pith. sign in

arxiv: 2606.23840 · v1 · pith:GSXTGDGWnew · submitted 2026-06-22 · 💻 cs.HC

Embodied Explainability and Ontological Obstacles: Why We Struggle to Explain the Answers of Large Language Models (LLMs)

Marvin Pafla , Jesse Hoey , Kate Larson , Mark Hancock This is my paper

Pith reviewed 2026-06-26 06:52 UTC · model grok-4.3

classification 💻 cs.HC
keywords explainabilitylarge language modelsembodied accountontological obstaclesXAI practiceaffordancesoverreliancesituated practice
0
0 comments X

The pith

Explainability claims for large language models should apply only to designs that give users ways to probe, coordinate, and repair behavior in actual practice.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that explainability is not a property extracted from a model's internals but something created when people act on affordances within shared practice. It identifies ontological obstacles in attempts to look inside large language models, where any surrogate explanation brings in outside abstractions that risk being taken as the model's own and where attention to internal steps overlooks how the explainer participates in making sense. This distinction matters because it shows why many current explanations are misnamed, which can distort their intended use and raise the chance of overreliance on model outputs. If the argument holds, attention shifts toward designs that make what matters publicly available so users can act on it directly.

Core claim

The paper claims that an embodied view of explainability shows why internal accounts of large language model answers encounter obstacles: surrogates import external abstractions that can be mistaken for the model's abstractions, and a focus on internal reasoning misses the participatory character of understanding. As a result, many explanations in current practice are misnamed, which skews their purpose and can increase overreliance. Embodied explanations instead reorganize sense-making by making relevant elements publicly available for action, so that explainability claims belong only to designs supplying affordances to probe, coordinate, and repair behavior in situated practice.

What carries the argument

The embodied account of explainability, in which understanding arises through action on affordances in shared practice, which carries the argument by exposing the limits of internal extraction methods.

If this is right

  • Explanations limited to model internals should not receive the label of explainability.
  • Misnamed explanations can distort their purpose and increase overreliance on model answers.
  • Embodied explanations make what matters publicly available so users can act on it.
  • Explainability applies only to designs that supply affordances for probing, coordinating, and repairing behavior in practice.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Designers could test whether adding explicit probe and repair actions to an interface lowers overreliance more than adding static internal explanations.
  • The same distinction between surrogate and embodied accounts could be checked in domains outside language models, such as image or sensor-based systems.
  • Teams working together might show different patterns of coordination when explanations are made available as shared actions rather than private internal reports.

Load-bearing premise

Any surrogate explanation necessarily imports external abstractions that can be mistaken for the model's own abstractions, and attention to internal reasoning always misses the participatory nature of understanding.

What would settle it

An experiment in which users receive either an internal surrogate explanation or an embodied design and show no difference in their ability to distinguish imported abstractions from model behavior or in their rate of overreliance on model answers.

read the original abstract

Explainability is often framed as a property of an AI model, with explanations extracted from its internals and shown to users. In this argument paper, we instead provide an embodied account of explainability based on Dourish and enactivist cognition: understanding is created in use as people act on affordances in shared practice. Using demonstrations and conceptual analysis, we reveal ontological obstacles when "looking inside" large language models: surrogates import external abstractions that can be mistaken for the model's, and focusing on internal reasoning misses that explainers participate in their own understanding. We discuss these obstacles in XAI practice, arguing that many explanations are misnamed, which skews their purpose and can increase overreliance. Finally, we highlight how embodied explanations reorganize sense-making by making what matters publicly available for action, and argue that explainability claims should be reserved for designs that provide affordances to probe, coordinate, and repair behaviour in situated practice.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The paper claims that explainability for LLMs should be understood through an embodied, enactivist account (drawing on Dourish) rather than by extracting internal surrogates from the model. It identifies two ontological obstacles—surrogates import external abstractions that can be mistaken for the model's own, and internal focus misses participatory sense-making—and uses demonstrations plus conceptual analysis to argue that many current explanations are misnamed, which can increase overreliance. The normative conclusion is that explainability claims should be reserved for designs providing affordances to probe, coordinate, and repair behaviour in situated practice.

Significance. If the argument holds, the paper offers a coherent conceptual reframing of XAI within HCI that shifts emphasis from internal model inspection to situated action and publicly available affordances. It explicitly credits and builds on established prior philosophical work (Dourish, enactivist cognition) without circularity, free parameters, or invented entities, and advances a falsifiable normative claim about appropriate naming of explanations.

minor comments (3)
  1. The abstract is information-dense; consider splitting the description of the two ontological obstacles into separate sentences to improve readability for readers outside enactivist traditions.
  2. In the discussion of XAI practice, the claim that explanations 'skew their purpose' would benefit from one additional sentence clarifying the mechanism by which misnaming leads to overreliance, even if only conceptually.
  3. Ensure the demonstrations referenced in the abstract are explicitly signposted with section numbers in the main text so readers can locate the concrete illustrations of the obstacles.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the accurate summary of our argument paper, the positive assessment of its significance, and the recommendation for minor revision. No specific major comments appear in the report, so we have no points requiring direct rebuttal or revision at this stage.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper advances a conceptual reframing of explainability as embodied and participatory, grounded in external philosophical sources (Dourish, enactivist cognition) rather than any internal equations, fitted parameters, or self-referential definitions. Its derivation proceeds via demonstrations and analysis to identify ontological obstacles and recommend affordance-based designs; this chain does not reduce by construction to its own inputs or to a load-bearing self-citation chain. The argument remains self-contained within its stated philosophical framing.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper rests on philosophical premises from embodied and enactivist cognition rather than empirical measurements or derivations; no free parameters or invented entities are introduced.

axioms (1)
  • domain assumption Understanding is created in use as people act on affordances in shared practice (Dourish and enactivist cognition)
    This framework is invoked to analyze explainability and identify obstacles when looking inside models.

pith-pipeline@v0.9.1-grok · 5704 in / 1258 out tokens · 29948 ms · 2026-06-26T06:52:58.932997+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

119 extracted references · 64 canonical work pages · 1 internal anchor

  1. [1]

    Fred Adams and Ken Aizawa. 2001. The bounds of cognition.Philosophical Psychology14, 1 (2001), 43–64

    2001

  2. [2]

    Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. 2018. Sanity checks for saliency maps. InAdvances in Neu- ral Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran As- sociates, Inc. https://proceedings.neurips.cc/paper_files/pape...

    2018

  3. [3]

    aboutness

    Kathleen Akins. 1996. Of sensory systems and the "aboutness" of mental states. Journal of Philosophy93, 7 (1996), 337–372. doi:10.2307/2941125

    work page doi:10.2307/2941125 1996

  4. [4]

    Ali Alkhatib. 2021. To live in their utopia: Why algorithmic systems create absurd outcomes. InProceedings of the 2021 CHI Conference on Human Factors in Computing Systems(Yokohama, Japan)(CHI ’21). Association for Computing Ma- chinery, New York, NY, USA, Article 95, 9 pages. doi:10.1145/3411764.3445740

    work page doi:10.1145/3411764.3445740 2021

  5. [5]

    David Alvarez Melis, Harmanpreet Kaur, Hal Daumé III, Hanna Wallach, and Jennifer Wortman Vaughan. 2021. From human explanation to model inter- pretability: A framework based on weight of evidence.Proceedings of the AAAI Conference on Human Computation and Crowdsourcing9, 1 (Oct. 2021), 35–47. doi:10.1609/hcomp.v9i1.18938

    work page doi:10.1609/hcomp.v9i1.18938 2021

  6. [6]

    Ayman Alzayat, Mark Hancock, and Miguel A. Nacenta. 2019. Quantitative measurement of tool embodiment for virtual reality input alternatives. InPro- ceedings of the 2019 CHI Conference on Human Factors in Computing Systems (Glasgow, Scotland Uk)(CHI ’19). Association for Computing Machinery, New York, NY, USA, 1–11. doi:10.1145/3290605.3300673

    work page doi:10.1145/3290605.3300673 2019

  7. [7]

    Emmanuel Ameisen, Jack Lindsey, Adam Pearce, Wes Gurnee, Nicholas L. Turner, Brian Chen, Craig Citro, David Abrahams, Shan Carter, Basil Hos- mer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Ri...

    2025

  8. [8]

    Iqbal, Jina Suh, Brian A

    Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. 2019. Guidelines for human- AI interaction. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland Uk)(CHI ’19). Associa...

    work page doi:10.1145/3290605.3300233 2019

  9. [9]

    Iván Arcuschin, Jett Janiak, Robert Krzyzanowski, Senthooran Rajamanoharan, Neel Nanda, and Arthur Conmy. 2025. Chain-of-thought reasoning in the wild is not always faithful. InWorkshop on Reasoning and Planning for Large Language Models. San Fransisco, CA. https://openreview.net/forum?id=L8094Whth0

    2025

  10. [10]

    Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, and Daniel Weld. 2021. Does the whole exceed its parts? The effect of AI explanations on complementary team performance. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (Yokohama, Japan)(CHI ’21). Association for Computing M...

    work page doi:10.1145/3411764.3445717 2021

  11. [11]

    Alejandro Barredo Arrieta, Natalia Díaz-Rodríguez, Javier Del Ser, Adrien Ben- netot, Siham Tabik, Alberto Barbado, Salvador Garcia, Sergio Gil-Lopez, Daniel Molina, Richard Benjamins, Raja Chatila, and Francisco Herrera. 2020. Ex- plainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI.Information...

    work page doi:10.1016/j.inffus.2019.12.012 2020

  12. [12]

    Nighat Bibi, Jane Courtney, and Kevin McGuinness. 2025. Enhancing brain disease diagnosis with XAI: A review of recent studies.ACM Trans. Comput. Healthcare6, 2, Article 16 (Feb. 2025), 35 pages. doi:10.1145/3709152

    work page doi:10.1145/3709152 2025

  13. [13]

    Ned Block. 2007. Review of Alva Noë, Action in Perception. InConsciousness, Function, and Representation, Volume 1: Collected Papers. The MIT Press. doi:10. 7551/mitpress/2111.003.0022

    2007

  14. [14]

    2019.Situated interaction

    Dan Bohus and Eric Horvitz. 2019.Situated interaction. Association for Com- puting Machinery and Morgan & Claypool, 105–143. https://doi.org/10.1145/ 3233795.3233800

    arXiv 2019

  15. [15]

    Nattapat Boonprakong, Benjamin Tag, Jorge Goncalves, and Tilman Dingler

  16. [16]

    In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25)

    How do HCI researchers study cognitive biases? A scoping review. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 473, 20 pages. doi:10.1145/3706598.3713450

    work page doi:10.1145/3706598.3713450 2025

  17. [17]

    Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gr...

    2020

  18. [18]

    Peter Carruthers. 2015. Perceiving mental states.Consciousness and Cognition 36 (2015), 498 – 507. doi:10.1016/j.concog.2015.04.009

    work page doi:10.1016/j.concog.2015.04.009 2015

  19. [19]

    Dongpan Chen, Dehui Kong, Jinghua Li, Shaofan Wang, and Baocai Yin. 2023. A survey of visual affordance recognition based on deep learning.IEEE Trans- actions on Big Data9, 6 (2023), 1458–1476. doi:10.1109/TBDATA.2023.3291558

    work page doi:10.1109/tbdata.2023.3291558 2023

  20. [20]

    Andy Clark. 2015. Radical predictive processing.The Southern Journal of Philosophy53, S1 (2015), 3–27. doi:10.1111/sjp.12120

    work page doi:10.1111/sjp.12120 2015

  21. [21]

    Roberto Confalonieri, Ludovik Coba, Benedikt Wagner, and Tarek R. Besold. 2021. A historical perspective of explainable artificial intelli- gence.WIREs Data Mining and Knowledge Discovery11, 1 (2021), e1391. arXiv:https://wires.onlinelibrary.wiley.com/doi/pdf/10.1002/widm.1391 doi:10. 1002/widm.1391

    work page doi:10.1002/widm.1391 2021

  22. [22]

    2021.The Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence

    Kate Crawford. 2021.The Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press, New Haven, CT

    2021

  23. [23]

    Laura Cros Vila and Bob Sturm. 2025. (Mis)communicating with our AI systems. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 416, 9 pages. doi:10.1145/3706598.3713771

    work page doi:10.1145/3706598.3713771 2025

  24. [24]

    Marina Danilevsky, Kun Qian, Ranit Aharonov, Yannis Katsis, Ban Kawas, and Prithviraj Sen. 2020. A survey of the state of explainable AI for natural language processing. InProceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing...

    2020

  25. [25]

    Shai Danziger, Jonathan Levav, and Liora Avnaim-Pesso. 2011. Extraneous factors in judicial decisions.Proceedings of the National Academy of Sciences 108, 17 (2011), 6889–6892. doi:10.1073/pnas.1018033108

    work page doi:10.1073/pnas.1018033108 2011

  26. [26]

    Regina de Brito Duarte, Mónica Costa Abreu, Joana Campos, and Ana Paiva

  27. [27]

    InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25)

    The amplifying effect of explainability in AI-assisted decision-making in groups. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, USA, Article 259, 15 pages. doi:10.1145/3706598.3713534

    work page doi:10.1145/3706598.3713534 2025

  28. [28]

    Hanne De Jaegher and Ezequiel Di Paolo. 2007. Participatory sense-making. Phenomenology and the Cognitive Sciences6, 4 (01 Dec 2007), 485–507. doi:10. 1007/s11097-007-9076-9

    2007

  29. [29]

    Hanne De Jaegher, Ezequiel Di Paolo, and Shaun Gallagher. 2010. Can social interaction constitute social cognition?Trends in Cognitive Sciences14, 10 (2010), 441 – 447. doi:10.1016/j.tics.2010.06.009 Cited by: 731

    work page doi:10.1016/j.tics.2010.06.009 2010

  30. [30]

    Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of inter- pretable machine learning. doi:10.48550/ARXIV.1702.08608

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1702.08608 2017

  31. [31]

    2001.Where the action is: The foundations of embodied interaction

    Paul Dourish. 2001.Where the action is: The foundations of embodied interaction. MIT press

    2001

  32. [32]

    Paul Dourish. 2004. What we talk about when we talk about context.Personal and Ubiquitous Computing8, 1 (01 Feb 2004), 19–30. doi:10.1007/s00779-003- 0253-8

    work page doi:10.1007/s00779-003- 2004

  33. [33]

    Paul Dourish. 2013. Epilogue: Where the action was, wasn’t, should have been, and might yet be.ACM Trans. Comput.-Hum. Interact.20, 1, Article 2 (April 2013), 4 pages. doi:10.1145/2442106.2442108

    work page doi:10.1145/2442106.2442108 2013

  34. [34]

    Jacob Dunefsky, Philippe Chlenski, and Neel Nanda. 2024. Transcoders find interpretable LLM feature circuits. InThe Thirty-eighth Annual Conference on Neural Information Processing Systems. https://openreview.net/forum?id= J6zHcScAo0

    2024

  35. [36]

    Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Mar- tin Wattenberg, and Christopher Olah. 2022. Toy models of superposition. arXiv:2209.10652 [cs.LG] https://arxiv.org/abs/2209.10652

    Pith/arXiv arXiv 2022

  36. [37]

    Philip W Fink, Patrick S Foo, and William H Warren. 2009. Catching fly balls in virtual reality: A critical test of the outfielder problem.J Vis9, 13 (Dec. 2009), 14.1–8

    2009

  37. [38]

    Raymond Fok and Daniel S. Weld. 2023. In search of verifiability: Explana- tions rarely enable complementary performance in AI-advised decision making. ArXivabs/2305.07722 (2023). Pafla et al

    arXiv 2023

  38. [39]

    Huber, and Christian Horz

    Benjamin Fresz, Elena Dubovitskaya, Danilo Brajovic, Marco F. Huber, and Christian Horz. 2025.How Should AI Decisions Be Explained? Requirements for Explanations from the Perspective of European Law. Vol. 7. AAAI Press, 438–450

    2025

  39. [40]

    Shaun Gallagher. 2008. Direct perception in the intersubjective context.Con- scious Cogn17, 2 (April 2008), 535–543

    2008

  40. [41]

    2023.Embodied and Enactive Approaches to Cognition

    Shaun Gallagher. 2023.Embodied and Enactive Approaches to Cognition. Cam- bridge University Press

    2023

  41. [42]

    Gallegos, Ryan A

    Isabel O. Gallegos, Ryan A. Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, and Nesreen K. Ahmed

  42. [43]

    and Rossi, Ryan A

    Bias and fairness in large language models: A survey.Computational Linguistics50, 3 (09 2024), 1097–1179. arXiv:https://direct.mit.edu/coli/article- pdf/50/3/1097/2471010/coli_a_00524.pdf doi:10.1162/coli_a_00524

    work page doi:10.1162/coli_a_00524 2024

  43. [44]

    William W. Gaver. 1991. Technology affordances. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(New Orleans, Louisiana, USA)(CHI ’91). Association for Computing Machinery, New York, NY, USA, 79–84. doi:10.1145/108844.108856

    work page doi:10.1145/108844.108856 1991

  44. [45]

    Amirata Ghorbani, Abubakar Abid, and James Zou. 2019. Interpretation of neural networks is fragile.Proceedings of the AAAI Conference on Artificial Intelligence33, 01 (Jul. 2019), 3681–3688. doi:10.1609/aaai.v33i01.33013681

    work page doi:10.1609/aaai.v33i01.33013681 2019

  45. [46]

    2014.The Ecological Approach to Visual Perception: Classic Edition

    James J Gibson. 2014.The Ecological Approach to Visual Perception: Classic Edition. Psychology press

    2014

  46. [47]

    Alvin Goldman and Frederique de Vignemont. 2009. Is social cognition embod- ied?Trends in Cognitive Science13, 4 (2009), 154–159

    2009

  47. [48]

    Alvin I. Goldman. 2012. A moderate approach to embodied cognitive science. Review of Philosophy and Psychology3, 1 (2012), 71–88. doi:10.1007/s13164-012- 0089-0

    work page doi:10.1007/s13164-012- 2012

  48. [49]

    right to explanation

    Bryce Goodman and Seth Flaxman. 2017. European union regulations on algorithmic decision-making and a “right to explanation”.AI Magazine38, 3 (Oct. 2017), 50–57. doi:10.1609/aimag.v38i3.2741

    work page doi:10.1609/aimag.v38i3.2741 2017

  49. [50]

    Łukasz Górski and Shashishekar Ramakrishna. 2021. Explainable artificial intelligence, lawyer’s perspective. InProceedings of the Eighteenth International Conference on Artificial Intelligence and Law(São Paulo, Brazil)(ICAIL ’21). Association for Computing Machinery, New York, NY, USA, 60–68. doi:10.1145/ 3462757.3466145

    arXiv 2021

  50. [51]

    Pulkit Goyal, Emily Baird, Mandyam V Srinivasan, and Florian T Muijres. 2023. Visual guidance of honeybees approaching a vertical landing surface.Journal of Experimental Biology226, 17 (2023)

    2023

  51. [52]

    Herbert Paul Grice. 1982. Meaning revisited. InMutual Knowledge, N. V. Smith (Ed.). Academic Press, New York, 223–243

    1982

  52. [53]

    Halpern and Judea Pearl

    Joseph Y. Halpern and Judea Pearl. 2005. Causes and explanations: A structural- model approach. Part I: Causes.The British Journal for the Philosophy of Science 56, 4 (12 2005), 843–887. doi:10.1093/bjps/axi147

    work page doi:10.1093/bjps/axi147 2005

  53. [54]

    Halpern and Judea Pearl

    Joseph Y. Halpern and Judea Pearl. 2005. Causes and explanations: A structural- model approach. Part II: Explanations.The British Journal for the Philosophy of Science56, 4 (12 2005), 889–911. doi:10.1093/bjps/axi148

    work page doi:10.1093/bjps/axi148 2005

  54. [55]

    Gaole He, Nilay Aishwarya, and Ujwal Gadiraju. 2025. Is conversational XAI all you need? Human-AI decision making with a conversational XAI assistant. InProceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25). Association for Computing Machinery, New York, NY, USA, 907–924. doi:10.1145/3708359.3712133

    work page doi:10.1145/3708359.3712133 2025

  55. [56]

    1962.Being and Time, translated by J

    Martin Heidegger. 1962.Being and Time, translated by J. Macquarrie and E. Robinson. Oxford: Blackwell

    1962

  56. [57]

    Geoffrey Hinton. 2022. The forward-forward algorithm: Some preliminary investigations. arXiv:2212.13345 [cs.LG] https://arxiv.org/abs/2212.13345

    arXiv 2022

  57. [58]

    1989.Ideas Pertaining to a Pure Phenomenology and to a Phenomenological Philosophy: Second Book Studies in the Phenomenology of Constitution

    Edmund Husserl. 1989.Ideas Pertaining to a Pure Phenomenology and to a Phenomenological Philosophy: Second Book Studies in the Phenomenology of Constitution. Vol. 3. Springer Science & Business Media

    1989

  58. [59]

    1995.Cognition in the Wild

    Edwin Hutchins. 1995.Cognition in the Wild. The MIT Press. doi:10.7551/ mitpress/1881.001.0001

    1995

  59. [60]

    Edwin Hutchins. 2000. Distributed cognition.International Encyclopedia of the Social and Behavioral Sciences138, 1 (2000), 1–10

    2000

  60. [61]

    Edwin Hutchins. 2011. Enculturating the supersized mind.Philosophical Studies 152, 3 (2011), 437 – 446. doi:10.1007/s11098-010-9599-8

    work page doi:10.1007/s11098-010-9599-8 2011

  61. [62]

    Hutto and Glenda Satne

    Daniel D. Hutto and Glenda Satne. 2015. The natural origins of content. Philosophia43, 3 (2015), 521–536. doi:10.1007/s11406-015-9644-0

    work page doi:10.1007/s11406-015-9644-0 2015

  62. [63]

    Sarthak Jain and Byron C. Wallace. 2019. Attention is not Explanation. InPro- ceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 3543–3556. doi:10.18653/v1/N19-1357

    work page doi:10.18653/v1/n19-1357 2019

  63. [64]

    Lorenzo Jamone, Emre Ugur, Angelo Cangelosi, Luciano Fadiga, Alexandre Bernardino, Justus Piater, and José Santos-Victor. 2018. Affordances in psychol- ogy, neuroscience, and robotics: A survey.IEEE Transactions on Cognitive and Developmental Systems10, 1 (2018), 4–25. doi:10.1109/TCDS.2016.2594134

    work page doi:10.1109/tcds.2016.2594134 2018

  64. [65]

    Jones and Benjamin K

    Cameron R. Jones and Benjamin K. Bergen. 2024. Does GPT-4 pass the Turing test?. InProceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Kevin Duh, Helena Gomez, and Steven Bethard (Eds.). Association for Computational Linguistics, Mexico City...

    work page doi:10.18653/v1/2024.naacl-long.290 2024

  65. [66]

    Kirchhoff

    Alan Jurgens and Michael D. Kirchhoff. 2019. Enactive social cognition: Di- achronic constitution & coupled anticipation.Consciousness and Cognition70 (2019), 1–10. doi:10.1016/j.concog.2019.02.001

    work page doi:10.1016/j.concog.2019.02.001 2019

  66. [67]

    Sunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao, Tania Lombrozo, and Olga Russakovsky. 2025. Fostering appropriate reliance on large language models: The role of explanations, sources, and inconsistencies. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems (CHI ’25). Association for Computing Machinery, New York, NY, U...

    work page doi:10.1145/3706598.3714020 2025

  67. [68]

    u tt, Kristof T. and D \

    Pieter-Jan Kindermans, Sara Hooker, Julius Adebayo, Maximilian Alber, Kristof T. Schütt, Sven Dähne, Dumitru Erhan, and Been Kim. 2019.The (Un)reliability of Saliency Methods. Springer International Publishing, Cham, 267–280. doi:10.1007/978-3-030-28954-6_14

    work page doi:10.1007/978-3-030-28954-6_14 2019

  68. [69]

    Michael Kirchhoff and Julian Kiverstein. 2024. Diachronic constitution. Manuscrito47, 1 (2024), 2022–0042. doi:10.1590/0100-6045.2024.v47n1.mj

    work page doi:10.1590/0100-6045.2024.v47n1.mj 2024

  69. [70]

    Why does quantum field theory in curved spacetime make sense? And what happens to the algebra of observables in the thermodynamic limit?,

    Julian Kiverstein and Michael Kirchhoff. 2023.Dissolving the Causal-Constitution Fallacy: Diachronic Constitution and the Metaphysics of Extended Cognition. Springer International Publishing, Cham, 155–173. doi:10.1007/978-3-031- 39744-8_10

    work page doi:10.1007/978-3-031- 2023

  70. [71]

    Bernard Koch, Emily Denton, Alex Hanna, and Jacob Gates Foster. 2021. Re- duced, reused and recycled: The life of a dataset in machine learning research. InThirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https://openreview.net/forum?id=zNQBIBKJRkd

    2021

  71. [72]

    Michal Kosinski. 2024. Evaluating large language models in theory of mind tasks. Proceedings of the National Academy of Sciences121, 45 (2024), e2405460121. arXiv:https://www.pnas.org/doi/pdf/10.1073/pnas.2405460121 doi:10.1073/pnas. 2405460121

    work page doi:10.1073/pnas.2405460121 2024

  72. [73]

    T. S. Kuhn. 1962.The Structure of Scientific Revolutions.Chicago, University of Chicago Press

    1962

  73. [74]

    & Hinton, G

    Yann LeCun, Y. Bengio, and Geoffrey Hinton. 2015. Deep learning.Nature521 (05 2015), 436–44. doi:10.1038/nature14539

    work page doi:10.1038/nature14539 2015

  74. [75]

    Yi-Chi Liao and Christian Holz. 2025. Redefining affordance via computational rationality. InProceedings of the 30th International Conference on Intelligent User Interfaces (IUI ’25). Association for Computing Machinery, New York, NY, USA, 1188–1202. doi:10.1145/3708359.3712114

    work page doi:10.1145/3708359.3712114 2025

  75. [76]

    Jack Lindsey, Wes Gurnee, Emmanuel Ameisen, Brian Chen, Adam Pearce, Nicholas L. Turner, Craig Citro, David Abrahams, Shan Carter, Basil Hosmer, Jonathan Marcus, Michael Sklar, Adly Templeton, Trenton Bricken, Callum McDougall, Hoagy Cunningham, Thomas Henighan, Adam Jermyn, Andy Jones, Andrew Persic, Zhenyi Qi, T. Ben Thompson, Sam Zimmerman, Kelley Rivo...

    2025

  76. [77]

    Zachary C. Lipton. 2018. The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery.Queue 16, 3 (June 2018), 31–57. doi:10.1145/3236386.3241340

    work page doi:10.1145/3236386.3241340 2018

  77. [78]

    Yi-Long Lu, Chunhui Zhang, Jiajun Song, Lifeng Fan, and Wei Wang. 2025. Do theory of mind benchmarks need explicit human-like reasoning in language models? arXiv:2504.01698 [cs.CL] https://arxiv.org/abs/2504.01698

    arXiv 2025

  78. [79]

    Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. InAdvances in Neural Information Processing Systems (NIPS ’17, Vol. 30). Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/ paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf

    2017

  79. [80]

    Joanna McGrenere and Wayne Ho. 2000. Affordances: Clarifying and evolv- ing a concept. InProceedings of the Graphics Interface. Canadian Human- Computer Communications Society, Montreal, Quebec, Canada, 179–186. http: //graphicsinterface.org/wp-content/uploads/gi2000-24.pdf

    2000

  80. [81]

    2012.Phenomenology of Perception (DA Landes, trans.)

    Maurice Merleau-Ponty. 2012.Phenomenology of Perception (DA Landes, trans.). Routledge New York

    2012

Showing first 80 references.