Sign in

Abel Jansma

@abelaer.bsky.social
671 followers 350 following 116 posts

Compositionality in natural and artificial intelligence || Fellow @emergenceDIEP, University of Amsterdam

PostsRepliesMedia
Abel Jansma @abelaer.bsky.social · 14/09/2026
🚨 New paper! arxiv.org/abs/2609.11948 In 2021, a group of climate scientists realised that different attribution methods in climate modelling gave the same answer, and conjectured that this holds in general. It turns you can prove this with Game Theory! 🧵
120
Abel Jansma @abelaer.bsky.social · 22/06/2026
New paper alert 🚨 “A Compositional Calculus for Semantic Synergy in Language Model Embeddings” A training-free way to extract synergy from LLM embedding vectors. 🧵
100
Abel Jansma @abelaer.bsky.social · 18/03/2026
Gave a talk at the Softmax Alignment meeting—pretty nice lecture room.
011
Abel Jansma @abelaer.bsky.social · 18/03/2026
I asked somebody in the Berkeley AI safety scene if they meditate. “No,” they said, “I’m not really bliss bottlenecked at the moment”.
020
Abel Jansma @abelaer.bsky.social · 10/03/2026
Every year, our apricot is the first to blossom, which is easy to remember because “apricot” shares a linguistic root with “precocious”.
020
Abel Jansma @abelaer.bsky.social · 04/03/2026
I hope that when I'm 88 I'm also still able to embrace new technologies with such joy and curiosity: www-cs-faculty.stanford.edu/~knuth/paper...
www-cs-faculty.stanford.edu
010
Abel Jansma @abelaer.bsky.social · 02/12/2025
I found this surprising and somewhat worrying: openAI is using an AI model to align their model spec. #NeurIPS2025
010
Abel Jansma @abelaer.bsky.social · 22/10/2025
A few months ago I started discussing causal emergence with Erik Hoel. This led to a really fun collaboration, and a new approach to “engineer emergence”. Erik just published an overview of the ideas, goals, and dreams:
120
Reposted by Abel Jansma
Rebecca R Helm @rebeccarhelm.bsky.social · 09/10/2025
Many sea stars begin life as young fairy-like creature (called a brachiolaria) that float through the open ocean. Eventually, a small star forms within them (here in yellow). The fairy-like brachiolaria sinks under the star’s weight, and the star pops out! 🎥@the_story_of_a_biologist (on Insta)
7510180
Abel Jansma @abelaer.bsky.social · 08/10/2025
🚨New paper: arxiv.org/abs/2510.05786 *Shapley values beyond game theory* We show that Shapley values aren’t just about dividing payoffs--they are the right way to project down any higher-order structure. We generalise them, and Möbius inversions, in important ways: 🧵
arxiv.org
Möbius transforms and Shapley values for vector-valued functions on weighted directed acyclic multigraphs
We generalize the concept of Möbius inversion and Shapley values to directed acyclic multigraphs and weighted versions thereof. We further allow value functions (games) and thus their Möbius transform...
1103
Abel Jansma @abelaer.bsky.social · 23/09/2025
This is how Rota originally introduced the incidence algebra. Everyone since has (correctly) required the ring to be commutative. Did people in the '60s just refer to commutative rings as associative rings?
000
Abel Jansma @abelaer.bsky.social · 23/09/2025
Just to balance out the discourse: the #NeurIPS2025 review process for this paper went great. Fair reviews, mostly responsive reviewers, and a thoughtful AC that caught a possible conflict of interest. Definitely improved the paper.
010
Abel Jansma @abelaer.bsky.social · 22/09/2025
The #NeurIPS2025 version is now online: arxiv.org/pdf/2501.11447 It includes a new analysis to show that LLM semantics can be decomposed: the negativity of "horribly bad" is redundantly encoded in the two words, whereas "not bad" has synergistic semantics (i.e. negation):
030
Abel Jansma @abelaer.bsky.social · 19/09/2025
The "partial causality decomposition" was just accepted for a spotlight at #NeurIPS2025! The final version includes a decomposition of LLM semantics---the Arxiv version should be updated soon. Stay tuned!
010
Abel Jansma @abelaer.bsky.social · 05/08/2025
While I'm flattered, it's a bit weird that google's AI defers to me when you search for this:
000
Abel Jansma @abelaer.bsky.social · 06/05/2025
Next week we're organising a workshop on the role of analogies in (artificial) intelligence, with: Melanie Mitchell (@melaniemitchell.bsky.social), Martha Lewis, Jules Hedges (‪@julesh.mathstodon.xyz.ap.brid.gy‬), and Han van der Maas. Register here: www.d-iep.org/workshopanal...
d-iep.org
WORKSHOPANALOGIES | DIEP
251
Abel Jansma @abelaer.bsky.social · 08/04/2025
Don't take my word for it--take Reviewer 2's: "I found the paper extremely interesting and deep" A gentle introduction is available at abeljansma.nl/2025/01/28/m...
abeljansma.nl
Complex Systems and Quantitative Mereology
010
Abel Jansma @abelaer.bsky.social · 08/04/2025
My new approach to higher-order interactions in complex systems is now published in Physical Review Research: journals.aps.org/prresearch/a...
journals.aps.org
Mereological approach to higher-order structure in complex systems: From macro to micro with M\"obius
Relating macroscopic observables to microscopic interactions is a central challenge in the study of complex systems. While current approaches often focus on pairwise interactions, a complete understan...
121
Abel Jansma @abelaer.bsky.social · 06/02/2025
just one more index bro I swear just one more subscript and it's gonna be so clear just one more index please bro
010
Abel Jansma @abelaer.bsky.social · 04/02/2025
New blog post 🚨 A gentle dive into the mereology of complex systems, Möbius inversion, and a new way to think about higher-order interactions—no prior knowledge needed! abeljansma.nl/2025/01/28/m...
abeljansma.nl
Complex Systems and Quantitative Mereology
021
Abel Jansma @abelaer.bsky.social · 22/01/2025
New year, new Möbius inversion! This new paper is an example of my more general proposal that you should study complex systems with 'quantitative mereology' by applying the Möbius inversion theorem: arxiv.org/abs/2404.14423
arxiv.org
A Mereological Approach to Higher-Order Structure in Complex Systems: from Macro to Micro with Möbius
Relating microscopic interactions to macroscopic observables is a central challenge in the study of complex systems. Addressing this question requires understanding both pairwise and higher-order inte...
011
Abel Jansma @abelaer.bsky.social · 22/01/2025
🚨New paper! The “partial causality decomposition” When many things influence an outcome, how to distinguish individual vs collective #causality? A framework to disentangle these complex relationships into synergistic, redundant, and unique components: arxiv.org/abs/2501.11447 🧵
arxiv.org
152
Abel Jansma @abelaer.bsky.social · 06/01/2025
Very excited that this is now published: Stator is a new method to infer higher-order interactions in gene expression data, which reveals cell states and types without clustering! It's an "intersectional" approach to cellular identity: cells can have multiple identities--states are not disjoint!
031
Reposted by Abel Jansma
vi🌸 @pinkddle.bsky.social · 27/12/2024
this is a pretty interesting way of looking at collatz math.stackexchange.com/questions/26...
24410
Abel Jansma @abelaer.bsky.social · 27/12/2024
I bet those ants can get an even bigger sofa around a corner.
020
Abel Jansma @abelaer.bsky.social · 26/12/2024
There’s an analogy to be made between Wolfram’s physics project, and Borges’ Library of Babel.
110
Abel Jansma @abelaer.bsky.social · 24/12/2024
In between changing countries, jobs, and becoming a father, I didn’t manage to read much this last year. But I just finished “the Maniac” by Labatut and thought it was fantastic. On to “the world beyond the world” by @erikhoel.blogsky.venki.dev.
120
Reposted by Abel Jansma
Mike Morgan @mdmorgan.bsky.social · 13/12/2024
I am STOKED that myself and @avakhamseh.bsky.social are looking for a joint EastBIO PhD candidate across @uniofaberdeen.bsky.social and @uoe-sps.bsky.social to develop cutting-edge statistical models at the interface of single cell genomics and quantitative genetics: shorturl.at/vQo0P pls reskeet!
shorturl.at
EASTBIO: Mapping DNA variants to cell states in health and disease at University of Aberdeen on FindAPhD.com
PhD Project - EASTBIO: Mapping DNA variants to cell states in health and disease at University of Aberdeen , listed on FindAPhD.com
003
Abel Jansma @abelaer.bsky.social · 13/12/2024
Is it a common assumption that personality traits like openness and agreeableness are genetically determined? Or is this circular reasoning because their polygenic scores are derived from the UKBB in the first place?
010
Abel Jansma @abelaer.bsky.social · 09/12/2024
Hofstadter's laundry: this soap washes 2x more than expected, even when you take into account Hofstadter's laundry
010
Reposted by Abel Jansma
Frank Noe @franknoe.bsky.social · 06/12/2024
Super excited to preprint our work on developing a Biomolecular Emulator (BioEmu): Scalable emulation of protein equilibrium ensembles with generative deep learning from @msftresearch.bsky.social ch AI for Science. www.biorxiv.org/content/10.1...
21441147
Abel Jansma @abelaer.bsky.social · 03/12/2024
omg I just found out that cod(f) ≠ dom(g) tfw no gf😔
000
Abel Jansma @abelaer.bsky.social · 28/11/2024
I always found it crazy that there were just 66 years between the first human flight and the moon landing. Now in 15 months, AIs have gone from random guessing to expert level.
030
Reposted by Abel Jansma
Vincent van Gogh @vangogh.bsky.social · 27/11/2024
Swift, 1887
Swift
111116
Abel Jansma @abelaer.bsky.social · 25/11/2024
A lot of emergence research goes: 1) Here's a new measure for emergence. 2) It makes sense on 3 deterministic var's. 3) We gave 6 people ketamine and ayahuasca and asked them about their parents while hooked up to an EEG machine. 4) Emergent brain dynamics! I feel like there's a step 2.5 missing.
061
Abel Jansma @abelaer.bsky.social · 25/11/2024
Is this @ricardsole.bsky.social drawing a hopfield swarm of tumbleweeds?
120
Abel Jansma @abelaer.bsky.social · 24/11/2024
I’ve had the same experience. Is this mainly a difference in the human feedback part of RLHF? If so, then we should create a version where it’s just scientists giving feedback for this specific use case: thinking through and formalising ideas.
110
Abel Jansma @abelaer.bsky.social · 24/11/2024
I’m not affiliated to this group but have only seen and heard great things from them, so this looks like a very cool position!
120
Abel Jansma @abelaer.bsky.social · 24/11/2024
How your email finds me
030
Reposted by Abel Jansma
Kyle Cranmer @kylecranmer.bsky.social · 23/11/2024
Write math on 🦋 with UnicodeIt! For example: θ ∈ ℝⁿ or pp̅ → μ⁺μ⁻ Use website or install system-wide in Linux, macOS, or windows www.unicodeit.net (Created several years ago with @svenkreiss.bsky.social)
An screenshot of UnicodeIt website
1928662
Abel Jansma @abelaer.bsky.social · 24/11/2024
I couldn’t find a starter pack for emergence researchers, so i started one. Which bsky accounts am I missing? go.bsky.app/G8Abzar
3265
Abel Jansma @abelaer.bsky.social · 23/11/2024
I guess this is true for ML in general, since the whole field essentially evolves by gradient descent, so it doesn’t matter if some unknown number of claims are false. However, as an individual researcher, I still want to know if *my* claim is statistically valid.
020
Abel Jansma @abelaer.bsky.social · 22/11/2024
This is quite surprising. Is this the result of the starter pack feature?
000
Abel Jansma @abelaer.bsky.social · 22/11/2024
Ice skating diatoms!
183
Abel Jansma @abelaer.bsky.social · 20/11/2024
I seem to be following…myself? Is this supposed to be possible? @bsky.app
000
Abel Jansma @abelaer.bsky.social · 20/11/2024
Looking for the starter pack that contains all starter packs
000
Abel Jansma @abelaer.bsky.social · 20/11/2024
When I come across papers like this, my first thought is “so cool/quaint!”—quickly followed by “yeah I’m not gonna read this”. Latex has made me typographically xenophobic.
010
Abel Jansma @abelaer.bsky.social · 19/11/2024
New preprint! “The Fast Möbius Transform: An algebraic approach to information decomposition” Deep theory of higher-order information theory with immediate practical applications and speedups—a very fun collab with @frosas.bsky.social and Pedro Mediano arxiv.org/abs/2410.06224 1/n
arxiv.org
The Fast Möbius Transform: An algebraic approach to information decomposition
The partial information decomposition (PID) and its extension integrated information decomposition ($Φ$ID) are promising frameworks to investigate information phenomena involving multiple variables. A...
191
Abel Jansma @abelaer.bsky.social · 19/11/2024
🖐️ New here—I’m a physicist, trying to understand the role of composition, hierarchies, and higher order interactions in complex systems. I hope to create bridges between #physics, #biology, #machinelearning, #AI, #cybernetics using #mathematics: arxiv.org/abs/2404.14423 Stay tuned for more on this!
arxiv.org
A Mereological Approach to Higher-Order Structure in Complex Systems: from Macro to Micro with Möbius
Relating microscopic interactions to macroscopic observables is a central challenge in the study of complex systems. Addressing this question requires understanding both pairwise and higher-order inte...
050