Reading statuses — How deeply the paper was READ — not whether it is any good, which is lit-statuses. The two disagree in every direction: a foundational paper can carry a Skimmed note, and a paper in the attic can carry a Read one, since reading it carefully is often how it got there (ADR-025).
Skimmed — abstract, figures and selected sections; honest, useful, and explicitly not enough to source a practice from.
12 of 378 NOTE documents. Back to the full index.
| # | Title | Summary | Status |
|---|---|---|---|
| NOTE-054 | Mish: A Self Regularized Non-Monotonic Activation Function | Proposes f(x) = x·tanh(softplus(x)), a smooth non-monotonic activation in the Swish family. Reported +2.1 AP50 over Leaky ReLU on YOLOv4/MS-COCO and ~1% top-1 over ReLU on ResNet-50/ImageNet. Read from the abstract only — ar5iv has no rendering for this identifier. | Skimmed |
| NOTE-074 | Advances and Open Problems in Federated Learning | A 66,000-word multi-institution survey defining federated learning and cataloguing its open problems. Its durable contribution to this record is the cross-device / cross-silo distinction, which separates two settings with almost nothing in common operationally. | Skimmed |
| NOTE-207 | Contextures: The Mechanism of Representation Learning | A representation is the association between the input and a context variable; capturing its maximum information is optimal on tasks compatible with that context. A context is most useful when the association is neither too strong nor too weak, and mixing contexts is offered as the cheap way to get there. Skimmed: a 313k-character dissertation, read at summary level. | Skimmed |
| NOTE-352 | Language Design as Information Renormalization | 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. | Skimmed |
| NOTE-354 | AgentSociety | 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. | Skimmed |
| NOTE-355 | Topos and Stacks of Deep Neural Networks | 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”. | Skimmed |
| NOTE-356 | Rigor with Machine Learning from Field Theory to the Poincaré Conjecture | 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. | Skimmed |
| NOTE-373 | Tiny RNNs discover cognitive strategies | 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. | Skimmed |
| NOTE-374 | Your Brain on ChatGPT (cognitive debt) | 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”. | Skimmed |
| NOTE-375 | Burrell: automated decision-making as domination | 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. | Skimmed |
| NOTE-376 | Surya: heliophysics foundation model | 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. | Skimmed |
| NOTE-377 | Generative AI on social media: an experiment | 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. | Skimmed |