# Sources | The Intent Layer

Source: https://setu-labs.co/manifesto-sources.html

> The 62 sources behind The Intent Layer, a manifesto from Setu.

[Download PDF ](https://setu-labs.co/assets/setu-the-intent-layer.pdf)

## Sources and further reading

Quantitative claims were checked against the abstracts of the primary publications in October 2026. Preprints are marked and have not completed peer review. Entries 1, 17, 30, 59, 60, 61 and 62 are cited from the published record without being re-fetched during that check.

1. Dhakal V, Feit AM, Kristensson PO, Oulasvirta A. Observations on typing from 136 million keystrokes. *Proc. CHI* (2018). [doi:10.1145/3173574.3174220](https://doi.org/10.1145/3173574.3174220)

2. Coupé C, Oh YM, Dediu D, Pellegrino F. Different languages, similar encoding efficiency. *Science Advances* 5, eaaw2594 (2019). [doi:10.1126/sciadv.aaw2594](https://doi.org/10.1126/sciadv.aaw2594)

3. Zheng J, Meister M. The unbearable slowness of being: why do we live at 10 bits/s? *Neuron* 113 (2025; online 2024). [doi:10.1016/j.neuron.2024.11.008](https://doi.org/10.1016/j.neuron.2024.11.008)

4. Wolpaw JR et al. Brain–computer interfaces for communication and control. *Clinical Neurophysiology* 113, 767–791 (2002). [doi:10.1016/S1388-2457(02)00057-3](https://doi.org/10.1016/S1388-2457(02)00057-3)

5. Vidal JJ. Toward direct brain–computer communication. *Annual Review of Biophysics and Bioengineering* 2, 157–180 (1973). [doi:10.1146/annurev.bb.02.060173.001105](https://doi.org/10.1146/annurev.bb.02.060173.001105)

6. Willett FR et al. High-performance brain-to-text communication via handwriting. *Nature* 593, 249–254 (2021). [nature.com/articles/s41586-021-03506-2](https://www.nature.com/articles/s41586-021-03506-2)

7. Metzger SL et al. A high-performance neuroprosthesis for speech decoding and avatar control. *Nature* 620, 1037–1046 (2023). [nature.com/articles/s41586-023-06443-4](https://www.nature.com/articles/s41586-023-06443-4)

8. Willett FR et al. A high-performance speech neuroprosthesis. *Nature* 620, 1031–1036 (2023). [nature.com/articles/s41586-023-06377-x](https://www.nature.com/articles/s41586-023-06377-x)

9. Card NS et al. An accurate and rapidly calibrating speech neuroprosthesis. *New England Journal of Medicine* 391, 609–618 (2024). [doi:10.1056/NEJMoa2314132](https://doi.org/10.1056/NEJMoa2314132)

10. Moses DA et al. Neuroprosthesis for decoding speech in a paralyzed person with anarthria. *New England Journal of Medicine* 385, 217–227 (2021). [doi:10.1056/NEJMoa2027540](https://doi.org/10.1056/NEJMoa2027540)

11. Tang J, LeBel A, Jain S, Huth AG. Semantic reconstruction of continuous language from non-invasive brain recordings. *Nature Neuroscience* 26, 858–866 (2023). [nature.com/articles/s41593-023-01304-9](https://www.nature.com/articles/s41593-023-01304-9)

12. Scotti PS et al. Reconstructing the mind’s eye: fMRI-to-image with contrastive learning and diffusion priors. *NeurIPS* (2023). [arXiv:2305.18274](https://arxiv.org/abs/2305.18274)

13. Scotti PS et al. MindEye2: shared-subject models enable fMRI-to-image with 1 hour of data. *ICML*, PMLR 235 (2024). [proceedings.mlr.press/v235/scotti24a](https://proceedings.mlr.press/v235/scotti24a.html)

14. Gong Z et al. NeuroClips: towards high-fidelity and smooth fMRI-to-video reconstruction. *NeurIPS* (2024, oral). [arXiv:2410.19452](https://arxiv.org/abs/2410.19452)

15. Lévy J et al. Brain-to-text decoding: a non-invasive approach via typing. Preprint (2025). [arXiv:2502.17480](https://arxiv.org/abs/2502.17480)

16. Zhang M et al. Accurate decoding of natural sentences from non-invasive brain recordings. Preprint (June 2026). [ai.meta.com/research/publications](https://ai.meta.com/research/publications/accurate-decoding-of-natural-sentences-from-non-invasive-brain-recordings)

17. Défossez A et al. Decoding speech perception from non-invasive brain recordings. *Nature Machine Intelligence* 5, 1097–1107 (2023). [doi:10.1038/s42256-023-00714-5](https://doi.org/10.1038/s42256-023-00714-5)

18. Gaddy D, Klein D. Digital voicing of silent speech. *Proc. EMNLP* (2020). [aclanthology.org/2020.emnlp-main.445](https://aclanthology.org/2020.emnlp-main.445/)

19. Kaifosh P, Reardon TR, CTRL-labs at Reality Labs. A generic non-invasive neuromotor interface for human–computer interaction. *Nature* 645 (2025). [doi:10.1038/s41586-025-09255-w](https://doi.org/10.1038/s41586-025-09255-w)

20. Hochberg LR et al. Reach and grasp by people with tetraplegia using a neurally controlled robotic arm. *Nature* 485, 372–375 (2012). [doi:10.1038/nature11076](https://doi.org/10.1038/nature11076)

21. Flesher SN et al. A brain–computer interface that evokes tactile sensations improves robotic arm control. *Science* 372, 831–836 (2021). [doi:10.1126/science.abd0380](https://doi.org/10.1126/science.abd0380)

22. Edelman BJ et al. Noninvasive neuroimaging enhances continuous neural tracking for robotic device control. *Science Robotics* 4, eaaw6844 (2019). [doi:10.1126/scirobotics.aaw6844](https://doi.org/10.1126/scirobotics.aaw6844)

23. Lorach H et al. Walking naturally after spinal cord injury using a brain–spine interface. *Nature* 618, 126–133 (2023). [doi:10.1038/s41586-023-06094-5](https://doi.org/10.1038/s41586-023-06094-5)

24. Mitchell P et al. Assessment of safety of a fully implanted endovascular brain–computer interface for severe paralysis in 4 patients. *JAMA Neurology* 80, 270–278 (2023). [doi:10.1001/jamaneurol.2022.4847](https://doi.org/10.1001/jamaneurol.2022.4847)

25. Kunz EM et al. Inner speech in motor cortex and implications for speech neuroprostheses. *Cell* 188 (2025). [doi:10.1016/j.cell.2025.06.015](https://doi.org/10.1016/j.cell.2025.06.015)

26. Kuruppu G et al. EEG foundation models: a critical review of current progress and future directions. Preprint (2025). [arXiv:2507.11783](https://arxiv.org/abs/2507.11783)

27. Liu D et al. EEG-FM-Compass: progress, benchmarking, and future directions for EEG foundation models. Preprint (2026); journal reference *National Science Review*. [arXiv:2601.17883](https://arxiv.org/abs/2601.17883)

28. Nunes de Oliveira JM et al. Scaling laws for EEG decoding: how much data is enough? Preprint (September 2026). [arXiv:2609.35056](https://arxiv.org/abs/2609.35056)

29. Allen EJ et al. A massive 7T fMRI dataset to bridge cognitive neuroscience and artificial intelligence. *Nature Neuroscience* 25, 116–126 (2022). [doi:10.1038/s41593-021-00962-x](https://doi.org/10.1038/s41593-021-00962-x)

30. Boto E et al. Moving magnetoencephalography towards real-world applications with a wearable system. *Nature* 555, 657–661 (2018). [doi:10.1038/nature26147](https://doi.org/10.1038/nature26147)

31. Yuste R et al. Four ethical priorities for neurotechnologies and AI. *Nature* 551, 159–163 (2017). [doi:10.1038/551159a](https://doi.org/10.1038/551159a)

32. UNESCO. Recommendation on the Ethics of Neurotechnology. Adopted by the General Conference, November 2025. [unesco.org/en/ethics-neurotech](https://www.unesco.org/en/ethics-neurotech)

33. Republic of Chile. Law 21.383, amending Article 19 of the Constitution to protect mental integrity and brain activity in the face of neurotechnology (2021). [bcn.cl/leychile](https://www.bcn.cl/leychile/navegar?idNorma=1166983)

34. Banville H, Benchetrit Y, d’Ascoli S, Rapin J, King J-R. Scaling laws for decoding images from brain activity. Preprint (2025). [arXiv:2501.15322](https://arxiv.org/abs/2501.15322)

35. Fan C et al. Plug-and-play stability for intracortical brain–computer interfaces: a one-year demonstration of seamless brain-to-text communication. *NeurIPS* 36, 42258–42270 (2023). [arXiv:2311.03611](https://arxiv.org/abs/2311.03611)

36. Karpowicz BM et al. Stabilizing brain–computer interfaces through alignment of latent dynamics. *Nature Communications* 16, 4662 (2025). [doi:10.1038/s41467-025-59652-y](https://doi.org/10.1038/s41467-025-59652-y)

37. Degenhart AD et al. Stabilization of a brain–computer interface via the alignment of low-dimensional spaces of neural activity. *Nature Biomedical Engineering* 4, 672–685 (2020). [doi:10.1038/s41551-020-0542-9](https://doi.org/10.1038/s41551-020-0542-9)

38. Orsborn AL et al. Closed-loop decoder adaptation shapes neural plasticity for skillful neuroprosthetic control. *Neuron* 82, 1380–1393 (2014). [doi:10.1016/j.neuron.2014.04.048](https://doi.org/10.1016/j.neuron.2014.04.048)

39. Perdikis S, Tonin L, Saeedi S, Schneider C, Millán JdR. The Cybathlon BCI race: successful longitudinal mutual learning with two tetraplegic users. *PLoS Biology* 16, e2003787 (2018). [doi:10.1371/journal.pbio.2003787](https://doi.org/10.1371/journal.pbio.2003787)

40. Azabou M et al. A unified, scalable framework for neural population decoding. *NeurIPS* (2023). [arXiv:2310.16046](https://arxiv.org/abs/2310.16046)

41. Jiang W-B, Zhao L-M, Lu B-L. Large brain model for learning generic representations with tremendous EEG data in BCI. *ICLR* (2024). [arXiv:2405.18765](https://arxiv.org/abs/2405.18765)

42. Radford A et al. Robust speech recognition via large-scale weak supervision. Preprint (2022). [arXiv:2212.04356](https://arxiv.org/abs/2212.04356)

43. Villalobos P et al. Will we run out of data? Limits of LLM scaling based on human-generated data. Preprint (2022, revised 2024). [arXiv:2211.04325](https://arxiv.org/abs/2211.04325)

44. Schrimpf M et al. The neural architecture of language: integrative modeling converges on predictive processing. *PNAS* 118, e2105646118 (2021). [doi:10.1073/pnas.2105646118](https://doi.org/10.1073/pnas.2105646118)

45. Goldstein A et al. Shared computational principles for language processing in humans and deep language models. *Nature Neuroscience* 25, 369–380 (2022). [doi:10.1038/s41593-022-01026-4](https://doi.org/10.1038/s41593-022-01026-4)

46. Li Z et al. Learning from brains how to regularize machines. *NeurIPS* (2019). [arXiv:1911.05072](https://arxiv.org/abs/1911.05072)

47. Moussa O, Klakow D, Toneva M. Improving semantic understanding in speech language models via brain-tuning. *ICLR* (2025). [arXiv:2410.09230](https://arxiv.org/abs/2410.09230)

48. Chavarriaga R, Sobolewski A, Millán JdR. Errare machinale est: the use of error-related potentials in brain–machine interfaces. *Frontiers in Neuroscience* 8, 208 (2014). [doi:10.3389/fnins.2014.00208](https://doi.org/10.3389/fnins.2014.00208)

49. Iturrate I et al. Teaching brain–machine interfaces as an alternative paradigm to neuroprosthetics control. *Scientific Reports* 5, 13893 (2015). [doi:10.1038/srep13893](https://doi.org/10.1038/srep13893)

50. O’Sullivan JA et al. Attentional selection in a cocktail party environment can be decoded from single-trial EEG. *Cerebral Cortex* 25, 1697–1706 (2015). [doi:10.1093/cercor/bht355](https://doi.org/10.1093/cercor/bht355)

51. Ngo H-VV, Martinetz T, Born J, Mölle M. Auditory closed-loop stimulation of the sleep slow oscillation enhances memory. *Neuron* 78, 545–553 (2013). [doi:10.1016/j.neuron.2013.03.006](https://doi.org/10.1016/j.neuron.2013.03.006)

52. Biasiucci A et al. Brain-actuated functional electrical stimulation elicits lasting arm motor recovery after stroke. *Nature Communications* 9, 2421 (2018). [doi:10.1038/s41467-018-04673-z](https://doi.org/10.1038/s41467-018-04673-z)

53. Cervera MA et al. Brain–computer interfaces for post-stroke motor rehabilitation: a meta-analysis. *Annals of Clinical and Translational Neurology* 5, 651–663 (2018). [doi:10.1002/acn3.544](https://doi.org/10.1002/acn3.544)

54. Cortese S et al. Neurofeedback for attention-deficit/hyperactivity disorder: meta-analysis of clinical and neuropsychological outcomes from randomized controlled trials. *J. Am. Acad. Child Adolesc. Psychiatry* 55, 444–455 (2016). [doi:10.1016/j.jaac.2016.03.007](https://doi.org/10.1016/j.jaac.2016.03.007)

55. Dorkenwald S et al. Neuronal wiring diagram of an adult brain. *Nature* 634, 124–138 (2024). [doi:10.1038/s41586-024-07558-y](https://doi.org/10.1038/s41586-024-07558-y)

56. Huth AG et al. Natural speech reveals the semantic maps that tile human cerebral cortex. *Nature* 532, 453–458 (2016). [doi:10.1038/nature17637](https://doi.org/10.1038/nature17637)

57. Hebart MN et al. THINGS-data, a multimodal collection of large-scale datasets for investigating object representations in human brain and behavior. *eLife* 12, e82580 (2023). [doi:10.7554/eLife.82580](https://doi.org/10.7554/eLife.82580)

58. Obeid I, Picone J. The Temple University Hospital EEG data corpus. *Frontiers in Neuroscience* 10, 196 (2016). [doi:10.3389/fnins.2016.00196](https://doi.org/10.3389/fnins.2016.00196)

59. Deng J et al. ImageNet: a large-scale hierarchical image database. *Proc. CVPR* (2009). [doi:10.1109/CVPR.2009.5206848](https://doi.org/10.1109/CVPR.2009.5206848)

60. Azevedo FAC et al. Equal numbers of neuronal and nonneuronal cells make the human brain an isometrically scaled-up primate brain. *Journal of Comparative Neurology* 513, 532–541 (2009). [doi:10.1002/cne.21974](https://doi.org/10.1002/cne.21974)

61. Sutton R. The bitter lesson. Essay (2019). [incompleteideas.net](http://www.incompleteideas.net/IncIdeas/BitterLesson.html)

62. Neurorights Foundation. Safeguarding brain data: assessing the privacy practices of consumer neurotechnology companies. Report (2024). [Report (PDF)](https://perseus-strategies.com/wp-content/uploads/2024/04/FINAL_Consumer_Neurotechnology_Report_Neurorights_Foundation_April-1.pdf)