Naftali Weinberger
@dagophile.bsky.social
Interested in all things causal modeling. Ongoing projects on causal analyses of discrimination and on causation in dynamical systems.
"Are we the baddies?"
November 9, 2025 at 12:03 AM
"Are we the baddies?"
I'm revising a paper, and I still haven't managed to force myself to remove a snarky comment that doesn't seem uber-professional, but which best captures the reaction I'm trying to pre-empt. What do y'all think?
November 7, 2025 at 6:23 PM
I'm revising a paper, and I still haven't managed to force myself to remove a snarky comment that doesn't seem uber-professional, but which best captures the reaction I'm trying to pre-empt. What do y'all think?
We swear that Bielefeld exists! We even had a speaker coming from there. And his train was delayed. In Bielefeld! Which totally exists!
November 6, 2025 at 5:54 PM
We swear that Bielefeld exists! We even had a speaker coming from there. And his train was delayed. In Bielefeld! Which totally exists!
"At 76.4 percent, it's the lowest turnout for a parliamentary election since 2012"
October 29, 2025 at 10:47 PM
"At 76.4 percent, it's the lowest turnout for a parliamentary election since 2012"
I have no idea what you’re talking about…
September 2, 2025 at 6:40 PM
I have no idea what you’re talking about…
Has anyone else watched Zoolander since watching Severance and picked up on the stylistic similarities?
August 17, 2025 at 2:46 AM
Has anyone else watched Zoolander since watching Severance and picked up on the stylistic similarities?
This clip is the part of the last episode that has so far generated the most discussion.
youtube.com/clip/Ugkxeuv...
youtube.com/clip/Ugkxeuv...
July 8, 2025 at 3:52 PM
This clip is the part of the last episode that has so far generated the most discussion.
youtube.com/clip/Ugkxeuv...
youtube.com/clip/Ugkxeuv...
July 5, 2025 at 2:35 AM
Jupyter Notebooks: Stop trying to make fetch happen
June 24, 2025 at 6:15 PM
Jupyter Notebooks: Stop trying to make fetch happen
Coming next week on Causal Foundations: Simpson's Paradox!
Subscribe to my YouTube channel in order to not miss episodes when they're released.
www.youtube.com/@dagophile
Subscribe to my YouTube channel in order to not miss episodes when they're released.
www.youtube.com/@dagophile
June 19, 2025 at 10:30 PM
Coming next week on Causal Foundations: Simpson's Paradox!
Subscribe to my YouTube channel in order to not miss episodes when they're released.
www.youtube.com/@dagophile
Subscribe to my YouTube channel in order to not miss episodes when they're released.
www.youtube.com/@dagophile
One of the fun things of doing the causal YouTube channel is figuring out new ways to do visualizations of causal concepts. Here's an animation for inducing d-separation by conditioning on a common cause.
youtube.com/@dagophile?s...
youtube.com/@dagophile?s...
June 15, 2025 at 11:55 PM
One of the fun things of doing the causal YouTube channel is figuring out new ways to do visualizations of causal concepts. Here's an animation for inducing d-separation by conditioning on a common cause.
youtube.com/@dagophile?s...
youtube.com/@dagophile?s...
I found Billy and Suzy! Time to put an end to their rock-throwing shenanigans!
June 11, 2025 at 1:41 PM
I found Billy and Suzy! Time to put an end to their rock-throwing shenanigans!
Well, it was good while it lasted...
Here's ChatGPTs denial of my request of an image of "a human trying to teach an alien to play pool, but where the alien is unable to understand because he lacks causal concepts"
Here's ChatGPTs denial of my request of an image of "a human trying to teach an alien to play pool, but where the alien is unable to understand because he lacks causal concepts"
June 10, 2025 at 2:54 PM
Well, it was good while it lasted...
Here's ChatGPTs denial of my request of an image of "a human trying to teach an alien to play pool, but where the alien is unable to understand because he lacks causal concepts"
Here's ChatGPTs denial of my request of an image of "a human trying to teach an alien to play pool, but where the alien is unable to understand because he lacks causal concepts"
Episode 2 of Causal Foundations will be released on Monday.
Subscribe to be notified when it is posted.
youtube.com/@dagophile?s...
Subscribe to be notified when it is posted.
youtube.com/@dagophile?s...
June 4, 2025 at 11:30 PM
Episode 2 of Causal Foundations will be released on Monday.
Subscribe to be notified when it is posted.
youtube.com/@dagophile?s...
Subscribe to be notified when it is posted.
youtube.com/@dagophile?s...
Ultimately, my aim in the talk was not to offer an account of why the causal ordering and time ordering match (again, I had 10 minutes), but to give the audience a sense of how one might approach the issues DA was raising within a causal modeling framework.
June 1, 2025 at 8:09 PM
Ultimately, my aim in the talk was not to offer an account of why the causal ordering and time ordering match (again, I had 10 minutes), but to give the audience a sense of how one might approach the issues DA was raising within a causal modeling framework.
I concluded by exogenizing depth in the bathtub case, yielding the model in the box. These are the relations we'd infer in a world where we never reached equilibrium. This is intriguing, since DA's "past hypothesis" derives the arrow of time from the universe starting in a far-from-equilibrium state
June 1, 2025 at 8:09 PM
I concluded by exogenizing depth in the bathtub case, yielding the model in the box. These are the relations we'd infer in a world where we never reached equilibrium. This is intriguing, since DA's "past hypothesis" derives the arrow of time from the universe starting in a far-from-equilibrium state
I then turned to a case in which water flows into and out of a bathtub, w/ an equilibrium condition at which inflow=outflow. The dynamic model (top) gives an intuitive ordering. The equilibrium model is counterintuitive, but captures equilibrium values of the variables after transient perturbations
June 1, 2025 at 8:09 PM
I then turned to a case in which water flows into and out of a bathtub, w/ an equilibrium condition at which inflow=outflow. The dynamic model (top) gives an intuitive ordering. The equilibrium model is counterintuitive, but captures equilibrium values of the variables after transient perturbations
I begin with an example due to Simon and Rescher, in which the wheat grown in a field depends on rainfall. Rainfall is exogenous, since it is not caused by wheat. But over a long enough timescale, agriculture does influence climate. So rainfall is only exogenous at shorter scales.
June 1, 2025 at 8:09 PM
I begin with an example due to Simon and Rescher, in which the wheat grown in a field depends on rainfall. Rainfall is exogenous, since it is not caused by wheat. But over a long enough timescale, agriculture does influence climate. So rainfall is only exogenous at shorter scales.
DA is correct that there is little in the causal modeling literature on the worldly conditions underlying the causal asymmetry. But I believe we gain insight into these conditions by looking at how causal models are relative to the spatiotemporal scale at which a system is considered.
June 1, 2025 at 8:09 PM
DA is correct that there is little in the causal modeling literature on the worldly conditions underlying the causal asymmetry. But I believe we gain insight into these conditions by looking at how causal models are relative to the spatiotemporal scale at which a system is considered.
I began by distinguishing between temporal and causal asymmetry. Within causal models C->E implies nothing about time, but only about probabilities. The causal asymmetry is that causes of causes (X) are correlated w/ their effects (E), but causes of effects (Y) are uncorrelated w/ their causes (C).
June 1, 2025 at 8:09 PM
I began by distinguishing between temporal and causal asymmetry. Within causal models C->E implies nothing about time, but only about probabilities. The causal asymmetry is that causes of causes (X) are correlated w/ their effects (E), but causes of effects (Y) are uncorrelated w/ their causes (C).
I was responding to a talk by philosopher of physics David Albert (DA), in which he expressed dissatisfaction with various approaches to reconciling the asymmetry of causation with fundamental physics. He was skeptical that causal models could help, but ended by inviting me to say more about this.
June 1, 2025 at 8:09 PM
I was responding to a talk by philosopher of physics David Albert (DA), in which he expressed dissatisfaction with various approaches to reconciling the asymmetry of causation with fundamental physics. He was skeptical that causal models could help, but ended by inviting me to say more about this.
I’ll be thinking about this for a while. It’s one of those books that’s almost surreally immersed in recent-ish history and subcultures (Berlin hipsters c. 2010), but in a strange way reminded me of Dino Buzzati’s The Tartar Steppe from the 1930s. Have any of you read this?
May 18, 2025 at 3:45 PM
I’ll be thinking about this for a while. It’s one of those books that’s almost surreally immersed in recent-ish history and subcultures (Berlin hipsters c. 2010), but in a strange way reminded me of Dino Buzzati’s The Tartar Steppe from the 1930s. Have any of you read this?
Ok frequentists, let’s call a truce. This has gone too far.
May 15, 2025 at 1:50 AM
Ok frequentists, let’s call a truce. This has gone too far.
This might be recency bias, but I think this is the best paper I've written. It showcases how causal models can unite engineering, dynamic systems theory and biology, while pointing to the work to be done in learning and applying causal concepts.
philsci-archive.pitt.edu/25288/
philsci-archive.pitt.edu/25288/
May 13, 2025 at 2:46 PM
This might be recency bias, but I think this is the best paper I've written. It showcases how causal models can unite engineering, dynamic systems theory and biology, while pointing to the work to be done in learning and applying causal concepts.
philsci-archive.pitt.edu/25288/
philsci-archive.pitt.edu/25288/