_lists/#theory

2 17 52

Reposted by Kou Murayama

Charley Wu | hiring PhDs/Postdocs @thecharleywu.bsky.social · Apr 25

🙌 Hot off the presses @natcomms.nature.com! We created a custom #Minecraft environment to study a long-standing puzzle in cognitive science:
How do humans flexibly adapt their individual and social learning strategies in dynamic, realistic situations? Check it out 👉 www.nature.com/articles/s41... 🧵👇

8 55 180

Kou Murayama @koumurayama.bsky.social · Apr 25

Our new preprint by Claudia Neuendorf!! Is social network information useful for prediction? Using a social network dataset of 46,000 students in 2,000 classrooms, we predicted various class-level outcomes from 313 social network metrics with machine learning methods.

osf.io/preprints/ps...

OSF

osf.io

1 7

Reposted by Kou Murayama

Dr. Kristy A. Robinson @krisarob.bsky.social · Apr 22

Super excited for #AERA2025 to kick off tomorrow! As a former Coloradan and frequent visitor who currently lives at sea level, while we're in the Mile High City I highly recommend keeping well hydrated and looking for signs of altitude sickness. It's a thing!

en.wikipedia.org/wiki/Altitud...

6 6 24

Reposted by Kou Murayama

Jeff Greene @jeffgreene.bsky.social · Apr 21

An instrument is not reliable or valid. Viewing validity as an argument, based on multiple types of validity and reliability evidence, addresses concerns about alpha, in particular. #PsychSciSky #AcademicSky #EduSky doi.org/10.1007/s106...

Why We Might Still be Concerned About Low Cronbach’s Alphas in Domain-specific Knowledge Tests - Educational Psychology Review

Edelsbrunner et al. Educational Psychology Review, 37, 1–43, 2025 recently published a systematic review and meta-analysis of Cronbach's alphas in domain-specific knowledge tests. While appreciating…

doi.org

1 4

Reposted by Kou Murayama

Drew Engelhardt @amengel.bsky.social · Apr 20

Okay appendices are getting out of control.

1 1 11

Kou Murayama @koumurayama.bsky.social · Apr 20

Just to give a context. He is not a leader or a ministry. He is an MP of an opposition party.

Kou Murayama @koumurayama.bsky.social · Apr 20

Also don’t forget cash! We had a small trip and none of the places accepted card payment!

1

Kou Murayama @koumurayama.bsky.social · Apr 19

I think you are talking about “ablations” in LLM? This has been common ever since neural network I believe.

2