iiinova — where your digital self keeps evolving

Reposted by Steve Haroz

Michael Friendly @datavisfriendly.bsky.social · 20h

#TodayinHistory #dataviz #OTD 📊 🎂Sep 29, 1829 Michael George Mulhall born in Dublin, Ireland 🇮🇪 1884: 🥇1st? use of a pictogram, to represent data by icons proportional to a number The train one is accurate; the wheel one commits the area illusion, using diameter to represent the number

Capital employed in 1882 in France, UK and US, portrayed by trains whose length is ~ to the number

Pictograms displaying Steam power (top) and horsepower per 1000 inhabitants by wheels whose diameter is proportional to the number represented

Photo of Michael Mulhall looking to his right and wearing a long beard

071

Steve Haroz @steveharoz.com · 21h

So the whole giant story about 5 men being stopped from performing a major terrorist attack on a UK air force base involved in the US war on Iran ... is looking like just some local guys stealing petrol from nearby farm equipment. 🤡

011

Reposted by Steve Haroz

Sam Schwarzkopf @sampendu.bsky.social · 23h

If you can spare ~20 min on an online study on perception & #mentalimagery please consider participating: #visionscience #psychscisky #neuroskyence tstbl.co/131-782

11514

Reposted by Steve Haroz

Anthony Moser @anthonymoser.com · 21/09/2026

as a hater let me acknowledge something ai is good at: producing irritating discourse at scale this is usually because, like "ai" itself, people are talking about different things like they are one thing so let me disentangle, with statements numbered for easy disagreement

6401116

Reposted by Steve Haroz

Brian McNoldy @bmcnoldy.bsky.social · 26/09/2026

If I search for tropical cyclones that actually came within 100 miles of New Mexico, I found 16 of them going back to 1916. The most recent was Newton in 2016. This isn't just remnants bringing rain, these are actual data points as tropical cyclones.

4403

Reposted by Steve Haroz

Michelle Greene @mgreenephd.bsky.social · 25/09/2026

🚨New paper alert! 🚨 The visual system tunes itself to the statistics of its input. How do individual experiences differently tune vision? In this work, @bjbalas.bsky.social and I examined how one individual difference—height—changes the visual diet and how this affects perception. 1/

29430

Reposted by Steve Haroz

Katie Mack @astrokatie.com · 24/09/2026

💯

684083

Reposted by Steve Haroz

Leah McElrath @leahmcelrath.bsky.social · 24/09/2026

AP Stylebook warns against anthropomorphizing AI systems: “Avoid language that gives them human characteristics… Instead, explain what a system does, how well it performs, who built it and who could be affected by it.”

APStylebook @APStylebook
X.com
Artificial intelligence systems do not think, feel, want or understand. Avoid language that gives them human characteristics. This is called anthropomorphizing, when we ascribe human traits, emotions or behaviors to non-human things, such as animals or inanimate objects.
Instead, explain what a system does, how well it performs, who built it and who could be affected by it.

1970102257

Reposted by Steve Haroz

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 Steve Haroz

Dan Quintana @dsquintana.bsky.social · 19/09/2026

New preprint! 🎉 I analysed 1660 papers from 4 psychology journals and found materials sharing went from 9% of papers in 2015 to 82% in 2025, and these materials *do* get downloaded — a median of 135 times each. BUT shared code is often hard to run. doi.org/10.31234/osf... Let's walk through it 🧵

Two-panel figure. Panel a is a flow diagram tracking 1,611 empirical psychology articles from publication year (545 in 2015, 552 in 2020, 514 in 2025) to repository-link type: 785 link an OSF project, 85 link another platform, and 741 link no repository. Of those with an OSF link, download counts were retrieved for 670 and not retrieved for 115. Panel b is a line chart of the share of empirical papers linking OSF across 2015, 2020 and 2025. The overall rate, shown as a dashed black line, rises from 9% to 57% to 82%. All four journals rise steeply and end close together: Psychological Science 92%, JESP 89%, JML 83%, Cognition 76%, with Psychological Science highest throughout.

Three-panel figure. Panel a: ridgeline plot of downloads per file by material type on a log scale, with the percentage never downloaded labelled for each — archive 16% of 545 files, documents 20% of 2,970, code 12% of 3,471, other 17% of 1,646, data 21% of 10,051, media 35% of 2,120, images 35% of 4,102. Most files cluster between 1 and 10 downloads, with long right tails past 100. Panel b: ridgeline plot of downloads per paper by journal, log scale, with dashed median lines; Psychological Science is highest, then JESP, JML and Cognition. Panel c: stacked bars showing, for documents, data and code separately, the share of papers by download band (0, 1–10, 11–100, more than 100) in 2015, 2020 and 2025. The share exceeding 100 downloads falls sharply over time in all three types, from roughly two-thirds in 2015 to a quarter or less in 2025, as the 1–10 band grows.

Four-panel figure. Panel a: statistical languages detected among 333 papers with retrievable code — R 88%, SPSS 12%, Stata 4%, SAS 1%. Panel b: code red flags among those 333 papers — 34% hard-code an absolute path, 40% reference a missing file — above documentation among 672 OSF-linked papers — 21% have a README, 30% are documented by README, description or wiki. Panel c: among 562 Elsevier papers with no repository link, 44% (245) host at least one journal supplementary file but only 14% (77) host data, code or an archive. Panel d: composition of those 448 hosted files — documents 52%, data 21%, media 9%, other 7%, archive 6%, code 3%, images 1%. The code panels are green, the journal-supplement panels blue.

Coefficient plot (download predictors)

Dot-and-whisker plot of three standardised predictors of OSF download volume, each with a 95% confidence interval. Repository size (number of files) has the largest effect at about 0.76, citations about 0.38, and altmetric attention about 0.12. All three intervals sit entirely above zero, so each predicts more downloads, with repository size roughly twice the effect of citations and six times that of attention. X-axis: standardised effect, −0.2 to 1.0.

4264111

Steve Haroz @steveharoz.com · 17/09/2026

Many people are disappointed with the current state of technology, but the "popcorn" button on modern microwaves does actually work now.

151888

Reposted by Steve Haroz

Jon Harmon (he/him/his) @jonthegeek.com · 16/09/2026

I made it through my #PositConf2026 talk! The Design of Everyday #RStats Functions. Slides here: stbl.wrangle.zone/slides/every... The underlying 📦 {stbl} is on CRAN!

stbl.wrangle.zone

The Design of Everyday R Functions

5548

Steve Haroz @steveharoz.com · 16/09/2026

There is a spectrum of error culpability from typo to programming mistake to results-aware decision-making to negligent experiment/anslysis design. Fraud is the most extreme and could be the least common source of error.

100

Steve Haroz @steveharoz.com · 15/09/2026

I need everyone in marketing and branding to understand that no one gives a shit about their corporate updates. This is the actual title of an email I got today.

1100

Reposted by Steve Haroz

samuel mehr @mehr.nz · 15/05/2026

annals of book research, part one no amount of prior experience in child development can prepare you for this insane 1998 bill from the State of Florida, which REQUIRES state-funded daycares to PLAY CLASSICAL MUSIC TO INFANTS because they have ONE HUNDRED BILLION BRAIN CELLS

Florida Senate - 1998 SB 660
By Senator Turner
36-628-98
1 A bill to be entitled
2 An act relating to education; providing that
3 state-funded education and care programs for
4 infants and toddlers must foster brain
5 development; requiring an evaluation and a
6 report; providing an effective date.
7
8 WHEREAS, at birth, a child has one hundred billion
9 brain cells that will be developed by the experiences of life,
10 and
11 WHEREAS, the stimulation that causes brain development
12 can be positive, such as conversation, music, and parental
13 love, or it can be negative, such as neglect or emotional and
14 physical abuse, and
15 WHEREAS, during the first year of a child's life the
16 connections between the cells, the synapses, increase
17 twenty-fold, making the first year a crucial time for brain
18 development, and
19 WHEREAS, infants develop synapses when they listen to
20 language and music, see colors and shapes, and feel and handle
21 objects of different sizes, shapes, and textures, and
22 WHEREAS, there is no other time in a child's life as
23 productive for brain development as the first year, NOW
24 THEREFORE,

Be It Enacted by the Legislature of the State of Florida:
27
28 Section 1. Each state-funded education and care
29 program for children from birth to 5 years of age must provide
30 activities to foster brain development in infants and
31 toddlers. A program must provide an environment rich in
1
CODING:Words stricken are deletions; words underlined are additions.
Florida Senate - 1998 SB 660
36-628-98
1 language and music and filled with objects of various colors,
2 shapes, textures, and sizes to stimulate visual, tactile,
3 auditory, and linguistic senses in the children and must
4 include classical music and at least 30 minutes of reading to
5 the children each day. A program may be offered through an
6 existing early childhood program such as Healthy Start, the
7 Title I program, subsidized child care, the prekindergarten
8 early-intervention program, Florida First Start, the Head
9 Start program, or a private childcare program. A program must
10 provide training for the infants' and toddlers' parents
11 including direct dialogue and interaction between teachers and
12 parents demonstrating the urgency of brain development in the
13 first year of a child's life.

3536

Reposted by Steve Haroz

Matthew B. Jané @matthewbjane.bsky.social · 13/09/2026

I’ve been quiet on social media lately, but today I’m launching Audit Clinical Evidence (ACE), an initiative I’ve been developing over the past year. Take a look: AuditClinicalEvidence.org

auditclinicalevidence.org

ACE

Independent audits of published clinical research for statistical errors, data inconsistencies, and research integrity violations.

89132

Reposted by Steve Haroz

Solomon Kurz @solomonkurz.bsky.social · 04/07/2026

At a basic level, I think this depends on what you care about. If you want quick pubs for a grade or a promotion, just do t-tests. If you are interested in your data, learn how to fit and interpret ordinal models.

66114

Reposted by Steve Haroz

Icelandic Vision Lab @icevislab.bsky.social · 10/04/2026

🚨Preprint Alert🚨and Thread 🧵 The Visual Imagery Visually Anchored Scale (VIVAS) reveals dissociable perceptual dimensions and category-specific structure: osf.io/preprints/ps... Authors: @heidasigurdar.bsky.social, Árnason, Mäekalle, Vésteinsdóttir, @arnig.bsky.social 1/9

Photo of an eye by Beel coor on Unsplash: https://unsplash.com/photos/brown-and-black-eye-illustration-1AIHIjtuNCI

12513

Reposted by Steve Haroz

Timnit Gebru @timnitgebru.blacksky.app · 13/08/2026

🔇 🔇 🔇 My book, Deep Unlearning, is now available for preorders! I don't know how people write so many books because this one took a lot out of me. It turns out, I had a lot to say 😂, with editors cutting out 50k of my words 🫣 ✴️ You can now preorder it at www.simonandschuster.com/books/Deep-U....

Cover of my new book, Deep Unlearning: The Rise of AI and The Radicalization of a Tech Idealist.

There are two concentric circles in the book, the left being circuits in black an white, and the right being a bunch of dots with orange accents. The cover background is cream. And the words are written in black except for "Un" which is in orange.

732156755

Reposted by Steve Haroz

Giles Wilkes @gilesyb.bsky.social · 09/09/2026

It's always the way, isn't it giftarticle.ft.com/giftarticle/...

Graph shows far right support higher where the number of foreign nationals is lowest

763083812

Reposted by Steve Haroz

Derek Arnold @visnerd.bsky.social · 08/09/2026

A recent paper argued that there is no visual binding problem. I disagree, and wrote a response... journals.sagepub.com/doi/10.1177/... Related demonstrations can be found here... staff.psy.uq.edu.au/~uqdarnol/JS...

62412

Reposted by Steve Haroz

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 04/09/2026

It's a systemic problem in science reporting that these summaries exaggerate the evidence. In the actual candy study, the participants were all students, status was manipulated in the lab by telling some students they were better than others, and "nearly twice" means 1 piece vs 2 pieces.

Piff and his colleagues found that upper-class drivers were more likely to cut other cars off at junctions and ignore pedestrians at crossings. Wealthier people also appeared more willing to lie at work. In one experiment, volunteers were left alone with a jar of sweets ostensibly meant for children. When the researchers returned, upper-class people had snaffled nearly twice as many candies as lower-class people.

1329166

Steve Haroz @steveharoz.com · 03/09/2026

Every time manipulated or fabricated data is discovered, I think of all the studies I ran that could have told an incredibly compelling story if only the results were different. It's also why I've grown skeptical of people described as good "storytellers".

2425

Steve Haroz @steveharoz.com · 02/09/2026

Data Colada's scrutiny was only possible because they got the data. That's why I think that authors who don't share data+materials (and editors who protect those authors by allowing them to not share data+materials) are basically stating that they don't care if the results are misleading.

181

Reposted by Steve Haroz

Mark Rubin @markrubin.bsky.social · 02/09/2026

“To err is science.” Stephan Guttinger reviews Douglas Allchin's new book: "Toward a Philosophy of Error in Science" doi.org/10.1093/bios...

1215

Reposted by Steve Haroz

Kory Stamper @korystamper.bsky.social · 02/09/2026

Pro tip! The less you post about "Lake America," the less written evidence of its use there is, and the less likely any reputable dictionary company will enter it into their dictionaries. ONLY *YOU* CAN PREVENT BAD LEXICOGRAPHY

9399105

Reposted by Steve Haroz

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

Rakow’s new paper found that “around 90% of articles that discuss replication and over 80% of articles with author-identified replications are missed by searching databases for replicat* because databases hold few details per article”. 8/

1145

Steve Haroz @steveharoz.com · 31/08/2026

I went to see a movie in the theater for the first time in over a decade. The movie and theater were great. The other people seeing the movie were not. If movie theaters are still around in another 10 years, I'll try again.

030

Reposted by Steve Haroz

paolo @paolopalma.bsky.social · 20/08/2026

*hank hill voice* i sell spreadsheets and spreadsheet accessories

0132

Reposted by Steve Haroz

Will Harrison @willjharrison.bsky.social · 20/08/2026

great to see some places still have a backbone

071

Reposted by Steve Haroz

Jay Van Bavel, PhD @jayvanbavel.bsky.social · 19/08/2026

Using AI helps people get higher grades and get their work done faster, but they learn less & suffer on actual exams I saw this in my own large Intro Psych class: -the exam average is 85% -after AI, it shot up to 95% -after I made the final in person it went to 68% www.economist.com/graphic-deta...

14391150

Steve Haroz @steveharoz.com · 19/08/2026

Every once in a while, I am expecting an actual phone call and need to turn on the ringer. The frequency and quantity of scam/spam phone calls is incredibly annoying. My phone warns me, but it's still so obnoxious.

050

Reposted by Steve Haroz

Priya Silverstein @priyasilverstein.com · 17/08/2026

Should we still use the term "preregistration"? Our take here: osf.io/preprints/ps... tl;dr: we think yes! With @lspitzer.bsky.social, @lukaswallrich.bsky.social, and @josefinaw.bsky.social

osf.io

OSF

02513

Reposted by Steve Haroz

Health Nerd @gidmk.bsky.social · 17/08/2026

The Jason Arday saga made me furious and sad in equal measure so I wrote about it. The whole thing is deeply unpleasant. gidmk.substack.com/p/the-jason-...

gidmk.substack.com

The Jason Arday Saga Is Terrible And Everyone Involved Should Be Ashamed Of Themselves

The whole thing makes me furious

1012050

Reposted by Steve Haroz

Janne M. Korhonen @jmkorhonen.fi · 16/08/2026

If someone says "University of Ghent" from now on, pretty sure my first reaction will be "oh the place that hired a white supremacist antivaxxer who spent Ghent money to hound one academic to suicide and wants to hound others in order to become a professor of race 'science' and eugenics at Harvard?"

412839

Reposted by Steve Haroz

Olivia Guest · Ολίβια Γκεστ @olivia.science · 16/08/2026

There's even research into it, hilariously from pro AI people... It's like how even the petrochemical industry discovered they would ruin the planet Tully, S. M., Longoni, C., & Appel, G. (2025). Lower Artificial Intelligence Literacy Predicts Greater AI Receptivity. Journal of Marketing.

journals.sagepub.com

Lower Artificial Intelligence Literacy Predicts Greater AI Receptivity - Stephanie M. Tully, Chiara Longoni, Gil Appel, 2025

As artificial intelligence (AI) transforms society, understanding factors that influence AI receptivity is increasingly important. The current research investig...

17932

Steve Haroz @steveharoz.com · 12/08/2026

Unbiased but noisy! Great post by @gelliottmorris.com. While outcomes are necessarily dichotomous, predictions and the reliability of polling are often reported that way too. Polling can be both noisy and still informative.

I modified the noisy correlation graph to show red dots when the vote direction flips relative to the prediction.

030

Reposted by Steve Haroz

Lynn Schmittwilken @lschmittwilken.bsky.social · 04/08/2026

So happy to see this published! 🎉 Meet **deadleaves**, an #OpenScience Python package for generating Dead Leaves images to study #vision, segmentation, natural image statistics, and beyond. 📄 Paper (JOSS): doi.org/10.21105/jos... 📚 Documentation: deadleaves.readthedocs.io For more info 🧵

1126

Reposted by Steve Haroz

Dan Quintana @dsquintana.bsky.social · 11/08/2026

This is also a good reminder that scientific infrastructure is not free. Very easy to forget when the service *itself* is free.

0335

Steve Haroz @steveharoz.com · 11/08/2026

I'm very disappointed that research institutions and funding agencies have failed to step up over the years. Their unusable opaque archiving systems never held a candle to the transparency, usability, or accessibility of OSF.

1101

Steve Haroz @steveharoz.com · 06/08/2026

Also, I can't think of any good reason to put either gender or birth sex on a passport, ID, or drivers license.

090

Reposted by Steve Haroz

Retraction Watch @retractionwatch.com · 04/08/2026

The Center for Scientific Integrity is proud to announce the inaugural winners of the 2026 Ctrl-Z Award. Named for the universal keyboard shortcut for “undo,” the Ctrl-Z Award this year honors @cetaceanneeded.bsky.social and @katelaskowski.bsky.social for choosing transparency over reputation.

science.org

ScienceAdviser Exclusive: Meet the inaugural winners of the Ctrl Z Award

Today in Science and science: Ice age hunters’ penchant for female mammoths, a detailed vagal map, and more

26725

Reposted by Steve Haroz

SoundOfTheForest @soundoftheforest.bsky.social · 31/07/2026

I don’t care how respected you are as a person, science educator, author, artist, etc. If I find out that you are using generative AI in any aspect of your work, you lose all of my respect.

10822277