Zachary K Stine
@zacharykstine.bsky.social
Asst prof of computer science interested in computational methods for the study of language and culture.
Pinned
The Differential Meaning of Models: A Framework for Analyzing the Structural Consequences of Semantic Modeling Decisions
The proliferation of methods for modeling of human meaning-making constitutes a powerful class of instruments for the analysis of complex semiotic systems. However, the field lacks a general theoretic...
arxiv.org
New paper out titled, The differential meaning of models: a framework for analyzing the structural consequences of semantic modeling decisions. Co-authored with Jim Deitrick. We try to say some things about semantic models in simple, precise terms. Read it here: arxiv.org/abs/2509.00248
Reposted by Zachary K Stine
Pretty much no one can make their ideas clear to others on the 1st attempt. The two main reactions are "let's painstakingly clarify this with some back and forth", and "doesn't matter as long as the various interpretations are themselves interesting", leading to the 2 main branches of philosophy.
November 10, 2025 at 8:14 PM
Pretty much no one can make their ideas clear to others on the 1st attempt. The two main reactions are "let's painstakingly clarify this with some back and forth", and "doesn't matter as long as the various interpretations are themselves interesting", leading to the 2 main branches of philosophy.
A distributional semantic comparison of articles in Grokipedia vs Wikipedia could be interesting…
October 29, 2025 at 8:38 PM
A distributional semantic comparison of articles in Grokipedia vs Wikipedia could be interesting…
Reposted by Zachary K Stine
"Because science rejects claims to truth based on authority and depends on the criticism of established ideas, it is the enemy of autocracy. Because scientific knowledge is tentative and provisional, it is the enemy of dogma. "
October 25, 2025 at 9:41 PM
"Because science rejects claims to truth based on authority and depends on the criticism of established ideas, it is the enemy of autocracy. Because scientific knowledge is tentative and provisional, it is the enemy of dogma. "
Reposted by Zachary K Stine
Today's offering from the #NaturalPhilosophy Symposium: Kevin Zollman @kevinzollman.com on Refutation and Models of Social Organization. Commentary by Henry Farrell @himself.bsky.social.
www.youtube.com/watch?v=ybOr...
www.youtube.com/watch?v=ybOr...
October 24, 2025 at 6:16 PM
Today's offering from the #NaturalPhilosophy Symposium: Kevin Zollman @kevinzollman.com on Refutation and Models of Social Organization. Commentary by Henry Farrell @himself.bsky.social.
www.youtube.com/watch?v=ybOr...
www.youtube.com/watch?v=ybOr...
Reposted by Zachary K Stine
New paper on formats of representation in LLMs. I defend pluralism both about the vehicles of representation in ANNs (e.g. neurons, polytopes, embeddings) and about the formats of representation (e.g. nominal, analogue, structural). Hope it’s useful to someone. philpapers.org/rec/MALFOR-2
Fintan Mallory, Formats of Representation in Large Language Models - PhilPapers
This paper argues for a pluralist approach to representation in large language models. There are two parts to this pluralism, the first is that we should recognise more than one vehicle ...
philpapers.org
October 19, 2025 at 3:20 PM
New paper on formats of representation in LLMs. I defend pluralism both about the vehicles of representation in ANNs (e.g. neurons, polytopes, embeddings) and about the formats of representation (e.g. nominal, analogue, structural). Hope it’s useful to someone. philpapers.org/rec/MALFOR-2
As we put it here, “the shape is the meaning”: arxiv.org/abs/2509.00248
October 16, 2025 at 2:07 AM
As we put it here, “the shape is the meaning”: arxiv.org/abs/2509.00248
Reposted by Zachary K Stine
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
October 8, 2025 at 7:27 PM
What problem is explainability/interpretability research trying to solve in ML, and do you have a favorite paper articulating what that problem is?
I’ve been preparing a presentation on this paper and trying to more concisely get the main point across. I’d say it comes down to this:
To make the interpretive lens of a particular modeling decision visible, you have to contrast it against a population of alternative decisions.
1/5
To make the interpretive lens of a particular modeling decision visible, you have to contrast it against a population of alternative decisions.
1/5
New paper out titled, The differential meaning of models: a framework for analyzing the structural consequences of semantic modeling decisions. Co-authored with Jim Deitrick. We try to say some things about semantic models in simple, precise terms. Read it here: arxiv.org/abs/2509.00248
The Differential Meaning of Models: A Framework for Analyzing the Structural Consequences of Semantic Modeling Decisions
The proliferation of methods for modeling of human meaning-making constitutes a powerful class of instruments for the analysis of complex semiotic systems. However, the field lacks a general theoretic...
arxiv.org
October 8, 2025 at 6:38 PM
I’ve been preparing a presentation on this paper and trying to more concisely get the main point across. I’d say it comes down to this:
To make the interpretive lens of a particular modeling decision visible, you have to contrast it against a population of alternative decisions.
1/5
To make the interpretive lens of a particular modeling decision visible, you have to contrast it against a population of alternative decisions.
1/5
Reposted by Zachary K Stine
if attention mechanisms in transformers create graphlike transformations across text then it is actually an incredible pun that groups of sentences are called "para-graphs"
October 3, 2025 at 3:32 PM
if attention mechanisms in transformers create graphlike transformations across text then it is actually an incredible pun that groups of sentences are called "para-graphs"
Reposted by Zachary K Stine
"Helen de Cruz (1978–2025): an academic and personal tribute" *Religious Studies* Published online 2025:1-4.
doi.org/10.1017/S003...
@helendecruz.net
doi.org/10.1017/S003...
@helendecruz.net
Helen de Cruz (1978–2025): an academic and personal tribute | Religious Studies | Cambridge Core
Helen de Cruz (1978–2025): an academic and personal tribute
doi.org
September 30, 2025 at 7:37 PM
"Helen de Cruz (1978–2025): an academic and personal tribute" *Religious Studies* Published online 2025:1-4.
doi.org/10.1017/S003...
@helendecruz.net
doi.org/10.1017/S003...
@helendecruz.net
Reposted by Zachary K Stine
Extremely good stuff from Leif here
i was on Disintegrator podcast, a really awesome conversation
podcasts.apple.com/us/podcast/3...
podcasts.apple.com/us/podcast/3...
September 24, 2025 at 4:48 PM
Extremely good stuff from Leif here
Reposted by Zachary K Stine
I really enjoyed talking to @nsaphra.bsky.social about her thoughts on what much language model interpretability research misses. My latest in @quantamagazine.bsky.social:
To Understand AI, Watch How It Evolves | Quanta Magazine
Naomi Saphra thinks that most research into language models focuses too much on the finished product. She’s mining the history of their training for insights into why these systems work the way they d...
www.quantamagazine.org
September 24, 2025 at 1:52 PM
I really enjoyed talking to @nsaphra.bsky.social about her thoughts on what much language model interpretability research misses. My latest in @quantamagazine.bsky.social:
Reposted by Zachary K Stine
i think regardless of who has authored a paper, we (the scientific community) can and should stop criticizing the work on lack of perceived novelty. we can do better than perpetuating harmful myths about individual scientific papers having to present a discovery no one has ever thought of before.
September 21, 2025 at 7:10 PM
i think regardless of who has authored a paper, we (the scientific community) can and should stop criticizing the work on lack of perceived novelty. we can do better than perpetuating harmful myths about individual scientific papers having to present a discovery no one has ever thought of before.
Forgive one last point to vent about: The reviewer’s only other criticism was a lack of novelty. The obsession with novelty has made a lot of ML work insufferable so it’s unfortunate to see it here. But here’s who is apparently already making our points about how ML is used for humanities research:
Our second reviewer (we only had two) voted strong reject. Their biggest problem with the paper seemed to be the lack of empirical work, and they claimed CHR only wants empirical stuff. If that’s correct, it’s a real blight on an otherwise cool conference. 17/
September 21, 2025 at 4:43 AM
Forgive one last point to vent about: The reviewer’s only other criticism was a lack of novelty. The obsession with novelty has made a lot of ML work insufferable so it’s unfortunate to see it here. But here’s who is apparently already making our points about how ML is used for humanities research:
Reposted by Zachary K Stine
How to quantify the impact of AI on long-run cultural evolution? Published today, I give it a go!
400+ years of strategic dynamics in the game of Go (Baduk/Weiqi), from feudalism to AlphaGo!
400+ years of strategic dynamics in the game of Go (Baduk/Weiqi), from feudalism to AlphaGo!
September 16, 2025 at 2:04 PM
How to quantify the impact of AI on long-run cultural evolution? Published today, I give it a go!
400+ years of strategic dynamics in the game of Go (Baduk/Weiqi), from feudalism to AlphaGo!
400+ years of strategic dynamics in the game of Go (Baduk/Weiqi), from feudalism to AlphaGo!
Reposted by Zachary K Stine
Well, this got rejected today as a short position paper from CHR so I suppose I can share it now: arxiv.org/pdf/2508.00095
Here’s a hopefully coherent ramble about what we’re trying to make clear:
Here’s a hopefully coherent ramble about what we’re trying to make clear:
September 19, 2025 at 6:22 PM
Well, this got rejected today as a short position paper from CHR so I suppose I can share it now: arxiv.org/pdf/2508.00095
Here’s a hopefully coherent ramble about what we’re trying to make clear:
Here’s a hopefully coherent ramble about what we’re trying to make clear:
Well, this got rejected today as a short position paper from CHR so I suppose I can share it now: arxiv.org/pdf/2508.00095
Here’s a hopefully coherent ramble about what we’re trying to make clear:
Here’s a hopefully coherent ramble about what we’re trying to make clear:
September 19, 2025 at 6:22 PM
Well, this got rejected today as a short position paper from CHR so I suppose I can share it now: arxiv.org/pdf/2508.00095
Here’s a hopefully coherent ramble about what we’re trying to make clear:
Here’s a hopefully coherent ramble about what we’re trying to make clear:
Reposted by Zachary K Stine
Out now! Bride of Frankenstein [film|minutes]
September 11, 2025 at 11:52 PM
Out now! Bride of Frankenstein [film|minutes]
Reposted by Zachary K Stine
A quick summary for busy people:
We propose a mathematical framework for learning representations by extracting the algebra of transformations of worlds from the agent's perspective.
1/n
www.sciencedirect.com/science/arti...
We propose a mathematical framework for learning representations by extracting the algebra of transformations of worlds from the agent's perspective.
1/n
www.sciencedirect.com/science/arti...
Algebras of actions in an agent's representations of the world
Learning efficient representations allows robust processing of data, data that can then be generalised across different tasks and domains, and it is t…
www.sciencedirect.com
September 11, 2025 at 5:40 PM
A quick summary for busy people:
We propose a mathematical framework for learning representations by extracting the algebra of transformations of worlds from the agent's perspective.
1/n
www.sciencedirect.com/science/arti...
We propose a mathematical framework for learning representations by extracting the algebra of transformations of worlds from the agent's perspective.
1/n
www.sciencedirect.com/science/arti...
Reposted by Zachary K Stine
💻 We are very excited to announce the launch of our special issue Computational Formalism, edited by Tess McNulty and Laura Alice Chapot, that reconsiders the intersections of computation and form at this emerging technological and critical moment.
culturalanalytics.org/issue/12788
culturalanalytics.org/issue/12788
Vol. 10, Issue 3, 2025 | Published by Journal of Cultural Analytics
In this special issue, we bring together scholars from across multiple disciplines to reconsider the intersections of computation and form at this emerging technological and critical moment.
culturalanalytics.org
September 10, 2025 at 7:37 PM
💻 We are very excited to announce the launch of our special issue Computational Formalism, edited by Tess McNulty and Laura Alice Chapot, that reconsiders the intersections of computation and form at this emerging technological and critical moment.
culturalanalytics.org/issue/12788
culturalanalytics.org/issue/12788
Reposted by Zachary K Stine
“[Something] unpredictable, spontaneous, unformulable and ineffable is found in any terminal object. Standardizations, formulae, generalizations, principles, universals, have their place, but the place is that of being instrumental to better approximation to what is unique and unrepeatable.” (1/2)
September 10, 2025 at 4:15 PM
“[Something] unpredictable, spontaneous, unformulable and ineffable is found in any terminal object. Standardizations, formulae, generalizations, principles, universals, have their place, but the place is that of being instrumental to better approximation to what is unique and unrepeatable.” (1/2)
Reposted by Zachary K Stine
A GoFundMe for the instructor who was fired at Texas A&M!
I overlapped with the instructor, Melissa, as grad students in Notre Dame's English department. One of her former ND colleagues has started a GoFundMe for her: gofund.me/3f5b12078
Donate to Help Support Our Children's Literature Colleague, organized by Angel Matos
Recently, our colleague Melissa McCoul was fired from her position as a S… Angel Matos needs your support for Help Support Our Children's Literature Colleague
gofund.me
September 10, 2025 at 9:48 PM
A GoFundMe for the instructor who was fired at Texas A&M!
I have a thing under review right now that argues translations across research domains (as epistemic “languages”) are useful insofar as translators can give a theory of their work. Auto-translation necessarily hides interpretive choices and so can only be useful in very narrow cases.
[Sometimes I think about the folks who studied for years to be professional language translators.]
* APPLE SAYS AIRPODS PRO 3 WILL HAVE LIVE TRANSLATION
@reuters.com $AAPL
* APPLE SAYS AIRPODS PRO 3 WILL HAVE LIVE TRANSLATION
@reuters.com $AAPL
September 10, 2025 at 2:08 PM
I have a thing under review right now that argues translations across research domains (as epistemic “languages”) are useful insofar as translators can give a theory of their work. Auto-translation necessarily hides interpretive choices and so can only be useful in very narrow cases.