iiinova — where your digital self keeps evolving

Germans Savcisens (Savčišens) @savcisens.com · 26/08/2026

Research can wait a night 😋 finishing this summer with a silver medal in volley 🥈

Germans Savcisens (Savčišens) @savcisens.com · 28/07/2026

It’s that time of the year, catch me at @ic2s2.bsky.social @uvmvermont.bsky.social. I am not presenting any works, but would love to catch up over a cup of coffee 😋☕️ #ic2s2

041

Reposted by Germans Savcisens (Savčišens)

Nature Portfolio @natureportfolio.nature.com · 01/02/2026

A feature in Nature reports how research shows that ‘exercise snacks’ and other forms of everyday movement can greatly reduce the risk of heart disease and death. #medsky 🧪

go.nature.com

The surprisingly big health benefits of just a little exercise

‘Exercise snacks’ and other forms of everyday movement can greatly reduce the risk of heart disease and death.

14014

Germans Savcisens (Savčišens) @savcisens.com · 25/12/2025

It’s been two years since we published the #life2vec paper, and it’s still circulating widely. People keep discovering it but much of what circulates online is misleading. Agter a long time, I finally wrote a short explainer to clear up a few things: converges.medium.com/is-life2vec-...

converges.medium.com

Is life2vec a mess? What the internet got wrong.

Over the past two years, online death calculators have flooded the internet. I think the craze really took off after the introduction of…

010

Germans Savcisens (Savčišens) @savcisens.com · 03/12/2025

Attending @neuripsconf.bsky.social this week! If you want to chat about LLMs for behaviour / health / labour modeling... or about beliefs and opinions of LLMs, hit me up. I’ll also be presenting a poster on truth tracking at the Mechanistic Interpretability workshop later. Come say hi!

010

Germans Savcisens (Savčišens) @savcisens.com · 29/11/2025

My 2 cents: If you exploited the #openreview bug or are actively searching for the leaked data, you should seriously reconsider your place in research. If you cannot uphold the basic principle of double-blind review, how can we trust anything you publish?

020

Germans Savcisens (Savčišens) @savcisens.com · 23/09/2025

Truthfulness isn’t always binary. Sometimes it’s… neither 🤔 Our Trilemma of Truth paper is headed to the @neuripsconf.bsky.social Mechanistic Interpretability workshop 🚀 Let’s connect in San Diego! 🌴 Preprint: arxiv.org/abs/2506.23921 Code and data: github.com/carlomarxdk/...

091

Germans Savcisens (Savčišens) @savcisens.com · 23/08/2025

Had the pleasure of presenting our work on Three-valued veracity probes for LLMs at #NEMI Workshop! Mechanistic Interpretability has such a great and welcoming community. If we crossed paths - let’s connect! 🚀 Poster: zenodo.org/records/1690... Preprint: arxiv.org/abs/2506.23921

050

Germans Savcisens (Savčišens) @savcisens.com · 25/07/2025

@nunetsi.bsky.social had a great week at @ic2s2.bsky.social! Looking forward to the next #IC2S2 in Vermont 🔬⛰️

0191

Reposted by Germans Savcisens (Savčišens)

The Institute for Analytical Sociology @iasliu.bsky.social · 25/07/2025

🎥 All keynote talks from IC²S² ‘25 are now available on our YouTube channel! #ic2s2 #css

0229

Germans Savcisens (Savčišens) @savcisens.com · 23/07/2025

Colleagues are making sure that I stay focused at #IC2S2 🤓

1231

Germans Savcisens (Savčišens) @savcisens.com · 22/07/2025

Presented our work on veracity-tracking in LLMs at #IC2S2 today! Now looking forward to the next few days of great talks and conversations ✨️🎓

060

Germans Savcisens (Savčišens) @savcisens.com · 21/07/2025

Little wins: our "Trilemma of Truth" dataset just hit 150 downloads. It contains true, false, and neither-valued statements (inspired by the three-valued logic) used to stress-test LLMs for fact-checking, veracity tracking, and uncertainty handling. Dataset📚: huggingface.co/datasets/car...

huggingface.co

carlomarxx/trilemma-of-truth · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

010

Germans Savcisens (Savčišens) @savcisens.com · 20/07/2025

Perfect weather, charming streets, and a poster so big it almost needed its own boarding pass 🧳✨ Excited to attend #IC2S2 in Norrköping 🇸🇪 Find me at the Poster Session on Tuesday: "Improving Probes that Track Veracity in Large Language Models" (Poster ID: 39) 🧪

061

Germans Savcisens (Savčišens) @savcisens.com · 18/07/2025

I’m presenting a poster on my latest project: “The Trilemma of Truth.” Drop by to see how LLMs leverage three‑valued logic to model truth 🔢🤖 And hey, if you fancy grabbing a coffee ☕, DM me! 📄 Poster: zenodo.org/records/1605... 📖 Preprint: arxiv.org/abs/2506.23921

070

Reposted by Germans Savcisens (Savčišens)

arXiv cs.CL Computation and Language @cscl-bot.bsky.social · 01/07/2025

Germans Savcisens, Tina Eliassi-Rad: The Trilemma of Truth in Large Language Models arxiv.org/abs/2506.23921 arxiv.org/pdf/2506.23921 arxiv.org/html/2506.23921

033

Germans Savcisens (Savčišens) @savcisens.com · 01/07/2025

🚨 New preprint! Do LLMs really know what’s true? In our paper, @eliassi.bsky.social and I introduce sAwMIL: a probing method that distinguishes between true, false, and neither—capturing what LLMs actually “retain.” We evaluated 16 open models across 3 new datasets. 📄 arxiv.org/abs/2506.23921

arxiv.org

The Trilemma of Truth in Large Language Models

We often attribute human characteristics to large language models (LLMs) and claim that they "know" certain things. LLMs have an internal probabilistic knowledge that represents information retained d...

111

Germans Savcisens (Savčišens) @savcisens.com · 03/05/2025

That happens way too often to me 🥲

040

Germans Savcisens (Savčišens) @savcisens.com · 14/04/2025

What's the coolest guide/source on "Complex Data Visualization"? I am looking for some inspiration to visualize graphs and high dimensional data.

130

Reposted by Germans Savcisens (Savčišens)

Cate Hamilton @cateh.bsky.social · 18/03/2025

Great read from 2019 about abandoning the use of p-values in a dichotomous way and what we can do instead. More thinking, and less relying on significance tests to decide things for us! www.nature.com/articles/d41...

nature.com

Scientists rise up against statistical significance

Valentin Amrhein, Sander Greenland, Blake McShane and more than 800 signatories call for an end to hyped claims and the dismissal of possibly crucial effects.

043

Reposted by Germans Savcisens (Savčišens)

Kosta Derpanis @csprofkgd.bsky.social · 05/03/2025

Sometimes we need a reality check 😉 @serge.belongie.com

6295

Germans Savcisens (Savčišens) @savcisens.com · 08/02/2025

Amazing time with the folks from @tint-philosophy.bsky.social at the retreat on Predictability of Human Lives. Great people & discussions, and so much to reflect on—especially around integrative modeling and how neural networks can help us get there. Plus, a relaxing sauna to top it off!

020

Germans Savcisens (Savčišens) @savcisens.com · 27/01/2025

Visiting @mpidr.bsky.social this week—super excited to see what’s happening in Demographic Studies (don’t miss my talk!). Also, I’ll be in Berlin on Feb 2, Helsinki from Feb 3-6, and Copenhagen from Feb 10-12. Let me know if you’re around and up for a coffee 🧪🔬☕️

041

Reposted by Germans Savcisens (Savčišens)

Hiroki Sayama @hirokisayama.bsky.social · 16/01/2025

For those interdisciplinary students/scholars who are having identity crisis, this is for you (from 2018): "How to survive as an interdisciplinary being" www.slideshare.net/slideshow/ho... #NetSciX2025

slideshare.net

How to survive as an interdisciplinary being

How to survive as an interdisciplinary being - Download as a PDF or view online for free

1185

Reposted by Germans Savcisens (Savčišens)

Luca Maria Aiello @lajello.bsky.social · 15/01/2025

New tool to estimate the level of participation in collective action expressed in natural language. Applied to social media, it can produce large-scale and granular estimates of behavior change wrt collective action. github.com/ariannap13/e... @nerdsitu.bsky.social @itu.dk @carlsbergfondet.dk

0167

Germans Savcisens (Savčišens) @savcisens.com · 04/01/2025

I once asked ChatGPT how it thinks my life would look like in 20 years. And "Visionary Multidimensional Social Scientist" sounds like a great job title 😅 I guess it captured my love for the "His Dark Materials" trilogy.

000

Germans Savcisens (Savčišens) @savcisens.com · 02/01/2025

Happy to write this News & Views piece on the recent audit showing LLMs picking up "us versus them" biases: www.nature.com/articles/s43... (Read-only version: rdcu.be/d5ovo) Check out the amazing (original) paper here: www.nature.com/articles/s43...

nature.com

Large language models act as if they are part of a group - Nature Computational Science

An extensive audit of large language models reveals that numerous models mirror the ‘us versus them’ thinking seen in human behavior. These social prejudices are likely captured from the biased conten...

0137

Reposted by Germans Savcisens (Savčišens)

Tiago Peixoto @tiago.skewed.de · 23/11/2024

I don't like the way many CS papers are written, even the supposedly good ones, but these tips are very generically applicable and useful. Just ignore the bit about the acronyms...

0132

Germans Savcisens (Savčišens) @savcisens.com · 20/11/2024

If you want to follow what happens with #ML, #AI, #LLM research in Denmark - here is a great Starter Pack 😋 #researchers

050

Germans Savcisens (Savčišens) @savcisens.com · 20/11/2024

#YouTube has so far come up with the best application of GenAI (in recent months): summarization of videos and the ability to chat with them -- a great way to check the contents of 60+ min talks.

010

Germans Savcisens (Savčišens) @savcisens.com · 18/11/2024

Had the pleasure of presenting how transformers can help us decode/explore complex life patterns in labour and health trajectories. If you're curious about the intersection of machine learning, social science, and health, check it out here: youtu.be/szSY7MSkLtk?...

youtu.be

life2vec: Life trajectories in high dimensional spaces

YouTube video by CUHK Computational Social Science Laboratory

072

Reposted by Germans Savcisens (Savčišens)

estebanmoro @estebanmoro.bsky.social · 11/11/2024

Network Science Institute starter pack in BlueSky! A list of members and alumni (to be updated) go.bsky.app/N3PQTdw

12112

Reposted by Germans Savcisens (Savčišens)

Brennan Klein @jkbren.bsky.social · 13/11/2024

We're hiring a postdoc in the &-Lab at Northeastern's Network Science Institute! Looking for a curious, collaborative scholar to work on computational social science questions, at the intersection of data justice + network science. northeastern.wd1.myworkdayjobs.com/careers/job/...

05040

Germans Savcisens (Savčišens) @savcisens.com · 13/11/2024

Join the talk to hear more about transformers for social science: www.soc.cuhk.edu.hk/event/nov-14...

011

Germans Savcisens (Savčišens) @savcisens.com · 19/02/2024

A simple implementation of the #life2vec model is now available at github.com/carlomarxdk/.... You can try out the workflow with dummy data, + we are planning to add more examples (including finetuning) in the near future.

github.com

220

Reposted by Germans Savcisens (Savčišens)

Nature Portfolio @natureportfolio.nature.com · 18/12/2023

A study in Nature Computational Science presents a machine learning approach that may accurately predict different aspects of human lives, including the likelihood of early mortality and personality nuances. go.nature.com/3txgJCx 🧪

This is figure 2, which shows a two-dimensional projection of the concept space (using PaCMAP).

094