Rex "garbage in" Douglass
@rexdouglass.bsky.social
Applied Scientist in Industry. Previously UCSD. Princeton PhD.
Follow me for recreational methods trash talk.
www.rexdouglass.com
Follow me for recreational methods trash talk.
www.rexdouglass.com
Pinned
Help! ─ 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 open to work ─ Remote/Austin → www.rexdouglass.com
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
🟢 𝗢𝗽𝗲𝗻 𝘁𝗼 𝗪𝗼𝗿𝗸 — 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 (𝗥𝗲𝗺𝗼𝘁𝗲 / 𝗔𝘂𝘀𝘁𝗶𝗻) → rexdouglass.com
𝗛𝗼𝘄 𝗱𝗼 𝘆𝗼𝘂 𝗳𝗶𝗻𝗱 𝗮 𝟭‑𝗶𝗻‑𝟭,𝟬𝟬𝟬,𝟬𝟬𝟬 𝗲𝘃𝗲𝗻𝘁 𝗶𝗻 𝟭𝟬,𝟬𝟬𝟬+ 𝗵𝗼𝘂𝗿𝘀 𝗼𝗳 𝘃𝗶𝗱𝗲𝗼?
You 𝘀𝘁𝗿𝗮𝘁𝗶𝗳𝘆 𝘁𝗵𝗲 𝗵𝗮𝘆𝘀𝘁𝗮𝗰𝗸.
#ComputerVision #ActiveLearning #DatasetCuration #MLOps #VideoAnalytics #Manufacturing #AppliedScience
𝗛𝗼𝘄 𝗱𝗼 𝘆𝗼𝘂 𝗳𝗶𝗻𝗱 𝗮 𝟭‑𝗶𝗻‑𝟭,𝟬𝟬𝟬,𝟬𝟬𝟬 𝗲𝘃𝗲𝗻𝘁 𝗶𝗻 𝟭𝟬,𝟬𝟬𝟬+ 𝗵𝗼𝘂𝗿𝘀 𝗼𝗳 𝘃𝗶𝗱𝗲𝗼?
You 𝘀𝘁𝗿𝗮𝘁𝗶𝗳𝘆 𝘁𝗵𝗲 𝗵𝗮𝘆𝘀𝘁𝗮𝗰𝗸.
#ComputerVision #ActiveLearning #DatasetCuration #MLOps #VideoAnalytics #Manufacturing #AppliedScience
September 29, 2025 at 4:10 PM
🟢 𝗢𝗽𝗲𝗻 𝘁𝗼 𝗪𝗼𝗿𝗸 — 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 (𝗥𝗲𝗺𝗼𝘁𝗲 / 𝗔𝘂𝘀𝘁𝗶𝗻) → rexdouglass.com
𝗛𝗼𝘄 𝗱𝗼 𝘆𝗼𝘂 𝗳𝗶𝗻𝗱 𝗮 𝟭‑𝗶𝗻‑𝟭,𝟬𝟬𝟬,𝟬𝟬𝟬 𝗲𝘃𝗲𝗻𝘁 𝗶𝗻 𝟭𝟬,𝟬𝟬𝟬+ 𝗵𝗼𝘂𝗿𝘀 𝗼𝗳 𝘃𝗶𝗱𝗲𝗼?
You 𝘀𝘁𝗿𝗮𝘁𝗶𝗳𝘆 𝘁𝗵𝗲 𝗵𝗮𝘆𝘀𝘁𝗮𝗰𝗸.
#ComputerVision #ActiveLearning #DatasetCuration #MLOps #VideoAnalytics #Manufacturing #AppliedScience
𝗛𝗼𝘄 𝗱𝗼 𝘆𝗼𝘂 𝗳𝗶𝗻𝗱 𝗮 𝟭‑𝗶𝗻‑𝟭,𝟬𝟬𝟬,𝟬𝟬𝟬 𝗲𝘃𝗲𝗻𝘁 𝗶𝗻 𝟭𝟬,𝟬𝟬𝟬+ 𝗵𝗼𝘂𝗿𝘀 𝗼𝗳 𝘃𝗶𝗱𝗲𝗼?
You 𝘀𝘁𝗿𝗮𝘁𝗶𝗳𝘆 𝘁𝗵𝗲 𝗵𝗮𝘆𝘀𝘁𝗮𝗰𝗸.
#ComputerVision #ActiveLearning #DatasetCuration #MLOps #VideoAnalytics #Manufacturing #AppliedScience
Reposted by Rex "garbage in" Douglass
🟢 𝗢𝗽𝗲𝗻 𝘁𝗼 𝗪𝗼𝗿𝗸 — 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 · Remote / Austin
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
September 26, 2025 at 5:00 PM
🟢 𝗢𝗽𝗲𝗻 𝘁𝗼 𝗪𝗼𝗿𝗸 — 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 · Remote / Austin
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
🟢 𝗢𝗽𝗲𝗻 𝘁𝗼 𝗪𝗼𝗿𝗸 — 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 · Remote / Austin
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
September 26, 2025 at 5:00 PM
🟢 𝗢𝗽𝗲𝗻 𝘁𝗼 𝗪𝗼𝗿𝗸 — 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 · Remote / Austin
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
🎞️ 𝗦𝗹𝗶𝗱𝗲𝘀 tinyurl.com/yxr7k5f8
🚧 𝗣𝗿𝗼𝗷𝗲𝗰𝘁
Completely unsupervised segmentation + labeling of parts, tools, and people in manufacturing. I demo it on a random “How It’s Made” fire-extinguisher video.
🧰 𝗦𝘁𝗮𝗰𝗸
DINO · SAM-2 · Gemini · YOLO
Reposted by Rex "garbage in" Douglass
Help! ─ 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 open to work ─ Remote/Austin → www.rexdouglass.com
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
September 24, 2025 at 4:28 PM
Help! ─ 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 open to work ─ Remote/Austin → www.rexdouglass.com
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
Help! ─ 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 open to work ─ Remote/Austin → www.rexdouglass.com
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
September 24, 2025 at 4:28 PM
Help! ─ 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 open to work ─ Remote/Austin → www.rexdouglass.com
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
With new tools, I've been cooking:
▸ Machine-vision pipelines — RIOS Intelligent Machines
▸ Information-extraction pipelines — Microsoft
▸ Interactive SMS surveys — Pantheon Insights
Some ML Engineer at YouTube must handle just kids home for the holidays unsubscribing their parents from all the right wing channels.
September 15, 2025 at 10:31 PM
Some ML Engineer at YouTube must handle just kids home for the holidays unsubscribing their parents from all the right wing channels.
90% of machine learning is data cleaning.
September 13, 2025 at 8:19 PM
90% of machine learning is data cleaning.
Who turned America's military against Americans?
I'm tracking 313+ instances of support/opposition to the use of armed forces in domestic law enforcement in a new dataset:
"Public Positions on Militarization of Domestic Law Enforcement in the U.S."
docs.google.com/spreadsheets...
I'm tracking 313+ instances of support/opposition to the use of armed forces in domestic law enforcement in a new dataset:
"Public Positions on Militarization of Domestic Law Enforcement in the U.S."
docs.google.com/spreadsheets...
Public Positions on Militarization of Domestic Law Enforcement in the U.S.
docs.google.com
September 5, 2025 at 11:43 PM
Who turned America's military against Americans?
I'm tracking 313+ instances of support/opposition to the use of armed forces in domestic law enforcement in a new dataset:
"Public Positions on Militarization of Domestic Law Enforcement in the U.S."
docs.google.com/spreadsheets...
I'm tracking 313+ instances of support/opposition to the use of armed forces in domestic law enforcement in a new dataset:
"Public Positions on Militarization of Domestic Law Enforcement in the U.S."
docs.google.com/spreadsheets...
Public Positions on Militarization of Domestic Law Enforcement in the U.S.
t.co/P5HmsHF1fA
t.co/P5HmsHF1fA
August 28, 2025 at 8:13 AM
Public Positions on Militarization of Domestic Law Enforcement in the U.S.
t.co/P5HmsHF1fA
t.co/P5HmsHF1fA
Just the direct material costs for each additional year of war to Ukraine are about $111.7B or just over half their entire GDP burned per year
🚩$50B (25% of prewar GDP) to wartime defense spending over peace time levels
🚩$61.7B (30.8%) in direct destruction of things/sectors of the economy by Russia
🚩$50B (25% of prewar GDP) to wartime defense spending over peace time levels
🚩$61.7B (30.8%) in direct destruction of things/sectors of the economy by Russia
August 14, 2025 at 5:25 PM
Just the direct material costs for each additional year of war to Ukraine are about $111.7B or just over half their entire GDP burned per year
🚩$50B (25% of prewar GDP) to wartime defense spending over peace time levels
🚩$61.7B (30.8%) in direct destruction of things/sectors of the economy by Russia
🚩$50B (25% of prewar GDP) to wartime defense spending over peace time levels
🚩$61.7B (30.8%) in direct destruction of things/sectors of the economy by Russia
This is absolutely nuts:
🚩30% of Ukraine's population is either internally displaced, a refugee outside of the country, or under Russian occupation.
🚩About 14% of the population's homes have been destroyed. Each additional year of war destroys about another 3%.
🚩30% of Ukraine's population is either internally displaced, a refugee outside of the country, or under Russian occupation.
🚩About 14% of the population's homes have been destroyed. Each additional year of war destroys about another 3%.
August 14, 2025 at 5:37 AM
This is absolutely nuts:
🚩30% of Ukraine's population is either internally displaced, a refugee outside of the country, or under Russian occupation.
🚩About 14% of the population's homes have been destroyed. Each additional year of war destroys about another 3%.
🚩30% of Ukraine's population is either internally displaced, a refugee outside of the country, or under Russian occupation.
🚩About 14% of the population's homes have been destroyed. Each additional year of war destroys about another 3%.
Each additional year of war in Ukraine implies an additional:
7,953 Civilians Directly Killed
12,822 Civilians Directly Injured
7,953 Civilians Directly Killed
12,822 Civilians Directly Injured
August 13, 2025 at 6:54 PM
Each additional year of war in Ukraine implies an additional:
7,953 Civilians Directly Killed
12,822 Civilians Directly Injured
7,953 Civilians Directly Killed
12,822 Civilians Directly Injured
The bargaining model of war only has a few parameters. I'm often annoyed that the cost of fighting receives less serious measurement than military weapons/strategy. Then I remembered I pay $700 a month for LLMs, so here's the first in a series on Ukraine's costs from fighting.
August 13, 2025 at 7:20 AM
The bargaining model of war only has a few parameters. I'm often annoyed that the cost of fighting receives less serious measurement than military weapons/strategy. Then I remembered I pay $700 a month for LLMs, so here's the first in a series on Ukraine's costs from fighting.
Recently had a debate about two-way fixed effects and how it pretends to magically solve causal inference problems by just changing to a different DV than the one we actually care about. Here's that explained visually.
Here's raw annual city temperatures:
Here's raw annual city temperatures:
April 13, 2025 at 3:18 PM
Recently had a debate about two-way fixed effects and how it pretends to magically solve causal inference problems by just changing to a different DV than the one we actually care about. Here's that explained visually.
Here's raw annual city temperatures:
Here's raw annual city temperatures:
hahahahahaha
April 3, 2025 at 7:25 PM
hahahahahaha
Reposted by Rex "garbage in" Douglass
We are delighted to announce Reticulate 1.41!
You can now simply declare your dependencies using `py_require()`, and Reticulate will handle the rest. This seamless experience is powered by uv, an extremely fast #Python package manager written in Rust.
Learn more: posit.co/blog/reticul...
#RStats
You can now simply declare your dependencies using `py_require()`, and Reticulate will handle the rest. This seamless experience is powered by uv, an extremely fast #Python package manager written in Rust.
Learn more: posit.co/blog/reticul...
#RStats
March 3, 2025 at 3:05 PM
We are delighted to announce Reticulate 1.41!
You can now simply declare your dependencies using `py_require()`, and Reticulate will handle the rest. This seamless experience is powered by uv, an extremely fast #Python package manager written in Rust.
Learn more: posit.co/blog/reticul...
#RStats
You can now simply declare your dependencies using `py_require()`, and Reticulate will handle the rest. This seamless experience is powered by uv, an extremely fast #Python package manager written in Rust.
Learn more: posit.co/blog/reticul...
#RStats
Reposted by Rex "garbage in" Douglass
Big Shout Out to Andrew Heiss at Georgia State:
an API for grabbing the USAID data: foreignassistance-data.andrewheiss.com
USAID greenbook: foreignassistance.andrewheiss.com/greenbook.html
an API for grabbing the USAID data: foreignassistance-data.andrewheiss.com
USAID greenbook: foreignassistance.andrewheiss.com/greenbook.html
Datasette: 2025-02-03_foreign-assistance
foreignassistance-data.andrewheiss.com
February 6, 2025 at 9:57 AM
Big Shout Out to Andrew Heiss at Georgia State:
an API for grabbing the USAID data: foreignassistance-data.andrewheiss.com
USAID greenbook: foreignassistance.andrewheiss.com/greenbook.html
an API for grabbing the USAID data: foreignassistance-data.andrewheiss.com
USAID greenbook: foreignassistance.andrewheiss.com/greenbook.html
There's been some confusion about whether the new DeepSeek-R1 open source model includes a political propaganda/censorship layer baked in.
It does. Here's what it does in its own words and the experiments to reproduce.
It does. Here's what it does in its own words and the experiments to reproduce.
January 26, 2025 at 3:23 AM
There's been some confusion about whether the new DeepSeek-R1 open source model includes a political propaganda/censorship layer baked in.
It does. Here's what it does in its own words and the experiments to reproduce.
It does. Here's what it does in its own words and the experiments to reproduce.
Reposted by Rex "garbage in" Douglass
Yes, I talk about this issue in my blog post:
www.robertkubinec.com/post/fixed_e...
Stata has similar behavior. It's a very big deal with two-way FEs.
www.robertkubinec.com/post/fixed_e...
Stata has similar behavior. It's a very big deal with two-way FEs.
What Panel Data Is Really All About – Robert Kubinec
In this post I talk about my recent publication with Jonathan Kropko about panel data. We de-mistify panel data, expose some serious weaknesses in common models like two-way fixed effects (2-way FE), ...
www.robertkubinec.com
January 3, 2025 at 3:34 PM
Yes, I talk about this issue in my blog post:
www.robertkubinec.com/post/fixed_e...
Stata has similar behavior. It's a very big deal with two-way FEs.
www.robertkubinec.com/post/fixed_e...
Stata has similar behavior. It's a very big deal with two-way FEs.
Reposted by Rex "garbage in" Douglass
Only 6% of papers using SOEP data share their reproduction workflows. We need #openscience now @janmarcus.de onlinelibrary.wiley.com/doi/10.1111/...
Replication code availability over time and across fields: Evidence from the German Socio‐Economic Panel
Providing replication code is an inexpensive way to facilitate reproducibility. However, little is known about the extent of replication code provision. Therefore, we examine the availability of repl....
onlinelibrary.wiley.com
December 17, 2024 at 6:50 AM
Only 6% of papers using SOEP data share their reproduction workflows. We need #openscience now @janmarcus.de onlinelibrary.wiley.com/doi/10.1111/...
Reposted by Rex "garbage in" Douglass
UpSet won the #ieeevis InfoVis 10-year test of time award 🎉. Thanks to @ngehlenborg.bsky.social @henstr.bsky.social Romain Vuillemot, and Hanspeter Pfister for being an awesome team to work with on this. I wrote up my reflections on what made UpSet successful: vdl.sci.utah.edu/blog/2024/10...
Reflections on UpSet
This blog post was triggered by UpSet winning the 10-year Test of Time Award at IEEE VIS. In this post, I reflect on how UpSet came about, and what made it successful.
vdl.sci.utah.edu
October 18, 2024 at 2:54 PM
UpSet won the #ieeevis InfoVis 10-year test of time award 🎉. Thanks to @ngehlenborg.bsky.social @henstr.bsky.social Romain Vuillemot, and Hanspeter Pfister for being an awesome team to work with on this. I wrote up my reflections on what made UpSet successful: vdl.sci.utah.edu/blog/2024/10...
Reposted by Rex "garbage in" Douglass
And make sure to check out our demo application: huggingface.co/spaces/ciass...
Protest Segments - a Hugging Face Space by ciass
Discover amazing ML apps made by the community
huggingface.co
December 9, 2024 at 2:05 PM
And make sure to check out our demo application: huggingface.co/spaces/ciass...
Reposted by Rex "garbage in" Douglass
Finally out in @polanalysis.bsky.social (w/ @stefan-scholz.bsky.social, @zacharyst.bsky.social, @keremoglu.bsky.social and Bastian Goldlücke): "Improving Computer Vision Interpretability: Transparent Two-Level Classification for Complex Scenes" Available #OpenAccess at doi.org/10.1017/pan....
Improving Computer Vision Interpretability: Transparent Two-Level Classification for Complex Scenes | Political Analysis | Cambridge Core
Improving Computer Vision Interpretability: Transparent Two-Level Classification for Complex Scenes
doi.org
December 9, 2024 at 10:26 AM
Finally out in @polanalysis.bsky.social (w/ @stefan-scholz.bsky.social, @zacharyst.bsky.social, @keremoglu.bsky.social and Bastian Goldlücke): "Improving Computer Vision Interpretability: Transparent Two-Level Classification for Complex Scenes" Available #OpenAccess at doi.org/10.1017/pan....
Reposted by Rex "garbage in" Douglass
Ah, I found what I was looking for! From Imai et al.'s "Unpacking the Black Box of Causality" (2011). This is coming from the angle of two experiments in which you identify A -> B and B -> C and why you cannot infer the average causal mediation effect from that.
December 6, 2024 at 3:24 PM
Ah, I found what I was looking for! From Imai et al.'s "Unpacking the Black Box of Causality" (2011). This is coming from the angle of two experiments in which you identify A -> B and B -> C and why you cannot infer the average causal mediation effect from that.