pith. sign in

arxiv: 2606.25318 · v1 · pith:FY5TSCNJnew · submitted 2026-06-24 · 💻 cs.CV · cs.LG

REViT: Roto-reflection Equivariant Convolutional Vision Transformer

Sheir A. Zaheer , Alexander C. Holston , Chan Y. Park This is my paper

Pith reviewed 2026-06-25 21:23 UTC · model grok-4.3

classification 💻 cs.CV cs.LG
keywords roto-reflection equivariancevision transformerconvolutional attentionimage classificationdiscrete group equivariancesymmetry preservation
0
0 comments X

The pith

REViT equips vision transformers with discrete roto-reflection equivariance via convolutional attention and outperforms prior methods on image classification.

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

The paper introduces REViT, a vision transformer made equivariant to discrete rotations, reflections, and positions by discretizing the roto-reflection group and inserting convolutional attention. This targets the relative scarcity of equivariant transformers compared with CNN-based designs, while preserving symmetry in feature maps for tasks sensitive to input orientation. The authors outline challenges specific to transformers and present the discretization as a simpler route to exact group equivariance. Experiments show the resulting model exceeds earlier discrete roto-reflection equivariant networks in classification accuracy.

Core claim

REViT achieves discrete roto-reflection group equivariance in a vision transformer by combining a discretized roto-reflection group with convolutional attention, preserving rotational, flip, and positional symmetry and delivering higher image classification accuracy than existing discrete roto-reflection equivariant networks.

What carries the argument

Discretized roto-reflection group combined with convolutional attention inside the transformer blocks.

If this is right

  • Equivariance to rotations and reflections is maintained in feature maps for orientation-sensitive tasks.
  • Vision transformers can incorporate discrete group equivariance without relying exclusively on convolutional layers.
  • Performance improvements appear on image classification without additional dataset-specific tuning.

Where Pith is reading between the lines

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

  • The same discretization approach could be applied to object detection where orientation symmetry matters.
  • Training may require less rotation-based data augmentation when symmetries are built into the architecture.
  • Similar discretization strategies might extend to other discrete symmetry groups beyond roto-reflections.

Load-bearing premise

The discretization of the roto-reflection group together with convolutional attention produces exact equivariance and measurable gains without hidden post-hoc adjustments or dataset-specific tuning.

What would settle it

A verification test in which the network outputs change under the group's transformations or classification accuracy fails to exceed that of baseline equivariant models on standard image datasets.

Figures

Figures reproduced from arXiv: 2606.25318 by Alexander C. Holston, Chan Y. Park, Sheir A. Zaheer.

Figure 1
Figure 1. Figure 1: Rotation MNIST (x-axis) and PatchCamelyon (y-axis) performance of REViT vs existing approaches for discrete roto￾translation and roto-reflection group equivariance (G-SA (Romero & Cordonnier, 2021), G-CNN (Cohen & Welling, 2016), α-G￾CNN (Romero et al., 2020)). Sizes of the bubbles are proportional to the number of elements (group order) in the rotation or roto￾reflection (p4m) groups. ject can change dras… view at source ↗
Figure 2
Figure 2. Figure 2: Convolutional Projection of Key, Query and Values (Wu et al., 2021a). The self-attention operation defined in (2) and (4) is per￾mutation equivariant. In simpler terms, if the rows of X are rearranged (permuted), the resulting output Y will also undergo the same permutation, maintaining the same rela￾tive order of the elements. This property means that self￾attention ignores the input order, treating the i… view at source ↗
Figure 3
Figure 3. Figure 3: REViT: (a) L transformer blocks preceded by a lifting layer, (b) illustration of lifting layer for a roto-reflection group with 4 elements, each rotated by 90°, and (c) 3D group convolutional self-attention with two dimensions for spatial projection and 1 dimension along the group elements from lifting layer inverse rotation g −1 maps the shifted coordinate x ′ −x back to the kernel’s canonical space. Addi… view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of interpolation-induced approximation error under discrete rotations. Left: original discrete image on a pixel grid. Top-right: rotation by 90◦ , which aligns exactly with the grid and preserves values exactly. Bottom-right: rotation by 45◦ , where pixel locations fall between grid points and bilinear interpolation is required, resulting in mixed values and approximation artifacts. This discr… view at source ↗
read the original abstract

In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention. Roto-reflection equivariant networks preserve the rotational, flip and positional symmetry in feature maps, making them useful for tasks where orientation of the inputs is relevant to the model outputs. In image classification and object detection, most of the studies on roto-reflection equivariant models have focused on using convolutional neural networks rather than vision transformers. In this paper, we examine the challenges involved in achieving equivariance in vision transformers, and we propose a simpler way to implement a discretized roto-reflection group equivariant vision transformer. The experimental results demonstrate that our approach outperforms the existing approaches for developing discrete roto-reflection group equivariant neural networks for image classification.

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

1 major / 0 minor

Summary. The paper proposes REViT, a vision transformer architecture that achieves discrete roto-reflection (dihedral group) equivariance by lifting features to the group, applying group convolutions, and incorporating convolutional attention within transformer blocks. It claims this yields exact equivariance to rotations and reflections while outperforming prior discrete roto-reflection equivariant networks on image classification.

Significance. If the architecture delivers exact equivariance (rather than approximate) and the reported gains are shown to stem from the symmetry properties, the work would usefully extend equivariant CNN techniques to the transformer setting, addressing a gap noted in the abstract where most roto-reflection equivariant models have been CNN-based.

major comments (1)
  1. [Section 3, Eqs. (4-6)] Section 3, Eqs. (4–6): the attention mechanism is defined via standard dot-product attention applied to the lifted features. No additional constraints or group-equivariant formulation is described that would ensure the attention weights themselves transform correctly under the full dihedral action (including reflections). Because the central claim requires exact equivariance, this omission is load-bearing; without a proof or explicit verification that attention preserves the group action, the model may only be partially equivariant.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their careful review and for highlighting the need to substantiate the exact equivariance claim. We address the single major comment below and will incorporate the requested clarification in a revised manuscript.

read point-by-point responses

  1. Referee: [Section 3, Eqs. (4-6)] Section 3, Eqs. (4–6): the attention mechanism is defined via standard dot-product attention applied to the lifted features. No additional constraints or group-equivariant formulation is described that would ensure the attention weights themselves transform correctly under the full dihedral action (including reflections). Because the central claim requires exact equivariance, this omission is load-bearing; without a proof or explicit verification that attention preserves the group action, the model may only be partially equivariant.

    Authors: We agree that the current description in Section 3 relies on standard scaled dot-product attention applied after lifting the input to the dihedral group and that no separate group-equivariant formulation or proof is supplied for the attention weights under reflections. Because the central claim is exact roto-reflection equivariance, this point requires explicit treatment. In the revision we will add a short lemma (with proof) showing that the overall block remains equivariant: the group-lifted features transform as a regular representation, the convolutional projections that produce queries/keys/values are group convolutions (hence equivariant), and the subsequent softmax-normalized dot-product followed by the value projection preserves the group action because the same linear operations are applied uniformly across all group elements. If the proof reveals that reflections require an additional sign-flip or orientation-reversing adjustment in the attention, we will modify Eqs. (4–6) accordingly and report the change. We will also add a short empirical check (invariance of output under random dihedral transformations on a held-out set) to corroborate the algebraic argument. revision: yes

Circularity Check

0 steps flagged

No circularity detected in derivation chain

full rationale

The manuscript abstract and summary describe a proposed architecture for discrete roto-reflection equivariant vision transformers using convolutional attention, with an empirical claim of outperformance on image classification. No equations, self-citations, or derivation steps are visible that reduce a claimed prediction or uniqueness result to a fitted parameter or prior self-referential definition by construction. The central claim rests on experimental results rather than an internal tautology, and no load-bearing self-citation chain or ansatz smuggling is exhibited. This is the expected outcome when the paper's derivation remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract supplies no equations or implementation details, so no free parameters, axioms, or invented entities can be identified.

pith-pipeline@v0.9.1-grok · 5654 in / 1012 out tokens · 21622 ms · 2026-06-25T21:23:41.398064+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

77 extracted references · 8 canonical work pages

  1. [1]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Redet: A rotation-equivariant detector for aerial object detection , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  2. [2]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Learning RoI transformer for oriented object detection in aerial images , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  3. [3]

    , title =

    Deng, Congyue and Litany, Or and Duan, Yueqi and Poulenard, Adrien and Tagliasacchi, Andrea and Guibas, Leonidas J. , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , month =. 2021 , pages =

    2021

  4. [4]

    arXiv preprint arXiv:2206.04176 , year=

    Vn-transformer: Rotation-equivariant attention for vector neurons , author=. arXiv preprint arXiv:2206.04176 , year=

    arXiv

  5. [5]

    arXiv preprint arXiv:2206.11990 , year=

    Equiformer: Equivariant graph attention transformer for 3d atomistic graphs , author=. arXiv preprint arXiv:2206.11990 , year=

    arXiv

  6. [6]

    arXiv preprint arXiv:2306.12059 , year=

    Equiformerv2: Improved equivariant transformer for scaling to higher-degree representations , author=. arXiv preprint arXiv:2306.12059 , year=

    arXiv

  7. [7]

    arXiv preprint arXiv:2310.08061 , year=

    ETDock: A Novel Equivariant Transformer for Protein-Ligand Docking , author=. arXiv preprint arXiv:2310.08061 , year=

    arXiv

  8. [8]

    Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

    Equivariant point network for 3d point cloud analysis , author=. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

  9. [9]

    arXiv preprint arXiv:2010.02449 , year=

    On the universality of rotation equivariant point cloud networks , author=. arXiv preprint arXiv:2010.02449 , year=

    arXiv 2010

  10. [10]

    International conference on machine learning , pages=

    Group equivariant convolutional networks , author=. International conference on machine learning , pages=. 2016 , organization=

    2016

  11. [11]

    arXiv preprint arXiv:1803.02155 , year=

    Self-attention with relative position representations , author=. arXiv preprint arXiv:1803.02155 , year=

    Pith/arXiv arXiv

  12. [12]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

    Rethinking and improving relative position encoding for vision transformer , author=. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

  13. [13]

    International Conference on Learning Representations , year=

    Group Equivariant Stand-Alone Self-Attention For Vision , author=. International Conference on Learning Representations , year=

  14. [14]

    Advances in neural information processing systems , volume=

    Attention is all you need , author=. Advances in neural information processing systems , volume=

  15. [15]

    The architecture of modern mathematics , pages=

    A path to the epistemology of mathematics: Homotopy theory , author=. The architecture of modern mathematics , pages=. 2006 , publisher=

    2006

  16. [16]

    Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions , year=

    Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling , booktitle=. Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions , year=

  17. [17]

    Proceedings of the IEEE/CVF international conference on computer vision , pages=

    Cvt: Introducing convolutions to vision transformers , author=. Proceedings of the IEEE/CVF international conference on computer vision , pages=

  18. [18]

    2018 , eprint=

    Roto-Translation Covariant Convolutional Networks for Medical Image Analysis , author=. 2018 , eprint=

    2018

  19. [19]

    2020 , eprint=

    Attentive Group Equivariant Convolutional Networks , author=. 2020 , eprint=

    2020

  20. [20]

    2018 , eprint=

    Rotation Equivariant CNNs for Digital Pathology , author=. 2018 , eprint=

    2018

  21. [21]

    2017 , month =

    Ehteshami Bejnordi, Babak and Veta, Mitko and Diest, Paul and Ginneken, Bram and Karssemeijer, Nico and Litjens, Geert and van der Laak, Jeroen and Hermsen, Meyke and Manson, Quirine and Balkenhol, Maschenka and Geessink, Oscar and Stathonikos, Nikolaos and van Dijk, Marcory and Bult, Peter and Beca, Francisco and Beck, Andrew and Wang, Dayong and Khosla,...

    2017

  22. [22]

    Learning Multiple Layers of Features from Tiny Images , url =

    Krizhevsky, Alex , biburl =. Learning Multiple Layers of Features from Tiny Images , url =

  23. [23]

    International Conference on Machine Learning , year=

    An empirical evaluation of deep architectures on problems with many factors of variation , author=. International Conference on Machine Learning , year=

  24. [24]

    Learning rotation invariant convolutional filters for texture classification , url=

    Marcos, Diego and Volpi, Michele and Tuia, Devis , year=. Learning rotation invariant convolutional filters for texture classification , url=. doi:10.1109/icpr.2016.7899932 , booktitle=

    work page doi:10.1109/icpr.2016.7899932 2016

  25. [25]

    2022 , eprint=

    What is an equivariant neural network? , author=. 2022 , eprint=

    2022

  26. [26]

    Geometric deep learning: Going beyond euclidean data,

    Bronstein, Michael M. and Bruna, Joan and LeCun, Yann and Szlam, Arthur and Vandergheynst, Pierre , year=. Geometric Deep Learning: Going beyond Euclidean data , volume=. IEEE Signal Processing Magazine , publisher=. doi:10.1109/msp.2017.2693418 , number=

    work page doi:10.1109/msp.2017.2693418 2017

  27. [27]

    Representations of Finite Groups

    Fulton, William and Harris, Joe. Representations of Finite Groups. Representation Theory: A First Course. 2004. doi:10.1007/978-1-4612-0979-9_1

    work page doi:10.1007/978-1-4612-0979-9_1 2004

  28. [28]

    ImageNet: A large-scale hierarchical image database , year=

    Deng, Jia and Dong, Wei and Socher, Richard and Li, Li-Jia and Kai Li and Li Fei-Fei , booktitle=. ImageNet: A large-scale hierarchical image database , year=

  29. [29]

    2023 , eprint=

    The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry , author=. 2023 , eprint=

    2023

  30. [30]

    2021 , eprint=

    Equivariant message passing for the prediction of tensorial properties and molecular spectra , author=. 2021 , eprint=

    2021

  31. [31]

    Rotation Equivariant Vector Field Networks , url=

    Marcos, Diego and Volpi, Michele and Komodakis, Nikos and Tuia, Devis , year=. Rotation Equivariant Vector Field Networks , url=. doi:10.1109/iccv.2017.540 , booktitle=

    work page doi:10.1109/iccv.2017.540 2017

  32. [32]

    2018 , eprint=

    Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds , author=. 2018 , eprint=

    2018

  33. [33]

    International Conference on Learning Representations , year=

    An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale , author=. International Conference on Learning Representations , year=

  34. [34]

    Rethinking and Improving Relative Position Encoding for Vision Transformer , year=

    Wu, Kan and Peng, Houwen and Chen, Minghao and Fu, Jianlong and Chao, Hongyang , booktitle=. Rethinking and Improving Relative Position Encoding for Vision Transformer , year=

  35. [35]

    R eal F ormer: Transformer Likes Residual Attention

    He, Ruining and Ravula, Anirudh and Kanagal, Bhargav and Ainslie, Joshua. R eal F ormer: Transformer Likes Residual Attention. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021. doi:10.18653/v1/2021.findings-acl.81

    work page doi:10.18653/v1/2021.findings-acl.81 2021

  36. [36]

    Zhao, Linfeng and Li, Hongyu and Padr, Takn and Jiang, Huaizu and Wong, Lawson L.S. , year=. E(2)-Equivariant Graph Planning for Navigation , volume=. IEEE Robotics and Automation Letters , publisher=. doi:10.1109/lra.2024.3360011 , number=

    work page doi:10.1109/lra.2024.3360011 2024

  37. [37]

    2023 , eprint=

    Integrating Symmetry into Differentiable Planning with Steerable Convolutions , author=. 2023 , eprint=

    2023

  38. [38]

    2020 , editor =

    Bogatskiy, Alexander and Anderson, Brandon and Offermann, Jan and Roussi, Marwah and Miller, David and Kondor, Risi , booktitle =. 2020 , editor =

    2020

  39. [39]

    2016 , eprint=

    Permutation-equivariant neural networks applied to dynamics prediction , author=. 2016 , eprint=

    2016

  40. [40]

    2021 , school=

    Equivariant convolutional networks , author=. 2021 , school=

    2021

  41. [41]

    arXiv preprint arXiv:2010.10952 , year=

    A wigner-eckart theorem for group equivariant convolution kernels , author=. arXiv preprint arXiv:2010.10952 , year=

    arXiv 2010

  42. [42]

    IEEE transactions on pattern analysis and machine intelligence , volume=

    A survey on vision transformer , author=. IEEE transactions on pattern analysis and machine intelligence , volume=. 2022 , publisher=

    2022

  43. [43]

    ACM computing surveys (CSUR) , volume=

    Transformers in vision: A survey , author=. ACM computing surveys (CSUR) , volume=. 2022 , publisher=

    2022

  44. [44]

    Advances in neural information processing systems , volume=

    Se (3)-transformers: 3d roto-translation equivariant attention networks , author=. Advances in neural information processing systems , volume=

  45. [45]

    International conference on machine learning , pages=

    E (n) equivariant graph neural networks , author=. International conference on machine learning , pages=. 2021 , organization=

    2021

  46. [46]

    2018 IEEE Winter Conference on Applications of Computer Vision (WACV) , pages=

    A rotationally-invariant convolution module by feature map back-rotation , author=. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) , pages=. 2018 , organization=

    2018

  47. [47]

    IEEE Transactions on Image Processing , year=

    Rotational Convolution: Rethinking Convolution for Downside Fisheye Images , author=. IEEE Transactions on Image Processing , year=

  48. [48]

    2024 , eprint=

    Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures , author=. 2024 , eprint=

    2024

  49. [49]

    2020 , eprint=

    Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis , author=. 2020 , eprint=

    2020

  50. [50]

    CNNs on surfaces using rotation-equivariant features , volume=

    Wiersma, Ruben and Eisemann, Elmar and Hildebrandt, Klaus , year=. CNNs on surfaces using rotation-equivariant features , volume=. ACM Transactions on Graphics , publisher=. doi:10.1145/3386569.3392437 , number=

    work page doi:10.1145/3386569.3392437

  51. [51]

    Yufei Xu and Qiming Zhang and Jing Zhang and Dacheng Tao , booktitle=. Vi. 2021 , url=

    2021

  52. [52]

    A comparative study between vision transformers and CNNs in digital pathology , doi =

    Deininger, Luca and Stimpel, Bernhard and Yuce, Anil and Abbasi-Sureshjani, Samaneh and Schönenberger, Simon and Ocampo, Paolo and Korski, Konstanty and Gaire, Fabien , year =. A comparative study between vision transformers and CNNs in digital pathology , doi =

  53. [53]

    The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=

    3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction , author=. The Thirty-eighth Annual Conference on Neural Information Processing Systems , year=

  54. [54]

    2022 , eprint=

    Self-Supervised Equivariant Learning for Oriented Keypoint Detection , author=. 2022 , eprint=

    2022

  55. [55]

    International Conference on Learning Representations , year=

    Decoupled Weight Decay Regularization , author=. International Conference on Learning Representations , year=

  56. [56]

    CoRR , volume =

    Dan Hendrycks and Kevin Gimpel , title =. CoRR , volume =. 2016 , url =. 1606.08415 , timestamp =

    Pith/arXiv arXiv 2016

  57. [57]

    International conference on machine learning , pages=

    On the generalization of equivariance and convolution in neural networks to the action of compact groups , author=. International conference on machine learning , pages=. 2018 , organization=

    2018

  58. [58]

    Advances in neural information processing systems , volume=

    A general theory of equivariant cnns on homogeneous spaces , author=. Advances in neural information processing systems , volume=

  59. [59]

    International conference on machine learning , pages=

    Generalizing convolutional neural networks for equivariance to lie groups on arbitrary continuous data , author=. International conference on machine learning , pages=. 2020 , organization=

    2020

  60. [60]

    Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

    Harmonic networks: Deep translation and rotation equivariance , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

  61. [61]

    Cohen and Mario Geiger and Jonas Köhler and Max Welling , booktitle=

    Taco S. Cohen and Mario Geiger and Jonas Köhler and Max Welling , booktitle=. Spherical. 2018 , url=

    2018

  62. [62]

    International Conference on Learning Representations , year=

    Polar Transformer Networks , author=. International Conference on Learning Representations , year=

  63. [63]

    Proceedings of the european conference on computer vision (ECCV) , pages=

    Learning so (3) equivariant representations with spherical cnns , author=. Proceedings of the european conference on computer vision (ECCV) , pages=

  64. [64]

    Nature communications , volume=

    E (3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials , author=. Nature communications , volume=. 2022 , publisher=

    2022

  65. [65]

    International conference on Machine learning , pages=

    Gauge equivariant convolutional networks and the icosahedral CNN , author=. International conference on Machine learning , pages=. 2019 , organization=

    2019

  66. [66]

    Learning Multiple Layers of Features from Tiny Images , journal =

    Krizhevsky, Alex , year =. Learning Multiple Layers of Features from Tiny Images , journal =

  67. [67]

    Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education

    Clancey, William J. Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education. Proceedings of the Eighth International Joint Conference on Artificial Intelligence (IJCAI-83)

  68. [68]

    Classification Problem Solving

    Clancey, William J. Classification Problem Solving. Proceedings of the Fourth National Conference on Artificial Intelligence

  69. [69]

    , title =

    Robinson, Arthur L. , title =. 1980 , doi =. https://science.sciencemag.org/content/208/4447/1019.full.pdf , journal =

    1980

  70. [70]

    New Ways to Make Microcircuits Smaller---Duplicate Entry

    Robinson, Arthur L. New Ways to Make Microcircuits Smaller---Duplicate Entry. Science

  71. [71]

    Clancey and Glenn Rennels , abstract =

    Diane Warner Hasling and William J. Clancey and Glenn Rennels , abstract =. Strategic explanations for a diagnostic consultation system , journal =. 1984 , issn =. doi:https://doi.org/10.1016/S0020-7373(84)80003-6 , url =

    work page doi:10.1016/s0020-7373(84)80003-6 1984

  72. [72]

    and Rennels, Glenn R

    Hasling, Diane Warner and Clancey, William J. and Rennels, Glenn R. and Test, Thomas. Strategic Explanations in Consultation---Duplicate. The International Journal of Man-Machine Studies

  73. [73]

    Poligon: A System for Parallel Problem Solving

    Rice, James. Poligon: A System for Parallel Problem Solving

  74. [74]

    Transfer of Rule-Based Expertise through a Tutorial Dialogue

    Clancey, William J. Transfer of Rule-Based Expertise through a Tutorial Dialogue

  75. [75]

    The Engineering of Qualitative Models

    Clancey, William J. The Engineering of Qualitative Models

  76. [76]

    2017 , eprint=

    Attention Is All You Need , author=. 2017 , eprint=

    2017

  77. [77]

    Pluto: The 'Other' Red Planet

    NASA. Pluto: The 'Other' Red Planet