Neal Caren
@haphazardsoc.bsky.social
AOL Keyword: Carolina Sociology
[Coding Snippets](https://nealcaren.github.io/notes/)
[Website](http://nealcaren.org)
[Coding Snippets](https://nealcaren.github.io/notes/)
[Website](http://nealcaren.org)
His The Awful Truth “Beat the Rich” youtu.be/akEI9ZwtKcM?...
Beat The Rich / The Sodomobile
YouTube video by Cineverse
youtu.be
November 4, 2025 at 12:09 AM
His The Awful Truth “Beat the Rich” youtu.be/akEI9ZwtKcM?...
Is it this one? arxiv.org/abs/2509.03116? You might have the wrong paper link.
Measuring Scalar Constructs in Social Science with LLMs
Many constructs that characterize language, like its complexity or emotionality, have a naturally continuous semantic structure; a public speech is not just "simple" or "complex," but exists on a cont...
arxiv.org
October 27, 2025 at 5:47 PM
Is it this one? arxiv.org/abs/2509.03116? You might have the wrong paper link.
I've tried Tesseract and EasyOCR, and neither performs well on this corpus. Abbyy Finereader probably does better than those, but I need to restart my license.
Preliminary checks on Tesseract+LLM for cleaning are very hopeful for printed works.
Preliminary checks on Tesseract+LLM for cleaning are very hopeful for printed works.
September 15, 2025 at 11:36 AM
I've tried Tesseract and EasyOCR, and neither performs well on this corpus. Abbyy Finereader probably does better than those, but I need to restart my license.
Preliminary checks on Tesseract+LLM for cleaning are very hopeful for printed works.
Preliminary checks on Tesseract+LLM for cleaning are very hopeful for printed works.
Your LLM structured data stuff was 100% the impetutus from turning this into a more systemicatic process.
September 11, 2025 at 9:02 PM
Your LLM structured data stuff was 100% the impetutus from turning this into a more systemicatic process.