We study how large transient inputs cause post-perturbation memory failure in small recurrent neural networks (RNNs), and whether spectral summaries of early hidden-state trajectories provide information beyond simpler time-domain descriptions. Mechanistically, each of three tanh memory RNNs contained two stable zero-i...
Sohan Poudel· Zenodo (CERN European Organi...· 0 citations
Determining earthquake magnitude and location through fast, automated methods is fundamental for seismic monitoring. Recent studies have shown that Large Language Models (LLMs) can operate as pattern‐recognition systems capable of handling novel domains and purely numerical tasks. Here, we assess the utility of LLMs...
A. Bassani, Daniele Trappolini, G. Poggiali et al.· Journal of Geophysical Resea...· 0 citations
Behavioural Friction Theory decomposes the forces that govern a bounded decision system into four cognitive fields — Safety, Meaning, Ability, Effort. Are these fields intrinsic to a substrate, or the generic product of its exposure to experience? This paper uses a large language model as a controllable test substrate...
Tomas Pødenphant Lund· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This archive contains the complete replication package, frozen DNA specifications, core execution scripts, and 400 training run logs supporting the manuscript: "Initialization DNA: Sparse Weight-Space Programs for Accelerating Small Transformer Language Model Training" (submitted to Pattern Recognition, PR-D-26-12736 R...
Terrence Yang· Zenodo (CERN European Organi...· 0 citations
The apparent wind of a sailing craft and the aberration of starlight are taught as separate matters. What this paper shows is that at low speed they are one and the same function, and that they part only where the rule for composing velocities changes. No new theorem or law is claimed. Scope of this paper (scope note):...
Yuuki Yamagishi· Zenodo (CERN European Organi...· 0 citations
Second public release. v0.1.0 wrote eight facts, one trigger each. This one writes a small world: one hundred facts about an invented character (Quail), learned from sentences that use them, and recalled by the real llama.cpp engine on sentences it never saw. What changed since v0.1.0 Usage-corpus descent. The variable...
fulvian· Zenodo (CERN European Organi...· 0 citations
We report a narrow, strongly-verified result: a governed semantic engine that discovers a missing internal control in a family of business processes by cross-process analogy — reproducibly, with a machine-checked repair, and without a single model call. The engine, SEMPL, represents each process as a small list of type...
Vladimir Mikhailov· Zenodo (CERN European Organi...· 0 citations
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. An agent that stores what happens to it must decide what is worth storing and, later, what is worth reading back. The most-copied mechanism for the first decision is a scalar written at storage time: a language model is shown a record and asked how important it is....
Pranay M. Mahendrakar· Zenodo (CERN European Organi...· 0 citations
(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0. An agent that stores what happens to it must decide what is worth storing and, later, what is worth reading back. The most-copied mechanism for the first decision is a scalar written at storage time: a language model is shown a record and asked how important it is....
Pranay M. Mahendrakar· Zenodo (CERN European Organi...· 0 citations
Herbal medicines constitute a chemically diverse source of bioactive molecules and remain important components of traditional and complementary healthcare systems. However, the development of reproducible pharmaceutical formulations from herbal materials is complicated by variability in botanical identity, geographical...
Herbal medicines constitute a chemically diverse source of bioactive molecules and remain important components of traditional and complementary healthcare systems. However, the development of reproducible pharmaceutical formulations from herbal materials is complicated by variability in botanical identity, geographical...
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
