Sarita Rosenstock
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sarita Rosenstock has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
James Owen Weatherall
2 shared publications- James Owen Weatherall
Department of Logic and Philosophy of Science University of California Irvine
2 shared publications - Benjamin H. Feintzeig
Department of Philosophy, University of Washington, Seattle, USA
1 shared publication - Cailin O'Connor
University of California Irvine
1 shared publication Cailin O’cOnnor
1 shared publication- Christoph Treude
Singapore Management University, Singapore
1 shared publication
Latest Publications
- Open Access
- 24 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 177-188
Documenting Ethical Considerations in Open Source AI Models
Background: The development of AI-enabled software heavily depends on AI model documentation, such as model cards, due to different domain expertise between software engineers and model developers. From an ethical standpoint, AI model documentation conveys critical information on ethical considerations along with mitigation strategies for downstream developers to ensure the delivery of ethically compliant software. However, knowledge on such documentation practice remains scarce. Aims: The objective of our study is to investigate how developers document ethical aspects of open source AI models in practice, aiming at providing recommendations for future documentation endeavours. Method: We selected three sources of documentation on GitHub and Hugging Face, and developed a keyword set to identify ethics-related documents systematically. After filtering an initial set of 2,347 documents, we identified 265 relevant ones and performed thematic analysis to derive the themes of ethical considerations. Results: Six themes emerge, with the three largest ones being model behavioural risks, model use cases, and model risk mitigation. Conclusions: Our findings reveal that open source AI model documentation focuses on articulating ethical problem statements and use case restrictions. We further provide suggestions to various stakeholders for improving documentation practice regarding ethical considerations.
- 24 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 177-188
Open AccessDocumenting Ethical Considerations in Open Source AI Models
Background: The development of AI-enabled software heavily depends on AI model documentation, such as model cards, due to different domain expertise between software engineers and model developers. From an ethical standpoint, AI model documentation conveys critical information on ethical considerations along with mitigation strategies for downstream developers to ensure the delivery of ethically compliant software. However, knowledge on such documentation practice remains scarce. Aims: The objective of our study is to investigate how developers document ethical aspects of open source AI models in practice, aiming at providing recommendations for future documentation endeavours. Method: We selected three sources of documentation on GitHub and Hugging Face, and developed a keyword set to identify ethics-related documents systematically. After filtering an initial set of 2,347 documents, we identified 265 relevant ones and performed thematic analysis to derive the themes of ethical considerations. Results: Six themes emerge, with the three largest ones being model behavioural risks, model use cases, and model risk mitigation. Conclusions: Our findings reveal that open source AI model documentation focuses on articulating ethical problem statements and use case restrictions. We further provide suggestions to various stakeholders for improving documentation practice regarding ethical considerations.
- 1 February 2019
- Published by Elsevier in Studies in History and Philosophy of Science Part B: Studies in History and Philosophy of Modern Physics
- Vol. 65, 122-132
Why Be regular?, part I
- 1 February 2019
- Published by Elsevier in Studies in History and Philosophy of Science Part B: Studies in History and Philosophy of Modern Physics
- Vol. 65, 122-132
Why Be regular?, part I
- Open Access
- 2 March 2018
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 5
When It’s Good to Feel Bad: An Evolutionary Model of Guilt and Apology
We use techniques from evolutionary game theory to analyze the conditions under which guilt can provide individual fitness benefits, and so evolve. In particular, we focus on the benefits of guilty apology. We consider models where actors err in an iterated prisoner’s dilemma and have the option to apologize. Guilt either improves the trustworthiness of apology or imposes a cost on actors who apologize. We analyze the stability and likelihood of evolution of such a “guilt-prone” strategy against cooperators, defectors, grim triggers, and individuals who offer fake apologies, but continue to defect. We find that in evolutionary models guilty apology is more likely to evolve in cases where actors interact repeatedly over long periods of time, where the costs of apology are low or moderate, and where guilt is hard to fake. Researchers interested in naturalized ethics, and emotion researchers, can employ these results to assess the plausibility of fuller accounts of the evolution of guilt.
- 2 March 2018
- Published by Frontiers Media SA in Frontiers in Robotics and AI
- Vol. 5
Open AccessWhen It’s Good to Feel Bad: An Evolutionary Model of Guilt and Apology
We use techniques from evolutionary game theory to analyze the conditions under which guilt can provide individual fitness benefits, and so evolve. In particular, we focus on the benefits of guilty apology. We consider models where actors err in an iterated prisoner’s dilemma and have the option to apologize. Guilt either improves the trustworthiness of apology or imposes a cost on actors who apologize. We analyze the stability and likelihood of evolution of such a “guilt-prone” strategy against cooperators, defectors, grim triggers, and individuals who offer fake apologies, but continue to defect. We find that in evolutionary models guilty apology is more likely to evolve in cases where actors interact repeatedly over long periods of time, where the costs of apology are low or moderate, and where guilt is hard to fake. Researchers interested in naturalized ethics, and emotion researchers, can employ these results to assess the plausibility of fuller accounts of the evolution of guilt.
- Top Cited Papers
- 1 April 2017
- Published by Cambridge University Press (CUP) in Philosophy of Science
- Vol. 84 (2) , 234-252
In Epistemic Networks, Is Less Really More?
We show that previous results from epistemic network models by Kevin J. S. Zollman and Erich Kummerfeld showing the benefits of decreased connectivity in epistemic networks are not robust across changes in parameter values. Our findings motivate discussion about whether and how such models can inform real world epistemic communities.
- 1 April 2017
- Published by Cambridge University Press (CUP) in Philosophy of Science
- Vol. 84 (2) , 234-252
Top Cited PapersIn Epistemic Networks, Is Less Really More?
We show that previous results from epistemic network models by Kevin J. S. Zollman and Erich Kummerfeld showing the benefits of decreased connectivity in epistemic networks are not robust across changes in parameter values. Our findings motivate discussion about whether and how such models can inform real world epistemic communities.
- 1 October 2016
- Published by AIP Publishing in Journal of Mathematical Physics
- Vol. 57 (10) , 102902
A categorical equivalence between generalized holonomy maps on a connected manifold and principal connections on bundles over that manifold
A classic result in the foundations of Yang-Mills theory, due to Barrett [Int. J. Theor. Phys. 30, 1171–1215 (1991)], establishes that given a “generalized” holonomy map from the space of piece-wise smooth, closed curves based at some point of a manifold to a Lie group, there exists a principal bundle with that group as structure group and a principal connection on that bundle such that the holonomy map corresponds to the holonomies of that connection. Barrett also provided one sense in which this “recovery theorem” yields a unique bundle, up to isomorphism. Here we show that something stronger is true: with an appropriate definition of isomorphism between generalized holonomy maps, there is an equivalence of categories between the category whose objects are generalized holonomy maps on a smooth, connected manifold and whose arrows are holonomy isomorphisms, and the category whose objects are principal connections on principal bundles over a smooth, connected manifold. This result clarifies, and somewhat improves upon, the sense of “unique recovery” in Barrett’s theorems; it also makes precise a sense in which there is no loss of structure involved in moving from a principal bundle formulation of Yang-Mills theory to a holonomy, or “loop,” formulation.
- 1 October 2016
- Published by AIP Publishing in Journal of Mathematical Physics
- Vol. 57 (10) , 102902
A categorical equivalence between generalized holonomy maps on a connected manifold and principal connections on bundles over that manifold
A classic result in the foundations of Yang-Mills theory, due to Barrett [Int. J. Theor. Phys. 30, 1171–1215 (1991)], establishes that given a “generalized” holonomy map from the space of piece-wise smooth, closed curves based at some point of a manifold to a Lie group, there exists a principal bundle with that group as structure group and a principal connection on that bundle such that the holonomy map corresponds to the holonomies of that connection. Barrett also provided one sense in which this “recovery theorem” yields a unique bundle, up to isomorphism. Here we show that something stronger is true: with an appropriate definition of isomorphism between generalized holonomy maps, there is an equivalence of categories between the category whose objects are generalized holonomy maps on a smooth, connected manifold and whose arrows are holonomy isomorphisms, and the category whose objects are principal connections on principal bundles over a smooth, connected manifold. This result clarifies, and somewhat improves upon, the sense of “unique recovery” in Barrett’s theorems; it also makes precise a sense in which there is no loss of structure involved in moving from a principal bundle formulation of Yang-Mills theory to a holonomy, or “loop,” formulation.
- 1 November 2015
- Published by Elsevier in Studies in History and Philosophy of Science Part B: Studies in History and Philosophy of Modern Physics
- Vol. 52, 309-316
On Einstein algebras and relativistic spacetimes
- 1 November 2015
- Published by Elsevier in Studies in History and Philosophy of Science Part B: Studies in History and Philosophy of Modern Physics
- Vol. 52, 309-316
On Einstein algebras and relativistic spacetimes
- 1 October 2013
- Published by Elsevier in Physics of the Earth and Planetary Interiors
- Vol. 223, 32-39
Annealing of directionally solidified alloys revisited: No loss of solidification texture in Earth’s inner core
- 1 October 2013
- Published by Elsevier in Physics of the Earth and Planetary Interiors
- Vol. 223, 32-39
Annealing of directionally solidified alloys revisited: No loss of solidification texture in Earth’s inner core