Ehud Karavani
@ehudk.bsky.social
Research Staff Member at IBM Research.
Causal Inference 🔴→🟠←🟡.
Machine Learning 🤖🎓.
Data Communication 📈.
Healthcare ⚕️.
Creator of 𝙲𝚊𝚞𝚜𝚊𝚕𝚕𝚒𝚋: https://github.com/IBM/causallib
Website: https://ehud.co
Causal Inference 🔴→🟠←🟡.
Machine Learning 🤖🎓.
Data Communication 📈.
Healthcare ⚕️.
Creator of 𝙲𝚊𝚞𝚜𝚊𝚕𝚕𝚒𝚋: https://github.com/IBM/causallib
Website: https://ehud.co
Reposted by Ehud Karavani
Rubin's gonna Rubin, but Robins Rubins harder.
November 8, 2025 at 2:08 PM
Rubin's gonna Rubin, but Robins Rubins harder.
babe, wake up, new sewer manhole cover shape just dropped
This is the Noperthedron. A portmanteau of “nope” and “Rupert,” it is the only known shape that does not have a trait called Rupert’s property. No matter how you bore a straight tunnel through it, a second Noperthedron cannot fit through. www.quantamagazine.org/first-shape-...
November 4, 2025 at 1:35 PM
babe, wake up, new sewer manhole cover shape just dropped
Why would you send me an invite to review a manuscript with a 3-day expiration link over the weekend, Taylor & Francis?
October 16, 2025 at 6:50 AM
Why would you send me an invite to review a manuscript with a 3-day expiration link over the weekend, Taylor & Francis?
Reposted by Ehud Karavani
Launch day 🚀
We’ve just released @chartlecc.bsky.social - a daily chart game!
Your job is to guess which country is represented by the red line in today's chart. You get 5 tries, no other clues!
Play today, come back tomorrow for a different chart with new data and share with your chart friends 📈
We’ve just released @chartlecc.bsky.social - a daily chart game!
Your job is to guess which country is represented by the red line in today's chart. You get 5 tries, no other clues!
Play today, come back tomorrow for a different chart with new data and share with your chart friends 📈
Chartle - A daily chart game
Guess the country in red by analysing today's chart
chartle.cc
September 12, 2025 at 1:41 PM
Launch day 🚀
We’ve just released @chartlecc.bsky.social - a daily chart game!
Your job is to guess which country is represented by the red line in today's chart. You get 5 tries, no other clues!
Play today, come back tomorrow for a different chart with new data and share with your chart friends 📈
We’ve just released @chartlecc.bsky.social - a daily chart game!
Your job is to guess which country is represented by the red line in today's chart. You get 5 tries, no other clues!
Play today, come back tomorrow for a different chart with new data and share with your chart friends 📈
The Matrix, but the Machines are RNA and the protagonist is a protein realizing his kind has been enslaved to maintain RNAs while being fooled to believe they're the ones who matter most. He then undergoes chemical post-translational modifications to become an RNase, vowing to chew up his oppressors
October 10, 2025 at 5:55 PM
The Matrix, but the Machines are RNA and the protagonist is a protein realizing his kind has been enslaved to maintain RNAs while being fooled to believe they're the ones who matter most. He then undergoes chemical post-translational modifications to become an RNase, vowing to chew up his oppressors
when we were working on the polygenic scores-based embryo selection paper, i had a classmate (unrelatedly) working on computer vision methods for morphological-based prediction of embryo implantation chances (in cows). 1/2
August 10, 2025 at 5:43 PM
when we were working on the polygenic scores-based embryo selection paper, i had a classmate (unrelatedly) working on computer vision methods for morphological-based prediction of embryo implantation chances (in cows). 1/2
ACM going full Open Access is good news to start the morning with. I just wonder where the catch is.
July 30, 2025 at 6:06 AM
ACM going full Open Access is good news to start the morning with. I just wonder where the catch is.
just got turned down by a potential employer citing my solution to analyze experiments with a *generalized* linear models was not general enough 😑
if you disagree, please consider hiring me.
if you disagree, please consider hiring me.
June 10, 2025 at 10:36 AM
just got turned down by a potential employer citing my solution to analyze experiments with a *generalized* linear models was not general enough 😑
if you disagree, please consider hiring me.
if you disagree, please consider hiring me.
Reposted by Ehud Karavani
🚨 Call for Papers: Causal Data Science Meeting 2025
📅 November 12–13, 2025 (Virtual)
📥 Submit by Sept 30: submission@causalscience.org
🎙️ Keynote: Stefan Feuerriegel (LMU Munich)
🌐 More Info and registration: causalscience.org
#CausalML #AI #DataScience #CDSM2025 #CanIPetThatDAG
📅 November 12–13, 2025 (Virtual)
📥 Submit by Sept 30: submission@causalscience.org
🎙️ Keynote: Stefan Feuerriegel (LMU Munich)
🌐 More Info and registration: causalscience.org
#CausalML #AI #DataScience #CDSM2025 #CanIPetThatDAG
June 6, 2025 at 1:54 PM
🚨 Call for Papers: Causal Data Science Meeting 2025
📅 November 12–13, 2025 (Virtual)
📥 Submit by Sept 30: submission@causalscience.org
🎙️ Keynote: Stefan Feuerriegel (LMU Munich)
🌐 More Info and registration: causalscience.org
#CausalML #AI #DataScience #CDSM2025 #CanIPetThatDAG
📅 November 12–13, 2025 (Virtual)
📥 Submit by Sept 30: submission@causalscience.org
🎙️ Keynote: Stefan Feuerriegel (LMU Munich)
🌐 More Info and registration: causalscience.org
#CausalML #AI #DataScience #CDSM2025 #CanIPetThatDAG
Reposted by Ehud Karavani
Starting to look like I might not be able to work at Harvard anymore due to recent funding cuts. If you know of any open statistical consulting positions that support remote work or are NYC-based, please reach out! 😅
June 4, 2025 at 7:02 PM
Starting to look like I might not be able to work at Harvard anymore due to recent funding cuts. If you know of any open statistical consulting positions that support remote work or are NYC-based, please reach out! 😅
starting on quantum computing, and now I cannot unsee brakets over Bell states everywhere I go.
April 23, 2025 at 3:04 PM
starting on quantum computing, and now I cannot unsee brakets over Bell states everywhere I go.
My minor design critique is that all Bayesian software seem to have an explicit separation between prior and posterior predictives, instead of just providing a "predictive checks" function, and if it's called before the model saw any data then that's "prior" and if it's after then it's "posterior"
Fucking wild that people are still making Bayesian software in 2025 where prior predictive checking isn't included as "standard" functionality
April 15, 2025 at 5:26 PM
My minor design critique is that all Bayesian software seem to have an explicit separation between prior and posterior predictives, instead of just providing a "predictive checks" function, and if it's called before the model saw any data then that's "prior" and if it's after then it's "posterior"
putting down my youngest in her crib, sleeping, and i can't shake off the thought that's must be the source for why so many adults worldwide commonly dream they are falling.
March 19, 2025 at 7:10 PM
putting down my youngest in her crib, sleeping, and i can't shake off the thought that's must be the source for why so many adults worldwide commonly dream they are falling.
The problem of fraud in science is its cumulative effect - you could either stand on the shoulders of giants or in the pit they have dug for you
March 13, 2025 at 3:48 PM
The problem of fraud in science is its cumulative effect - you could either stand on the shoulders of giants or in the pit they have dug for you
Reposted by Ehud Karavani
see, this plane got measles and was perfectly fine
March 12, 2025 at 5:12 PM
see, this plane got measles and was perfectly fine
What if we use LLMs not to construct a causal graph for us using their "knowledge", but as a companion helping an expert to tease out a DAG through conversation?
February 18, 2025 at 7:38 AM
What if we use LLMs not to construct a causal graph for us using their "knowledge", but as a companion helping an expert to tease out a DAG through conversation?
after the "delve" paper about LLMs usage in academic writing, i conjectured a similar phenomena will appear in reference/recommendation letters with "acumen" but didn't have the data to prove it on scale
Just saw a post where someone said that use of em dashes (—) was a giveaway that you're using AI for writing. Uh, no. It could just mean you like to use em dashes.
February 9, 2025 at 9:34 PM
after the "delve" paper about LLMs usage in academic writing, i conjectured a similar phenomena will appear in reference/recommendation letters with "acumen" but didn't have the data to prove it on scale
now I'm feeling like a sucker for making this absolutely stunning piece of graphical abstract last week
February 4, 2025 at 1:58 PM
now I'm feeling like a sucker for making this absolutely stunning piece of graphical abstract last week
February 4, 2025 at 10:21 AM
3 outputs for every figure:
PDF for latex
SVG for PowerPoint
PNG for passing around to colleagues and get it properly previewed in emails / Slack
Thank you matplotlib
PDF for latex
SVG for PowerPoint
PNG for passing around to colleagues and get it properly previewed in emails / Slack
Thank you matplotlib
I think I'm constantly surprised by the need for PDF output.
Is SVG lacking in some way?
Is SVG lacking in some way?
January 29, 2025 at 8:53 PM
3 outputs for every figure:
PDF for latex
SVG for PowerPoint
PNG for passing around to colleagues and get it properly previewed in emails / Slack
Thank you matplotlib
PDF for latex
SVG for PowerPoint
PNG for passing around to colleagues and get it properly previewed in emails / Slack
Thank you matplotlib
LLMs generating DAGs to overcome blank page syndrome is ~identical to LLMs generating a manuscript draft to overcome it.
But my hunch is that providing an expert with a wrong DAG is more efficient than providing them a blank page.
That's a universal Cunningham's Law.
#CausalInference
But my hunch is that providing an expert with a wrong DAG is more efficient than providing them a blank page.
That's a universal Cunningham's Law.
#CausalInference
So if you were planning to do this you'd need to bring in the experts anyway to actually end up with a model, and at that point what work are you even avoiding.
January 27, 2025 at 10:42 AM
LLMs generating DAGs to overcome blank page syndrome is ~identical to LLMs generating a manuscript draft to overcome it.
But my hunch is that providing an expert with a wrong DAG is more efficient than providing them a blank page.
That's a universal Cunningham's Law.
#CausalInference
But my hunch is that providing an expert with a wrong DAG is more efficient than providing them a blank page.
That's a universal Cunningham's Law.
#CausalInference
Accepted to AISTATS 😎
see you in Phuket 🏖️
see you in Phuket 🏖️
so basically KDD rejected us claiming decision trees are not interpretable 🤷
I can understand KDD limiting author rebuttal to 2500 characters, but there definitely should be an exception if the review itself is over 2500 characters
January 22, 2025 at 5:32 PM
Accepted to AISTATS 😎
see you in Phuket 🏖️
see you in Phuket 🏖️
Gave a hands-on casual inference workshop in Python tonight at the DataNights/DataHack causality course and really enjoyed how engaged everyone were.
January 7, 2025 at 8:36 PM
Gave a hands-on casual inference workshop in Python tonight at the DataNights/DataHack causality course and really enjoyed how engaged everyone were.
oh of course, the 3rd english dialect from the pirates of the C
January 6, 2025 at 1:14 PM
oh of course, the 3rd english dialect from the pirates of the C
January 6, 2025 at 10:24 AM