References

CheungPruning

N. Cheung, Phased pruning in neural networks recapitulates selectivity–fragility trade-offs in brain development. Scientific Reports (2026). Published online 13 July 2026. https://doi.org/10.1038/s41598-026-62244-5.

CheungSupplied067A

N. Cheung, 067a_code_sub_v2.py and Combined 067A Num v3 (1).docx. Source code, version 9.3, and numerical manuscript supplied for the present analysis, undated. These supplied snapshots, rather than an unspecified later repository version, define the static audit.

CheungRepository

N. Cheung, Phased-Pruning-in-Neural-Networks-in-Brain-Development. Public project repository. https://github.com/cheungngo/Phased-Pruning-in-Neural-Networks-in-Brain-Development. A mutable repository; no unexamined revision is identified with the supplied source snapshot.

CheungPolygenic

N. Cheung, Polygenic dissection of synaptic pruning and glutamatergic signaling: contrasting mechanisms in ASD and ADHD. Preprints.org, version 1, posted 9 January 2026. Not peer reviewed. https://doi.org/10.20944/preprints202601.0692.v1.

CheungTiming

N. Cheung, Timing is everything: why the Cheung glutamatergic regimen is contraindicated in young children with autism but promising after puberty. Preprints.org, version 1, posted 2 December 2025. Hypothesis manuscript; not peer reviewed. https://doi.org/10.20944/preprints202512.0074.v1. Cited as developmental motivation, not as therapeutic evidence established by this paper.

CheungCliff

N. Cheung, The synaptic pruning cliff: threshold-like network fragility under internal stress and efficient recovery in a computational model of depression. Preprints.org, version 1, posted 13 January 2026. Not peer reviewed. https://doi.org/10.20944/preprints202601.0805.v1.

CheungEm06A

N. Cheung, One declared classical-limit package for a relational observable, and the stops it does not close: Em06-A, a scalar-only coherent limit of the first plateau coefficient. Manuscript Em06-A-v1.tex, version 1, undated. Enter Calculus Companion. https://enter.grok.me/browse/Em06-A. Documentary and methodological comparison; not a premise of the neural-network theorems.

CheungEm06B

N. Cheung, Manuscript Em06-B. Em06-B-v1.tex, version 1, undated. Supplied excerpt: “Ordered Weyl expectations and their classical limit,” thm:ordered, eq:ordered-general, eq:ordered-bound, and eq:ordered-vacuum, lines 991–1045. The quoted quantum result is not identified with a surviving-edge theorem. No unexamined version is assumed.

CheungVIIH

N. Cheung, Landmark VII-H: Normalization-independent connected quantum responses: complete ambiguity, observable descent, and a nonzero free-field benchmark. Manuscript VII-H.tex, version 1, undated. Enter Calculus Companion. https://enter.grok.me/browse/VII-H. A separate free Wick-square benchmark, not a network cue-interference model.

CheungVIII

N. Cheung, Landmark VII-I: Finite-time harmonic-coordinate insertions: three repair routes, finite-width free products, and sharp-prescription incompatibility. Manuscript VII-I.tex, version 1, undated. Enter Calculus Companion. https://enter.grok.me/browse/VII-I.

CheungVIIJ

N. Cheung, Manuscript VII-J. VII-J.tex, version 1, undated. Supplied excerpt: “The complete timed dependency network—scheduled ancestors,” example “A scheduled path with no surviving signal,” lines 541–547. Cited for the distinction between scheduled reachability and actual influence, not for an unprovided pruning theorem.

QianKlabjan

X. Qian and D. Klabjan, A probabilistic approach to neural network pruning. In Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research 139 (2021), 8640–8649. https://proceedings.mlr.press/v139/qian21a.html.

Koyuncu

E. Koyuncu, Theoretical guarantees for one-shot magnitude pruning and compute-adaptive early exit. In Proceedings of the 43rd International Conference on Machine Learning, Proceedings of Machine Learning Research 306 (2026), 60904–60947. https://proceedings.mlr.press/v306/koyuncu26a.html.

FrankleCarbin

J. Frankle and M. Carbin, The lottery ticket hypothesis: finding sparse, trainable neural networks. International Conference on Learning Representations (2019). https://openreview.net/forum?id=rJl-b3RcF7.

Tropp

J. A. Tropp, User-friendly tail bounds for sums of random matrices. Foundations of Computational Mathematics 12 (2012), 389–434. https://doi.org/10.1007/s10208-011-9099-z.

Tsuzuku

Y. Tsuzuku, I. Sato, and M. Sugiyama, Lipschitz-margin training: scalable certification of perturbation invariance for deep neural networks. Advances in Neural Information Processing Systems 31 (2018). https://arxiv.org/abs/1802.04034.

Cohen

J. Cohen, E. Rosenfeld, and J. Z. Kolter, Certified adversarial robustness via randomized smoothing. In Proceedings of the 36th International Conference on Machine Learning, Proceedings of Machine Learning Research 97 (2019), 1310–1320. https://proceedings.mlr.press/v97/cohen19c.html.

Hoeffding

W. Hoeffding, Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association 58, no. 301 (1963), 13–30.

EfronStein

B. Efron and C. Stein, The jackknife estimate of variance. The Annals of Statistics 9, no. 3 (1981), 586–596.

McDiarmid

C. McDiarmid, On the method of bounded differences. In J. Siemons, ed., Surveys in Combinatorics, 1989, London Mathematical Society Lecture Note Series 141, Cambridge University Press (1989), 148–188.

Tang

G. Tang et al., Loss of mTOR-dependent macroautophagy causes autistic-like synaptic pruning deficits. Neuron 83 (2014), 1131–1143. https://doi.org/10.1016/j.neuron.2014.07.040.

Matuskey

D. Matuskey et al., ${}^{11}\mathrm{C}$-UCB-J PET imaging is consistent with lower synaptic density in autistic adults. Molecular Psychiatry 30 (2025), 1610–1616. First published online 4 October 2024. https://doi.org/10.1038/s41380-024-02776-2.

Zielinski

B. A. Zielinski et al., Longitudinal changes in cortical thickness in autism and typical development. Brain 137 (2014), 1799–1812. https://doi.org/10.1093/brain/awu083.

PyTorchReproducibility

PyTorch Contributors, Reproducibility. Official PyTorch documentation. https://docs.pytorch.org/docs/main/notes/randomness.html. Software documentation; reproducibility claims remain version- and environment-specific.

PyTorchArgsort

PyTorch Contributors, torch.argsort. Official PyTorch documentation. https://docs.pytorch.org/docs/main/generated/torch.argsort.html. The stable=True option preserves the order of equal values.