Paper statuses — A paper’s standing in the anthology: whether it is worth reading. NOT whether its findings are true. Adam is Active here because it is worth reading; whether any particular thing it recommends is still what you should do is the SOTA scheme’s business, and the two can disagree in either direction (ADR-002).
Unreviewed — in the corpus, not yet read closely enough to place.
10 of 737 LIT documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| LIT-364 | Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed | Refinetti et al. (2021), ARXIV-2102.11742. A two-layer network with a few hidden units beats kernel methods on a Gaussian-mixture classification task in the high-dimensional limit, which separates feature learning from lazy training. | Deferred |
| LIT-694 | Rigor with Machine Learning from Field Theory to the Poincaré Conjecture | Gukov et al. (2024), ARXIV-2402.13321. Stochastic, black-box ML can still yield rigorous results in mathematics and physics along two routes. The first is conjecture generation followed by human proof, or RL searches whose outputs can be checked exactly; this is how an RL/Bayesian-optimized ribbon verifier ruled out over 800 candidate counterexamples to the smooth 4D Poincaré conjecture. The second is importing ML theory, such as NNGP/NN-field-theory and gradient-descent metric flows that include Perelman’s Ricci flow. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-695 | Language Design as Information Renormalization | Gallego et al. (2022), ARXIV-1708.01525. The paper models Chomsky’s MERGE as a coarse-graining tensor, so that sentence probabilities form mostly loop-free stochastic tensor networks. It argues from this that tree-like syntax gives polynomially decaying (long-range) correlations. It then concludes that tree-structured networks (it names deep CNNs, as Tree Tensor Networks) fit language, while MPS-like models (RNNs, HMMs) with exponentially decaying correlations do not. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-697 | AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society | Piao et al. (2025), ARXIV-2502.08691. The paper presents a simulator of about 10k LLM-driven agents in a realistic urban, social and economic environment. It claims that the simulator’s outcomes on polarization, inflammatory-message spread, UBI, hurricane mobility shocks and urban sustainability qualitatively match real-world empirical findings, which would make it usable as a testbed for social science. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-698 | Topos and Stacks of Deep Neural Networks | Belfiore et al. (2021), ARXIV-2106.14587. The authors claim that every DNN architecture defines a Grothendieck topos of sheaves over a site built from its graph, that backpropagation is a flow of morphisms in that topos, and that layer invariances (CNN translations, LSTM structure) are stacks, and they conjecture that these stacks explain generalization and support a homological notion of “semantic information”. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-715 | Surya: Foundation Model for Heliophysics | Roy et al. (2025), ARXIV-2508.14112. A 366M-parameter transformer pretrained on full-resolution (4096²) multi-instrument SDO imagery to forecast the next frame, then rollout-tuned, forecasts solar dynamics zero-shot. With LoRA fine-tuning it beats task-specific baselines on four downstream heliophysics tasks. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-716 | The Impact of Generative AI on Social Media: An Experimental Study | Møller et al. (2025), ARXIV-2506.14295. In a randomized experiment with 680 US participants, generative-AI writing aids raised engagement and output on a simulated social platform but lowered perceived quality and authenticity, with negative spill-over into threads, and no single tool improved both producer and consumer experience. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-717 | Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task | Kosmyna et al. (2025), ARXIV-2506.08872. In a small four-month EEG study, participants who wrote essays with ChatGPT showed the weakest brain connectivity, the lowest sense of ownership and the worst recall of their own essays. Those switched from ChatGPT to no tools stayed under-engaged, which the authors call accumulated “cognitive debt”. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-718 | Automated decision-making as domination | Burrell (2024), DOI-10.5210/fm.v29i4.13630. Defining algorithmic injustice as allocative unfairness is a product of computer science’s status and funding, not of the harms themselves. Redefining it as domination, following Iris Marion Young, widens the remedies from code fixes to law, participation, resistance and bans. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |
| LIT-719 | Discovering cognitive strategies with tiny recurrent neural networks | Ji-An et al. (2023), DOI-10.1038/s41586-025-09142-4. GRUs with only 1–4 units predict individual animals’ and humans’ choices in six reward-learning tasks better than 30+ classical cognitive models of the same dimensionality. Because they are so small, they can be read as dynamical systems, exposing strategies (state-dependent learning rates, perseveration, reward-induced indifference) that no classical model contains. | Deferred — seeded from the abstract and a skim on 2026-09-25; not read in full |