large language models

Genesis Cube or Squid Cube? A Dual-Use Framework for Artificial Collective Organisms

Large-language-model agents can be combined into persistent systems with differentiated roles, memory, coordination, tools and operational continuity. Yet aggregation, scale and commercial productivity alone do not create an organism. This paper introduces the concept of the artificial collective organism: a bounded di...

TCGA_brest_extraction

# Structured extraction of breast cancer pathology reports by five large language models (TCGA cohort) ## Description This dataset accompanies the manuscript *"Secure large language models for structured breast cancerpathology extraction: a consensus- and embedding-based evaluation"* (Astruc et al., manuscript inprepar...

The prose penalty in AI-assisted authorship

Generative AI based on large language models (LLMs) is increasingly used in academic, journalistic, and other professional and online writing, yet its implications for human authorship remain contested. We asked whether assignment of authorship credit depends on which task within the larger writing process a writer del...

Light Is Gathered by a Gravitational Lens, Yet the Curvature of the Geometry It Travels In Is Negative ── The deflection is the curvature integrated over the region outside the ray, by the Gauss-Bonnet theorem: tracing the ray gives 4.011823809924e−3 and the outside integral 4.000000000000e−3. Integrating inside diverges ── the separator is whether the region lies inside or outside the ray ── [Paper 1044]

Gravity bends light and gathers it as a lens does. Yet measure the curvature of the very geometry that light travels in, and it is negative. This paper counts that discrepancy as a difference in the region of integration. No new theorem and no new law is claimed. Scope of this paper (scope note): No new theorem and no...

Slicing a Light Sphere by Another Frame's Simultaneity Gives an Ellipse of Eccentricity β with the Emission Point at a Focus ── The radius in each direction is exactly the Doppler factor for that direction, the two vertices are k and 1/k, the semi-major axis is γ, the semi-minor axis is cT, and the centre is where the moving observer stands ── the separator is whose simultaneity does the cutting ── [Paper 1036]

Light emitted at the origin is said to spread as a sphere in every frame. This paper counts what comes out when that sphere is cut by the simultaneity of another frame. No new theorem and no new law is claimed. Scope of this paper (scope note): No new theorem and no new law is claimed──the Lorentz transformation, the i...

The Same 19.471221 Degrees Arises from Two Distinct Roots ── the half-angle of a ship's wake, arcsin(1/3)=19.471221 degrees, is a constant containing no speed, while the Mach angle arcsin(1/M) reaches the same value at the single point M=3 ── [Paper 515]

When two angles agree, one mechanism is readily assumed to be at work. This paper shows that 19.471221 degrees arises for two separate reasons──one independent of speed, the other taking that value only at M=3. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the Kel...

Longitudinal and Transverse Belong to the Field; x and y Belong to the Coordinates ── rotating the coordinates leaves the longitudinal share at 0.647222222222 without moving a digit, while the x share moves with every rotation ── both are called "splitting the field in two", and only one of them belongs to the field ── [Paper 517]

There are many ways to split a vector field in two. What this paper shows is that which of them belongs to the field and which to the coordinates can be measured by rotating the coordinates. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the Helmholtz decomposition...

Evaluating Mathematical Reasoning in Large Language Models: A Comprehensive Analysis of Prompting Strategies on the Google DeepMind Mathematics Dataset

Photon Condensation Beyond Spacetime: A Higher-Dimensional Geometric Model for Dark Matter, Dark Energy, and Early Universe Anomalies via Van Hove Saddles

TITLE: Photon Condensation Beyond Spacetime: A Higher-Dimensional Geometric Metric Framework via M4 and M5 Morse Saddles DESCRIPTION: This work presents an independent geometric framework and formal cosmological supplement that addresses contemporary astrophysical anomalies without postulating hypothetical dark sector...

The Size of the Falling Box in Which Gravity Cannot Be Told Is Set Not by Physics but by the Precision of the Instrument ── the difference in gravity between the top and bottom of the box is the tidal gradient 2GM/r³ times the height, and the height at which the box gives gravity away is precision divided by gradient: at the Earth's surface 3.243790 mm for a precision of 10⁻⁸ m/s² and 3.243790 μm for 10⁻¹¹, at the horizon of a solar-mass black hole 9.709164×10⁻¹⁹ m, and at the horizon of a billion solar masses 0.9709164 m ── the separator is whether what shrinks the box is precision or gradient ── [Paper 1029]

Einstein called the idea that gravity vanishes inside a falling box the happiest thought of his life. But gravity differs between the top and bottom of the box, by the tidal gradient times the height, and with a fine enough instrument gravity can be told in any box. This paper counts that difference and the box height...

Three Separate Answers Are All Decided Where Something Is Tangent ── The Legendre transform's contact point solves f'(x)=p, giving x=2.500000 and a conjugate of 6.250000 at p=5 ── the common tangent touches at v=+/-1 with slope 0.300000000, and between them the curve falls below it at 0 points ── [Paper 507]

A transform, a bound and a phase coexistence are taken to be separate tools. This paper shows that all three have their answers decided where something is tangent──the location of the contact point is the answer. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the L...

Semantically-Guided LLM Pipeline for Business Architecture Modelling with Incremental Knowledge Acquisition