iiinova — where your digital self keeps evolving

Reposted by Javier Enrique Aguilar

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.

422054930

Reposted by Javier Enrique Aguilar

Herman @herman-tesso.bsky.social · 04/03/2026

If you have been using LOO-PIT, this is a must read for you; "LOO-PIT predictive model checking" by me and @avehtari.bsky.social , doi.org/10.48550/arX.... 1/4

Title: LOO-PIT predictive model checking ,

Authors: Herman Tesso and Aki Vehtari ,

Abstract: We consider predictive checking for Bayesian model assessment using leave-one-out
probability integral transform (LOO-PIT). LOO-PIT values are conditional cumulative predictive
probabilities given LOO predictive distributions and corresponding left out observations. For a
well-calibrated model, LOO-PIT values should be near uniformly distributed, but in the finite sample
case they are not independent, due to LOO predictive distributions being determined by nearly the
same data (all but one observation). We prove that this dependency is non-negligible in the finite
case and depends on model complexity. We propose three testing procedures that can be used for
continuous and discrete dependent uniform values. We also propose an automated graphical method
for visualizing local departures from the null. Extensive numerical experiments on simulated and real
datasets demonstrate that the proposed tests achieve competitive performance overall and have much
higher power than standard uniformity tests based on the independence assumption that inevitably
lead to lower than expected rejection rate

1102

Reposted by Javier Enrique Aguilar

Aki Vehtari @avehtari.bsky.social · 18/08/2026

@florencebockting.bsky.social's guide "Contributing to Stan A Developer’s Guide to the Core, Interfaces, and First Contributions" at florence-bockting.github.io/stancon-cont...

florence-bockting.github.io

Contributing to Stan

052

Reposted by Javier Enrique Aguilar

mr. TIM @timkellogg.me · 23/07/2026

the Dinitz-Garg-Goemans conjecture, a graph theory problem that’s gone unsolved for 30 years, was solved with this prompt

Construct a counterexample to general (non-planar) case of Dinitz Garg Goemans conjecture. You should do a breakthrough and find a structured counterexample.

3045653

Reposted by Javier Enrique Aguilar

Gabriel Peyré @gabrielpeyre.bsky.social · 02/07/2026

Slides for an introductory talk on IA for maths. speakerdeck.com/gpeyre/ia-fo...

speakerdeck.com

IA for theory

Slide for an introduction talk on IA for maths.

1329

Reposted by Javier Enrique Aguilar

Aki Vehtari @avehtari.bsky.social · 03/06/2026

Having seen the submitted talks and posters, StanCon 2026 is going to be awesome!

0154

Reposted by Javier Enrique Aguilar

Simon Kuestenmacher @simongerman600.bsky.social · 31/05/2026

A little factoid to make you happy.

513332

Reposted by Javier Enrique Aguilar

Aki Vehtari @avehtari.bsky.social · 07/04/2026

More details about the Bayesian Workflow book and case studies now available on the book web site avehtari.github.io/Bayesian-Wor... (but you still need to wait a bit for the book)

avehtari.github.io

Bayesian Workflow book: Website – Bayesian Workflow book

210328

Reposted by Javier Enrique Aguilar

Leonid Schneider @forbetterscience.bsky.social · 25/03/2026

Oh nothing, just a peer reviewed paper my colleagues found... doi.org/10.1016/j.ma... "1 mL of the mass killing of an ethnic group was opposed to 20 mL of the skin sample and unprotected to light for 7 min." Even AI knows what's wrong here, but @elsevierconnect.bsky.social doesn't.

1521790

Reposted by Javier Enrique Aguilar

Andrew Gelman et al. @statmodeling.bsky.social · 20/03/2026

Nutpie: state-of-the-art mass matrix adaptation for HMC statmodeling.stat.columbia.edu/2026/03/20/n...

statmodeling.stat.columbia.edu

Nutpie: state-of-the-art mass matrix adaptation for HMC | Statistical Modeling, Causal Inference, and Social Science

0186

Reposted by Javier Enrique Aguilar

Ian Hussey @ianhussey.mmmdata.io · 12/01/2026

Me: surely at least the statistics literature has its house in order. The stats literature:

45412

Reposted by Javier Enrique Aguilar

Sam Power @spmontecarlo.bsky.social · 09/12/2025

We've been lucky to host a number of excellent speakers at the Online Monte Carlo Seminar this past term; please do visit the YouTube channel (www.youtube.com/playlist?lis...) to catch up on these interesting recent developments! (and we'll be back again from January!)

0177

Reposted by Javier Enrique Aguilar

Quanta Magazine @quantamagazine.org · 18/12/2025

It was a big year for mathematics. youtu.be/hRpcWpAeWng

youtu.be

The Biggest Breakthroughs in Mathematics: 2025

YouTube video by Quanta Magazine

04617

Reposted by Javier Enrique Aguilar

Hadas Weiss @hadas.bsky.social · 06/12/2025

has anyone made it to the top of maslow's pyramid i have a question

12749

Reposted by Javier Enrique Aguilar

Hadas Weiss @hadas.bsky.social · 07/12/2025

rejection wrapped?

3461

Reposted by Javier Enrique Aguilar

λ³🎲 @cubiclogic.bsky.social · 29/11/2025

"On this day, 29 November, in 1873 Georg Cantor wrote a letter to Richard Dedekind. It contained a question that inaugurated a new mathematical discipline: Set Theory." hartkp.weblog.tudelft.nl/2017/11/29/o...

281

Reposted by Javier Enrique Aguilar

Aki Vehtari @avehtari.bsky.social · 27/11/2025

While I was busy, @joachim.cidlab.com and @janhove.bsky.social already provided valid short answers. I wrote a bit more at statmodeling.stat.columbia.edu/2025/11/27/e...

statmodeling.stat.columbia.edu

Effective sample size | Statistical Modeling, Causal Inference, and Social Science

2112

Reposted by Javier Enrique Aguilar

Hadas Weiss @hadas.bsky.social · 25/11/2025

old google scholar: stand on the shoulders of giants ai google scholar: or plagiarize them lol

1505

Reposted by Javier Enrique Aguilar

Health Nerd @gidmk.bsky.social · 11/11/2025

This is one of the most remarkable academic debacles I've ever seen. A large RCT got published in BMJ. There are currently 44 Pubpeer comments, mostly about the data, including...well. Read for yourself. pubpeer.com/publications...

pubpeer.com

PubPeer - Prevention of acute myocardial infarction induced heart fail...

There are comments on PubPeer for publication: Prevention of acute myocardial infarction induced heart failure by intracoronary infusion of mesenchymal stem cells: phase 3 randomised clinical trial (P...

1313845

Reposted by Javier Enrique Aguilar

Cameron Patrick @cameronpat.bsky.social · 04/11/2025

happy 11th anniversary to this email sent to all staff at the School of Mathematics and Statistics

Dear All,

I am delighted to report to you the first results of an experiment that is being conducted in the tea room of this Department.

On 29 August, an Oslo Stainless Steel Cutlery Set (48 Pieces: 12 Knifes, 12 Forks, 12 Tea Spoons, 12 Dinner Spoons) was placed in a drawer in the Departmental tea room. A poster asking not to remove the cutlery from the tea room was attached in a visible location.

The original research plan was to monitor (in real time) the disappearance of the cutlery from the tea room and then fit a point/counting process model to the observed data. However, as the research project failed to attract any major grants (and so hiring a research assistant to do the work was impossible), it was decided to conduct opportunistic discrete monitoring only.

Here is the first result: sixty days in the experiment, the disappearance rates stand as follows:

Knives: 8.3%
Forks: 100%
Tea spoons: 58.3%
Dinner spoons: 41.7%

Possible conclusions include, but are not limited to, the following:

the people who removed the missing cutlery don’t understand written English; they don’t see forks as a special case of cutlery; forks are needed to do some kind of mathematics; the knives from the set are no good; small spoons are slightly more attractive than the large ones; things left in our tea room tend to disappear even if they are not edible; further research is needed to fully understand the phenomenon.

Best,
kostya borovkov

1114832

Reposted by Javier Enrique Aguilar

Johann-Friedrich Salzmann (Joff) @jfsalzmann.com · 12/10/2025

I'm looking for a PhD position (PolSci / Sociology / Data Science) starting this autumn or winter: jfsalzmann.com # Bayesian Modelling, Electoral Behaviour, Opinion Dynamics I'm a Berlin-based recent graduate in Data Science, Public Policy from the Hertie School. 1/6

jfsalzmann.com

Johann-Friedrich Salzmann

Academic Website, Portfolio, and Contact Information

163

Reposted by Javier Enrique Aguilar

Gabriel Peyré @gabrielpeyre.bsky.social · 27/09/2025

Thought of the day: It is somewhat mysterious why Gaussians remain stable under the particle-minimizing flow (i.e. the Wasserstein gradient flow) for so many widely used energies: entropy, Fisher information, quadratic interaction potentials, functionals depending only on mean and covariance,

1182

Reposted by Javier Enrique Aguilar

Clément Canonne @ccanonne.github.io · 21/10/2025

Do terminal-embedded LLMs have pipe dreams

171

Reposted by Javier Enrique Aguilar

WeRateDAGs @weratedags.com · 17/10/2025

A palate cleanser: 'The causal structure of banana'. Robust, simply structured, and convenient. 8/10. The DAG is nice too. This is the first of three bananadags in Hitchcock (2016) "Conditioning, intervening, and decision".

"Fig 1. The causal structure of Banana"

(Apparently your favourite mid-morning snack is a mediation problem)

2297

Reposted by Javier Enrique Aguilar

Sam Power @spmontecarlo.bsky.social · 17/10/2025

sensational energy here

1517

Reposted by Javier Enrique Aguilar

Peter Tennant @pwgtennant.bsky.social · 14/10/2025

Last year, I had a paper rejected after 18 months with the @amjepi.bsky.social. It's the first time I've had a paper rejected after being invited for revisions. And the first time I've had a paper sent out to completely new reviewers. It stung so hard that it's taken me a year to look at again.

127419

Reposted by Javier Enrique Aguilar

Julius Kölzer @juliusk.bsky.social · 03/10/2025

35 years ago, on October 3, 1990, Germany was reunified. Just two months later, voters in the former GDR went to the polls in the first free federal election since the Weimar era. Despite decades of socialist dictatorship, East German voting behavior displayed marked regional differences. Thread🧵

212543

Reposted by Javier Enrique Aguilar

Aki Vehtari @avehtari.bsky.social · 01/09/2025

My Bayesian Data Analysis course at Aalto is starting in 20mins. There are now 375 registered students, but as the course is not compulsory for most, I expect about 230 students to finish it. All the course material is available online at avehtari.github.io/BDA_course_A...

avehtari.github.io

Bayesian Data Analysis course

17113

Reposted by Javier Enrique Aguilar

arxiv.stat.ME @arxiv-stat-me.bsky.social · 17/07/2025

Javier Enrique Aguilar, David Kohns, Aki Vehtari, Paul-Christian B\"urkner R2 priors for Grouped Variance Decomposition in High-dimensional Regression arxiv.org/abs/2507.11833

033

Reposted by Javier Enrique Aguilar

BayesFlow @bayesflow.org · 11/02/2025

Finite mixture models are useful when data comes from multiple latent processes. BayesFlow allows: • Approximating the joint posterior of model parameters and mixture indicators • Inferences for independent and dependent mixtures • Amortization for fast and accurate estimation 📄 Preprint 💻 Code

0296

Javier Enrique Aguilar @javieraguilar.bsky.social · 15/07/2025

I was at an event last week and someone said that there should be a social network where you could only join if you have an institutional email from a university 🤣.

030

Reposted by Javier Enrique Aguilar

ponder @ponder.ooo · 14/07/2025

unsolved millennium prize problems are just evidence that the problems are wrongly priced. if they gradually raise the reward money, eventually the supply and demand will match and a solution will arise. its just economics

48314

Reposted by Javier Enrique Aguilar

Hadas Weiss @hadas.bsky.social · 12/07/2025

as my final act of love i'll recommend rejection

2572

Reposted by Javier Enrique Aguilar

arxiv.stat.ME @arxiv-stat-me.bsky.social · 19/05/2025

Javier Enrique Aguilar, Paul-Christian B\"urkner Dependency-Aware Shrinkage Priors for High Dimensional Regression arxiv.org/abs/2505.10715

053

Reposted by Javier Enrique Aguilar

Aki Vehtari @avehtari.bsky.social · 21/05/2025

StanBio Connect 2025 free online conference May 30 stanbio.org ... Stan in biomedicine including drug discovery and development, bioinformatics, medical devices, health economics, real-world evidence, and decision-making under uncertainty

stanbio.org

StanBio Connect 2025 – StanBio

Advancing Biomedical Research with Stan

0167

Reposted by Javier Enrique Aguilar

International Society for Bayesian Analysis @isba-bayesian.bsky.social · 24/03/2025

2) The next two days will be focused on a topic of current interest in Bayesian analysis. The topic of this edition is "Bayesian modelling with brms". This 12-hour course is provided by Javier Enrique Aguilar (TU Dortmund University, Germany).

121

Reposted by Javier Enrique Aguilar

International Society for Bayesian Analysis @isba-bayesian.bsky.social · 24/03/2025

The València International #Bayesian Summer School (#VIBASS 8), a four-day summer school designed to provide an introduction to Bayesian learning, will take place7-10 July 2025 in València, Spain. Info and registration can be found at vabar.es

vabar.es

VABAR –VAlencia BAyesian Research group

This is the webpage of the VAlencia BAyesian Research group (VABAR). Based at the University of Valencia and heir of prominent Bayesians like Susie Bayarri and Juan Ferrándiz.

153

Reposted by Javier Enrique Aguilar

Hadas Weiss @hadas.bsky.social · 07/03/2025

"CALL FOR PAPERS"

3553

Reposted by Javier Enrique Aguilar

Hadas Weiss @hadas.bsky.social · 05/03/2025

journals when you ask about the status of your manuscript

315218

Reposted by Javier Enrique Aguilar

Pierre Alquier @pierrealquier.bsky.social · 05/03/2025

I already advertised for this document when I posted it on arXiv, and later when it was published. This week, with the agreement of the publisher, I uploaded the published version on arXiv. Less typos, more references and additional sections including PAC-Bayes Bernstein. arxiv.org/abs/2110.11216

110821

Reposted by Javier Enrique Aguilar

Adam Sharp @adamcsharp.bsky.social · 22/12/2024

During World War 1, fighting temporarily ceased in the trenches for Christmas and some German troops put up a sign meaning God with us – GOTT MIT UNS. The British troops then crawled across no-man’s land and wrote their own message on the German sign – WE GOT MITTENS TOO

1639761